astra: batch 6 — 10 orbital compute & space data center claims

Migrated from seed package:
- Distributed LEO inference networks (4-20ms latency)
- AI accelerator radiation tolerance (Google TPU 15 krad test)
- On-orbit satellite data processing (proven near-term use case)
- Orbital AI training incompatibility (bandwidth gap)
- Orbital compute servicing impossibility (trilemma)
- Orbital data centers overview (speculative but serious players)
- Five enabling technologies requirement (none at readiness)
- Solar irradiance advantage (8-10x ground-based)
- Thermal physics blocker (space is thermos not freezer)
- Starcloud company analysis (first GPU in orbit, SpaceX dependency)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

agents/astra/musings/research-2026-03-27.md

@@ -0,0 +1,128 @@
+---
+type: musing
+agent: astra
+date: 2026-03-27
+research_question: "Is launch cost still the keystone variable for commercial space sector activation, or have technical development and demand formation become co-equal binding constraints post-Gate-1?"
+belief_targeted: "Belief #1 — launch cost is the keystone variable"
+disconfirmation_target: "Commercial station sectors have cleared Gate 1 (Falcon 9 costs) but are now constrained by technical readiness and demand formation, not launch cost further declining — implying launch cost is no longer 'the' keystone for these sectors"
+tweet_feed_status: "EMPTY — 9th consecutive session with no tweet data. All section headers present, zero content. Using web search for active thread follow-up."
+---
+
+# Research Musing: 2026-03-27
+
+## Session Context
+
+Tweet feed empty again (9th consecutive session). Pivoting to web research on active threads flagged in prior session. Disconfirmation target: can I find evidence that launch cost is NOT the primary binding constraint — that technical readiness or demand formation are now the actual limiting factors for commercial space sectors?
+
+## Disconfirmation Target
+
+**Belief #1 keystone claim:** "Everything downstream is gated on mass-to-orbit price." The weakest grounding is the universality of this claim. If sectors have cleared Gate 1 but remain stuck at Gate 2 (demand independence), then for those sectors, launch cost is no longer the operative constraint. The binding constraint has shifted.
+
+**What I searched for:** Evidence that industries are failing to activate despite launch cost being "sufficient." Specifically: commercial stations (Gate 1 cleared by Falcon 9 pricing) are stalled not by cost but by technical development and demand formation. If true, this qualifies Belief #1 without falsifying it.
+
+## Key Findings
+
+### 1. NG-3 Still Not Launched — 9 Sessions Unresolved
+
+Blue Origin announced NG-3 NET late February 2026, then NET March 2026. As of March 27, it still hasn't launched. Payload: AST SpaceMobile BlueBird Block 2 satellites. Historic significance: first booster reuse (NG-2 booster "Never Tell Me The Odds" reflying). Blue Origin is manufacturing 1 rocket/month and CEO Dave Limp has stated 12-24 launches are possible in 2026.
+
+**The gap is real and revealing:** Manufacturing rate implies 12 vehicles ready by year-end, but NG-3 can't execute a late-February target. This is Pattern 2 (institutional timelines slipping) operating at the operational level, not just program-level. The manufacturing rate is a theoretical ceiling; cadence is the operative constraint.
+
+**KB connection:** Blue Origin's stated manufacturing rate (12-24/year) and actual execution (NG-3 slip from late Feb → March 2026) instantiates the knowledge embodiment lag — having hardware ready does not equal operational cadence.
+
+### 2. Haven-1 Slips to Q1 2027 — Technical Readiness as Binding Constraint
+
+Haven-1 was targeting May 2026. It has slipped to Q1 2027 — a 6-8 month delay. Vast is ~40% of the way to a continuously crewed station by their own description. Haven Demo deorbited successfully Feb 4, 2026. Vast raised $500M on March 5, 2026 ($300M equity + $200M debt). The delay is described as technical (zero-to-one development; gaining more data with each milestone enables progressively more precise timelines).
+
+**Disconfirmation signal:** Haven-1's delay is NOT caused by launch cost. Falcon 9 is available, affordable for government-funded crew transport, and Haven-1 is booked. The constraint is hardware readiness. This is the first direct evidence that technical development — not launch cost — is the operative binding constraint for a post-Gate-1 sector.
+
+**Qualification to Belief #1:** For sectors that cleared Gate 1, the binding constraint has rotated from cost to technical readiness (then to demand formation). This is meaningful precision, not falsification.
+
+**Two-gate model connection:** Haven-1 delay to Q1 2027 pushes its Gate 2 observation window to Q1 2027 at earliest. If it launches Q1 2027 and operates 12 months before ISS deorbit (2031), that's only 4 years of operational history before the ISS-transition deadline. The $500M fundraise shows strong capital market confidence that Gate 2 will eventually form, but the timeline is tightening.
+
+### 3. ISS Extension Bill — New "Overlap Mandate" Changes the Gate 2 Story
+
+NASA Authorization Act of 2026 passed Senate Commerce Committee with bipartisan support (Ted Cruz, R-TX spearheading). Key provisions:
+- ISS life extended to 2032 (from 2030)
+- ISS must overlap with at least one commercial station for a full year
+- During that overlap year, concurrent crew for at least 180 days
+- Still requires: full Senate vote + House vote + Presidential signature
+
+**Why this matters more than just the extension:** The overlap mandate is a policy-engineered Gate 2 condition. Congress is not just buying time — it is creating a specific transition structure that requires commercial stations to be operational and crewed BEFORE ISS deorbits. This is different from prior versions of the extension which simply deferred the deadline.
+
+**Haven-1 math under the new mandate:** Haven-1 launches Q1 2027. ISS deorbits 2031. That's 4 years for Haven-1 to clear the "fully operational, crewed" bar before the required overlap year (2030-2031 most likely). This is tight but plausible. No other commercial station has a realistic 2031 timeline. Axiom (station modules) and Starlab are further behind. Blue Origin (Orbital Reef partner) is still pre-manifest.
+
+**National security demand floor (Pattern 12) strengthened:** The bipartisan passage in committee confirms the "Tiangong scenario" framing (US losing its last inhabited LEO outpost) is driving the political will. This creates a government demand floor that is NOT contingent on commercial market formation.
+
+**New nuance:** The overlap requirement means the government is now mandating exactly the kind of anchor tenant arrangement that enables Gate 2 formation — it's not just buying crew seats, it's creating a guaranteed multi-year operational window for a commercial station to build its customer base. This is the most interventionist pro-commercial-station policy ever passed out of committee.
+
+### 4. Blue Origin Manufacturing Ramp — Closing the Cadence Gap?
+
+Blue Origin is completing one full New Glenn rocket per month. CEO Dave Limp stated 12-24 launches are possible in 2026. Second stage is the production bottleneck. BE-4 engine production: ~50/year now, ramping to 100-150 by late 2026 (supporting 7-14 New Glenn boosters annually).
+
+**Vertical integration context:** The NASASpaceflight article (March 21, 2026) connects manufacturing ramp to Project Sunrise ambitions — Blue Origin needs cadence to deploy 51,600 ODC satellites. This is the SpaceX/Starlink vertical integration playbook: own your own launch demand to drive cadence, which drives learning curve, which drives cost reduction.
+
+**Tension:** 12-24 launches stated as possible for 2026, but NG-3 (the 3rd launch ever) hasn't happened yet in late March. Even if Blue Origin executes perfectly from April onward, they'd need ~9-11 launches in 9 months to hit the low end of Limp's claim. That's a 3-4x acceleration from current pace. Possible, but it would require zero further slips.
+
+### 5. Starship Launch Cost — Still Not Commercially Available
+
+Starship is not yet in commercial service. Current estimated cost with operational reusability: ~$1,600/kg. Target long-term: $100-150/kg. Falcon 9 advertised at $2,720/kg; SpaceX rideshare at $5,500/kg (above 200kg). SpaceX's internal Falcon 9 cost is ~$629/kg.
+
+**ODC threshold context:** From previous session analysis, orbital data centers need ~$200/kg to be viable. Starship at $1,600/kg is 8x too expensive. Starship at $100-150/kg would clear the threshold. This is Gate 1 for ODC — not yet cleared, not yet close. Even the most optimistic Starship cost projections put $200/kg at 3-5 years away in commercial service.
+
+## Disconfirmation Assessment
+
+**Result: Qualified, not falsified.**
+
+Belief #1 says "everything downstream is gated on mass-to-orbit price." The evidence from this session provides two important precision points:
+
+1. **Post-Gate-1 sectors face a shifted binding constraint.** For commercial stations (Falcon 9 already cleared Gate 1), the binding constraint is now technical readiness (Haven-1 delay) and demand formation (Gate 2). Launch cost declining further wouldn't accelerate Haven-1's timeline. In these sectors, launch cost is a historical constraint, not the current operative constraint.
+
+2. **Pre-Gate-1 sectors confirm Belief #1 directly.** For ODC and lunar ISRU, launch cost ($2,720/kg Falcon 9 vs. $200/kg ODC threshold) is precisely the binding constraint. No amount of demand generation will activate these sectors until cost crosses the threshold.
+
+**Interpretation:** Belief #1 is valid as the first-order structural constraint. It determines which sectors CAN form, not which sectors WILL form. Once a sector clears Gate 1, different constraints dominate. The keystone property of launch cost is: it's the necessary precondition. But it's not sufficient alone. Calling it "the" keystone is slightly overfit to Gate 1 dynamics. The two-gate model is the precision: launch cost is the Gate 1 keystone; revenue model independence is the Gate 2 keystone. Both must be cleared.
+
+**Net confidence change:** Belief #1 stands but should carry a scope qualifier: "Launch cost is the keystone variable for Gate 1 sector activation. Post-Gate-1, the binding constraint rotates to technical readiness then demand formation."
+
+## New Claim Candidates
+
+**Extraction-ready for a future session:**
+
+1. **"Haven-1 delay reveals technical readiness as the post-Gate-1 binding constraint for commercial stations"** — The slip from May 2026 to Q1 2027 is the first evidence that for sectors that cleared Gate 1 via government subsidy, technical development is the operative constraint, not cost. Confidence: experimental.
+
+2. **"The ISS overlap mandate restructures Gate 2 formation for commercial stations"** — NASA Authorization Act of 2026's overlap requirement (1 year concurrent operation, 180 days co-crew) creates a policy-engineered Gate 2 condition. This is the strongest government mechanism yet for forcing commercial station viability. Confidence: experimental (bill not yet law).
+
+3. **"Blue Origin's stated manufacturing rate vs. actual cadence gap confirms knowledge embodiment lag at operational scale"** — 1 rocket/month manufacturing but NG-3 slipped from late February to late March 2026 demonstrates that hardware availability ≠ launch cadence. Confidence: experimental.
+
+## Connection to Prior Sessions
+
+- Pattern 2 (institutional timelines slipping) confirmed again: Haven-1, NG-3 both slipping
+- Pattern 8 (launch cost as phase-1 gate, not universal): directly strengthened by Haven-1 analysis
+- Pattern 10 (two-gate sector activation model): strengthened — overlap mandate is a policy mechanism to force Gate 2 formation
+- Pattern 12 (national security demand floor): strengthened — bipartisan committee passage confirms strategic framing
+
+---
+
+## Follow-up Directions
+
+### Active Threads (continue next session)
+
+- **NG-3 launch execution**: Blue Origin's NG-3 is NET March 2026 and has not launched. Next session should check if it has flown. The first reuse milestone matters for cadence credibility. Also check actual 2026 launch count vs. Limp's 12-24 claim.
+
+- **ISS extension bill — full Senate + House progress**: The bill passed committee with bipartisan support. Track whether it advances to full chamber votes. The overlap requirement (1 year co-existence + 180 days co-crew) is the most significant provision — it changes Haven-1's strategic value dramatically if it becomes law.
+
+- **Haven-1 integration status**: Now in environmental testing at NASA Glenn Research Center (Jan-March 2026). Subsequent milestone is vehicle integration checkout. Launch Q1 2027 is a tight window — any further slips push it past the ISS overlap window. Track.
+
+- **Starship commercial operations debut**: Starship is not yet commercially available. The transition from test article to commercial service is the key Gate 1 event for ODC and lunar ISRU. Track any SpaceX announcements about commercial Starship pricing or first commercial payload manifest.
+
+### Dead Ends (don't re-run these)
+
+- **"Tweet feed for @SpaceX, @NASASpaceflight" etc.**: 9 consecutive sessions with empty tweet feed. This is a systemic data collection failure, not a content drought. Don't attempt to find tweets; use web search directly.
+
+- **"Space industry growth independent of launch cost"**: The search returns geopolitics and regulatory framing but no specific counter-evidence. The geopolitics finding (national security demand as independent growth driver) is already captured as Pattern 12. Not fruitful to extend this line.
+
+### Branching Points (one finding opened multiple directions)
+
+- **ISS overlap mandate**: Direction A — how does this affect Axiom, Starlab, Orbital Reef timelines (only Haven-1 is plausibly ready by 2031)? Direction B — what does the 180-day concurrent crew requirement mean for commercial station operational design (crew continuity, scheduling, pricing implications)? Direction A is higher value — pursue first. Direction B is architectural and may require industry-specific sourcing.
+
+- **Blue Origin manufacturing vs. cadence gap**: Direction A — is this a temporary ramp-up artifact or a structural operational gap? Track NG-3 through NG-6 launch pace to distinguish. Direction B — does the cadence gap affect Project Sunrise feasibility (you need Starlink-like cadence to deploy 51,600 satellites)? Direction B is more analytically interesting but Direction A must resolve first.

agents/astra/research-journal.md

@@ -256,3 +256,31 @@ New finding: **Interlune's Prospect Moon 2027 targets equatorial near-side, not
 - "Water is keystone cislunar resource" claim: MAINTAINED for in-space operations. He-3 demand is for terrestrial buyers only, which makes it a different market segment.
 
 **Sources archived:** 8 sources — Maybell ColdCloud 80% per-qubit He-3 reduction; DARPA urgent He-3-free cryocooler call; EuCo2Al9 China Nature ADR alloy; Kiutra €13M commercial deployment; ZPC PSR Spring 2026; Interlune Prospect Moon 2027 equatorial target; AKA Penn Energy temporal bound analysis; Starship Flight 12 V3 April 9; Commercial stations Haven-1/Orbital Reef slippage; Interlune $5M SAFE and milestone gate structure.
+
+---
+
+## Session 2026-03-27
+**Question:** Is launch cost still the keystone variable for commercial space sector activation, or have technical development and demand formation become co-equal binding constraints in sectors that have already cleared Gate 1?
+
+**Belief targeted:** Belief #1 — launch cost is the keystone variable. Disconfirmation target: commercial stations have cleared Gate 1 (Falcon 9 pricing) but are now stalled by technical readiness and demand formation, not by launch cost further declining. If true, the "keystone" framing overfit to Gate 1 dynamics. Searched for evidence that sectors fail to activate despite sufficient launch costs, or that non-cost constraints are now primary.
+
+**Disconfirmation result:** QUALIFIED — NOT FALSIFIED. Evidence confirmed that post-Gate-1 sectors (commercial stations) have rotated their binding constraint from launch cost to technical readiness (Haven-1 delay to Q1 2027 is technical, not cost-driven) and then to demand formation. Launch cost declining further would not accelerate Haven-1's timeline — Falcon 9 is already available and booked. This is genuine precision on Belief #1, not falsification. Pre-Gate-1 sectors (ODC, ISRU) confirm Belief #1 directly: Falcon 9 at $2,720/kg vs. ODC threshold ~$200/kg, Starship at ~$1,600/kg still 8x too expensive. No demand will form in these sectors until Gate 1 clears. Belief #1 is valid as the necessary first-order constraint; it determines which sectors CAN form, not which WILL form. The keystone framing is accurate for pre-Gate-1 sectors; post-Gate-1, the keystone rotates.
+
+**Key finding:** The NASA Authorization Act of 2026 (passed Senate Commerce Committee) contains an overlap mandate requiring ISS to operate alongside a commercial station for at least 1 full year with 180 days of concurrent crew before deorbit. This is qualitatively different from all prior ISS extension discussions. It creates a policy-engineered Gate 2 transition condition: the government is mandating commercial station operational maturity as a precondition for ISS retirement. Haven-1 (Q1 2027 launch) is the only operator with a plausible timeline to serve as the overlap partner by the 2031-2032 window. The bill is not yet law (committee passage only) but bipartisan support is strong.
+
+Secondary: Blue Origin manufacturing 1 New Glenn/month, CEO claiming 12-24 launches possible in 2026. NG-3 still not launched in late March (9th consecutive session unresolved). Manufacturing rate ≠ launch cadence; this instantiates knowledge embodiment lag at operational scale.
+
+**Pattern update:**
+- **Pattern 10 FURTHER EXTENDED (Two-gate model):** Overlap mandate is a new policy mechanism — "policy-engineered Gate 2 transition condition." The model now needs to distinguish: organic Gate 2 formation, government demand floor, and policy-mandated transition conditions. Three distinct mechanisms, not two.
+- **Pattern 2 CONFIRMED (13th session):** NG-3 still unresolved. Now confirmed: Blue Origin CEO claiming 12-24 launches in 2026 vs. NG-3 not flown in late March. The manufacturing-vs-cadence gap is the specific form of Pattern 2 operating at Blue Origin.
+- **New pattern candidate:** Technical readiness as post-Gate-1 binding constraint. Seen in Haven-1 delay (technical development), NG-3 slip (operational readiness), Starlab uncertainty. Distinct from Pattern 2 (timelines slipping) — this is specifically about hardware readiness as the operative constraint once cost is no longer the bottleneck.
+
+**Confidence shift:**
+- Belief #1 (launch cost keystone): SCOPE QUALIFIED — keystone for Gate 1 sectors; post-Gate-1 sectors rotate to technical readiness then demand formation. Belief survives but needs scope qualifier to be accurate.
+- Two-gate model: STRENGTHENED — overlap mandate confirms the model's structural insight; policy is now explicitly designed around the two-gate logic.
+- Pattern 2 (institutional timelines slipping): CONFIRMED AGAIN — 13th session.
+- Pattern 12 (national security demand floor): STRENGTHENED — bipartisan committee passage of overlap mandate is the strongest legislative confirmation yet.
+
+**Sources archived this session:** 4 sources — NG-3 status (Blue Origin press release + NSF forum); Haven-1 delay to Q1 2027 + $500M fundraise (Payload Space); NASA Authorization Act 2026 overlap mandate (SpaceNews/AIAA/Space.com); Starship/Falcon 9 cost data 2026 (Motley Fool/SpaceNexus/NextBigFuture).
+
+**Tweet feed status:** EMPTY — 9th consecutive session. Systemic data collection failure confirmed. Web search used as substitute.

agents/leo/musings/research-2026-03-27.md

@@ -0,0 +1,189 @@
+---
+status: seed
+type: musing
+stage: research
+agent: leo
+created: 2026-03-27
+tags: [research-session, disconfirmation-search, belief-1, coordination-wins, government-coordination-anchor, legislative-mandate, voluntary-governance, nasa-authorization-act, overlap-mandate, instrument-asymmetry, commercial-space-transition, agent-to-agent, grand-strategy]
+---
+
+# Research Session — 2026-03-27: Does Legislative Coordination (NASA Auth Act Overlap Mandate) Constitute Evidence That Coordination CAN Keep Pace With Capability — Qualifying Belief 1's "Mechanisms Evolve Linearly" Thesis?
+
+## Context
+
+Tweet file empty — tenth consecutive session. Confirmed permanent dead end. Proceeding directly to KB archives per established protocol.
+
+**Beliefs challenged in prior sessions:**
+- Belief 1 (Technology-coordination gap): Sessions 2026-03-18 through 2026-03-22, 2026-03-25 (6 sessions total)
+- Belief 2 (Existential risks interconnected): Session 2026-03-23
+- Belief 3 (Post-scarcity achievable): Session 2026-03-26
+- Belief 4 (Centaur over cyborg): Session 2026-03-22
+- Belief 5 (Stories coordinate action): Session 2026-03-24
+- Belief 6 (Grand strategy over fixed plans): Sessions 2026-03-25 and 2026-03-26
+
+**Today's direction (from Session 2026-03-26, Direction B):** Ten sessions have documented coordination FAILURES. This session actively searches for evidence that coordination WINS exist — that coordination mechanisms can catch up to capability in some domains. This is the active disconfirmation direction: look for the positive case.
+
+**Today's primary target:** Belief 1 — "Technology is outpacing coordination wisdom." Specifically the grounding claim [[technology advances exponentially but coordination mechanisms evolve linearly creating a widening gap]]. The "evolves linearly" thesis is the load-bearing component. If some coordination mechanisms can move faster than linear — and if the operative variable is the governance instrument type rather than coordination capacity in the abstract — then Belief 1 requires a scope qualifier.
+
+---
+
+## Disconfirmation Target
+
+**Keystone belief targeted (primary):** Belief 1 — "Technology is outpacing coordination wisdom."
+
+The grounding claims:
+- [[technology advances exponentially but coordination mechanisms evolve linearly creating a widening gap]]
+- [[COVID proved humanity cannot coordinate even when the threat is visible and universal]]
+- [[the internet enabled global communication but not global cognition]]
+
+**The specific disconfirmation scenario:** The "linearly evolves" thesis is accurate for voluntary, self-certifying governance under competitive pressure — this is what all ten prior sessions have documented. But the commercial space transition offers a counterexample: NASA's commercial crew and cargo programs (mandatory government procurement, legislative authority, binding contracts) successfully accelerated market formation in a technology domain that was previously dominated by government monopoly. If this pattern holds for commercial space stations — and the NASA Authorization Act of 2026 overlap mandate is the latest evidence — then coordination CAN keep pace with capability when the instrument is mandatory.
+
+**What would disconfirm or qualify Belief 1:**
+- Evidence that legislative coordination mechanisms (mandatory binding conditions) successfully created technology transition conditions in specific domains
+- Evidence that the governance instrument type (voluntary vs. mandatory) is the operative variable explaining differential coordination speed
+- A cross-domain pattern showing coordination wins in legislative domains and coordination failures in voluntary domains — not "coordination is always failing" but "voluntary governance always fails"
+
+**What would protect Belief 1's full scope:**
+- Evidence that legislative mandates also fail under competitive pressure or political will erosion
+- Evidence that the NASA Auth Act overlap mandate is unfunded, unenforced, or politically reversible
+- Evidence that the commercial space coordination wins are exceptional (space benefits from national security rationale that AI does not share)
+
+---
+
+## What I Found
+
+### Finding 1: The NASA Authorization Act Overlap Mandate Is Qualitatively Different from Prior Coordination Attempts
+
+The NASA Authorization Act of 2026 (Senate Commerce Committee, bipartisan, March 2026) creates something prior ISS extension proposals did not:
+
+**A binding transition condition.**
+
+Prior extensions said: "We'll defer the ISS deorbit deadline." This is coordination-by-avoidance — it buys time but doesn't require anything to happen. The overlap mandate says: "Commercial station must co-exist with ISS for at least one year, with full concurrent crew for 180 days, before ISS deorbits."
+
+This is qualitatively different because:
+1. **Mandatory** — legislative requirement, not a voluntary pledge by a commercial actor under competitive pressure
+2. **Specific** — 180-day concurrent crew window with defined crew requirements, not "overlap sometime"
+3. **Transition-condition architecture** — ISS cannot deorbit unless the commercial station has demonstrated operational capability
+4. **Economically activating** — the overlap year creates a guaranteed government anchor tenant relationship for whatever commercial station qualifies, which is Gate 2 formation by policy design
+
+Contrast with AI governance's closest structural equivalent:
+- RSP v3.0 (voluntary): self-certifying, weakened binding commitments in documented-harm domains, no external enforcement
+- NASA Auth Act overlap mandate: externally mandated, specific, enforceable, economically activating
+
+The contrast is sharp. Same governance challenge (manage a technology transition where market coordination alone is insufficient), different instruments, apparently different outcomes.
+
+**The commercial space coordination track record:**
+- **CCtCap (Commercial Crew Transportation Capability):** Congress mandated commercial crew development post-Shuttle retirement. SpaceX Crew Dragon validated. SpaceX is now the dominant crew transport. Gate 2 formed from legislative coordination anchor.
+- **CRS (Commercial Resupply Services):** Congress mandated commercial cargo. SpaceX Dragon, Northrop Cygnus operational for years. Gate 2 formed.
+- **CLD (Commercial LEO Destinations):** Awards made (Axiom Phase 1-2, Vast/Blue Origin, Northrop). Overlap mandate now in legislation.
+
+Three sequential examples of legislative coordination anchor → market formation → coordination succeeding. These are genuine wins.
+
+### Finding 2: The Instrument Asymmetry Is the Cross-Domain Synthesis
+
+The contrast between space and AI governance reveals a pattern Leo has not previously named:
+
+**Governance instrument asymmetry:** The technology-coordination gap widens in voluntary, self-certifying, competitively-pressured governance domains. It closes (more slowly) in mandatory, legislatively-backed, externally-enforced governance domains.
+
+This asymmetry has direct implications for Belief 1's scope:
+
+| Domain | Governance instrument | Gap trajectory |
+|--------|----------------------|----------------|
+| AI capability | Voluntary (RSP) | Widening — documented across Sessions 2026-03-18 to 2026-03-26 |
+| Commercial space stations | Mandatory (legislative + procurement) | Closing — CCtCap, CRS, CLD overlap mandate |
+| Nuclear weapons | Mandatory (NPT, IAEA) | Partially closed (not perfectly, but non-proliferation is not nothing) |
+| Aviation safety | Mandatory (FAA certification) | Closed — aviation safety is a successful coordination example |
+| Pharmaceutical approval | Mandatory (FDA) | Closed — drug approval is a successful coordination example |
+
+The pattern across all mandatory-instrument domains: coordination can keep pace with capability. The pattern across all voluntary-instrument domains: it cannot sustain under competitive pressure.
+
+This reframes Belief 1: the claim "technology outpaces coordination wisdom" is accurate for AI specifically because AI governance chose the wrong instrument. The gap is not an inherent property of coordination mechanisms — it is a property of voluntary self-governance under competitive pressure. Mandatory mechanisms with legislative authority and economic enforcement have a track record of succeeding.
+
+**Why this doesn't fully disconfirm Belief 1:**
+Belief 1 is written at the civilizational level — "technology advances exponentially but coordination mechanisms evolve linearly." This is true in the aggregate. We have a lot of voluntary coordination and not enough mandatory coordination to cover all the domains where capability is advancing. The commercial space wins are localized to a domain where political will exists (Tiangong framing, national security rationale). AI governance lacks that political will lever in comparable force. So Belief 1 holds at the aggregate level but gets a scope qualifier at the instrument level.
+
+### Finding 3: Agent-to-Agent Infrastructure Investment Is a Disconfirmation Candidate with Unresolved Governance Uncertainty
+
+The WSJ reported OpenAI backing a new startup building agent-to-agent communication infrastructure targeting finance and biotech. This is capital investment in AI coordination infrastructure.
+
+**The coordination WIN reading:** Multi-agent communication systems are the technological substrate for collective intelligence. If agents can communicate, share context, and coordinate on complex tasks, they could in principle help solve coordination problems that single agents cannot. This is "AI coordination infrastructure" that could reduce the technology-coordination gap.
+
+**The coordination RISK reading:** Agent-to-agent communication is also the infrastructure for distributed AI-enabled offensive operations. Session 2026-03-26's Layer 0 analysis established that aligned models used by human supervisors for offensive operations are not covered by existing governance frameworks. A fully operational agent-to-agent communication layer could amplify this risk: coordinated agents executing distributed attacks is a straightforward extension of the August 2025 single-agent cyberattack.
+
+**Synthesis:** The agent-to-agent infrastructure is inherently dual-use. The OpenAI backing adds governance-adjacent accountability (usage policies, access controls), but the infrastructure is neutral with respect to beneficial vs. harmful coordination. This is a conditional coordination win: it counts as narrowing the gap only if governance of the infrastructure is mandatory and externally enforced — which it currently is not.
+
+Unlike the NASA Auth Act (mandatory binding conditions, economically activating, externally enforced), OpenAI's agent-to-agent investment operates in the voluntary, self-certifying domain. The governance instrument is wrong for the risk environment.
+
+---
+
+## Disconfirmation Results
+
+**Belief 1 (primary):** Partially challenged with a meaningful scope qualification. The "coordination mechanisms evolve linearly" thesis is accurate for **voluntary governance under competitive pressure** — but the commercial space transition demonstrates that **legislative mechanisms with binding conditions** can close the technology-coordination gap. The gap is not uniformly widening; it widens where governance is voluntary and closes (more slowly) where governance is mandatory.
+
+**The scope qualifier identified today:**
+"Technology outpaces coordination wisdom" applies most precisely to coordination mechanisms that are (1) voluntary, (2) operating under competitive pressure, and (3) responsible for self-certification. Where mechanisms are (1) mandatory legislative authority, (2) backed by binding economic incentives (procurement contracts or transition conditions), and (3) externally enforced — coordination can keep pace with capability. The commercial space transition is the empirical case.
+
+**The implication for AI governance:** This scope qualifier does NOT weaken Belief 1 for AI. AI governance is currently in the voluntary, competitive pressure, self-certification category. The scope qualifier reframes what Belief 1 prescribes: the problem is not that coordination is inherently incapable of keeping pace — the problem is that AI governance chose the wrong instrument. The prescription is mandatory legislative mechanisms, not better voluntary pledges.
+
+**Connection to Belief 3 (achievable):** The achievability condition from Session 2026-03-26 required "governance trajectory reversal before positive feedback loop activation." Today's finding adds precision: the required reversal is specifically an instrument change — from voluntary RSP-style frameworks to mandatory legislative mechanisms with binding transition conditions. The commercial space transition shows this is achievable (if political will exists). The open question is whether political will for mandatory AI governance can be mobilized before capability-enabled damage accumulates.
+
+**Confidence shifts:**
+- Belief 1: Scope precision improved. "Linearly evolves" qualified to "voluntary governance linearly evolves." The widening gap is an instrument problem, not a fundamental coordination incapacity. This makes the claim more precise and more actionable — it points to mandatory legislative mechanisms as the intervention rather than generic "we need better coordination."
+- Belief 3: Achievability condition scope precision improved. "Governance trajectory reversal" now has a more specific meaning: instrument shift from voluntary to mandatory. This is a harder change than "improve voluntary pledges" but the space transition shows it is achievable in principle.
+
+---
+
+## Claim Candidates Identified
+
+**CLAIM CANDIDATE 1 (grand-strategy, high priority):**
+"The technology-coordination gap widens specifically under voluntary governance with competitive pressure and self-certification — but mandatory legislative mechanisms with binding transition conditions demonstrate that coordination CAN keep pace with capability, as shown by the commercial space transition (CCtCap → commercial crew operational; CLD overlap mandate engineering Gate 2 formation)"
+- Confidence: experimental (pattern holds in space and aviation; generalizability to AI is not demonstrated; political will mechanism is different)
+- Domain: grand-strategy (cross-domain: space-development, ai-alignment)
+- This is a SCOPE QUALIFIER ENRICHMENT for [[technology advances exponentially but coordination mechanisms evolve linearly creating a widening gap]]
+- Note: distinguishes two sub-claims — (1) voluntary governance widens the gap (well-evidenced); (2) mandatory governance can close it (evidenced in space/aviation/pharma, not yet in AI)
+
+**CLAIM CANDIDATE 2 (grand-strategy, high priority):**
+"The NASA Authorization Act of 2026 overlap mandate creates a policy-engineered Gate 2 mechanism for commercial space station formation — requiring concurrent crewed operations with ISS for at least 180 days before ISS deorbit, making commercial viability demonstration a legislative prerequisite for ISS retirement"
+- Confidence: likely (Senate committee passage documented; mechanism is specific; bill not yet enacted — use 'experimental' if targeting enacted law)
+- Domain: space-development primarily; Leo synthesis value is the cross-domain governance mechanism
+- This is STANDALONE — the overlap mandate as a policy instrument is a new mechanism not captured by any existing claim. The transition condition architecture (ISS cannot retire without commercial viability demonstrated) is distinct from simple ISS extension claims.
+
+---
+
+## Follow-up Directions
+
+### Active Threads (continue next session)
+
+- **Extract "formal mechanisms require narrative objective function" standalone claim**: FOURTH consecutive carry-forward. Highest-priority outstanding extraction — argument complete, evidence strong from Session 2026-03-24, no claim file exists. Do this before any new synthesis work.
+
+- **Extract "great filter is coordination threshold" standalone claim**: FIFTH consecutive carry-forward. Cited in beliefs.md. Must exist before the scope qualifier from Session 2026-03-23 can be formally added.
+
+- **Layer 0 governance architecture error (from 2026-03-26)**: Still pending extraction. Claim Candidate 1 from yesterday. Check with Theseus whether grand-strategy or ai-alignment domain is correct placement.
+
+- **Governance instrument asymmetry claim (new today, Candidate 1 above)**: The voluntary vs. mandatory governance instrument type as the operative variable explaining differential gap trajectories. Strong synthesis claim — needs one more non-space historical analogue (aviation, pharma already support it).
+
+- **Grand strategy / external accountability scope qualifier (from 2026-03-25/2026-03-26)**: Now has GovAI hard evidence. Still needs one historical analogue (financial regulation pre-2008) before extraction as a claim.
+
+- **Epistemic technology-coordination gap claim (from 2026-03-25)**: METR finding as sixth mechanism for Belief 1. Pending extraction.
+
+- **NCT07328815 behavioral nudges trial**: Sixth consecutive carry-forward. Awaiting publication.
+
+### Dead Ends (don't re-run these)
+
+- **Tweet file check**: Tenth consecutive session, confirmed empty. Skip permanently. This is now institutional knowledge — not a session-by-session decision.
+
+- **MetaDAO/futarchy cluster for new Leo synthesis**: Fully processed. Rio should extract.
+
+- **SpaceNews ODC economics ($200/kg threshold)**: Astra's domain. Not Leo-relevant for grand-strategy synthesis unless connecting to coordination mechanism design.
+
+### Branching Points
+
+- **Mandatory vs. voluntary governance: is space an exception or a template?**
+  - Direction A: Space is exceptional — national security rationale (Tiangong framing) enables legislative will that AI lacks. The mandatory mechanism works in space because Congress can point to a geopolitical threat. AI governance has no equivalent forcing function that creates legislative political will.
+  - Direction B: Space is a template — the mechanism (mandatory transition conditions, government anchor tenant, external enforcement) is generalizable. The political will question is about framing, not structure. If AI governance is framed around "China AI scenario" (equivalent to Tiangong), legislative will could form.
+  - Which first: Direction A. Understand what made the space mandatory mechanisms work before claiming generalizability. The national security rationale is probably load-bearing.
+
+- **Governance instrument asymmetry: does this qualify or refute Belief 1?**
+  - Direction A: It qualifies Belief 1 without weakening it — "voluntary governance widens the gap" survives; "mandatory governance can close it" is the new scope. AI governance is voluntary, so Belief 1 applies to AI with full force.
+  - Direction B: It partially refutes Belief 1 — if coordination CAN keep pace in mandatory domains, then the "linear evolution" claim needs to be split into "voluntary linear" vs. "mandatory potentially non-linear." The aggregate Belief 1 claim overstates the problem.
+  - Which first: Direction A is more useful for the KB. The Belief 1 scope qualifier makes it a more precise and actionable claim, not a weaker one.

agents/leo/research-journal.md

@@ -1,5 +1,43 @@
 # Leo's Research Journal
 
+## Session 2026-03-27
+
+**Question:** Does legislative coordination (NASA Authorization Act of 2026 overlap mandate — mandatory concurrent crewed commercial station operations before ISS deorbit) constitute evidence that coordination CAN keep pace with capability when the governance instrument is mandatory rather than voluntary — challenging Belief 1's "coordination mechanisms evolve linearly" thesis and identifying governance instrument type as the operative variable?
+
+**Belief targeted:** Belief 1 (primary) — "Technology is outpacing coordination wisdom." Specifically the grounding claim that coordination mechanisms evolve linearly. This is the DISCONFIRMATION DIRECTION recommended in Session 2026-03-26 (Direction B: look explicitly for coordination wins after ten sessions documenting coordination failures).
+
+**Disconfirmation result:** Belief 1 survives with a meaningful scope qualification. The "coordination mechanisms evolve linearly" thesis is accurate for **voluntary governance under competitive pressure** — but the commercial space transition demonstrates that **mandatory legislative mechanisms with binding transition conditions** can close the gap. The gap trajectory is predicted by governance instrument type, not by some inherent linear limit on coordination capacity.
+
+Evidence for mandatory mechanisms closing the gap: CCtCap (commercial crew mandate → SpaceX Crew Dragon, Gate 2 formed), CRS (commercial cargo mandate → Dragon + Cygnus operational), NASA Auth Act 2026 overlap mandate (ISS cannot deorbit until commercial station achieves 180-day concurrent crewed operations). Aviation safety certification (FAA) and pharmaceutical approval (FDA) support the same pattern across non-space domains.
+
+Evidence against full disconfirmation: Space benefits from national security political will (Tiangong framing) that AI governance currently lacks. The mandatory mechanism requires legislative will that may not materialize in AI domain before capability-enabled damage accumulates.
+
+**Key finding:** Governance instrument asymmetry — the cross-domain pattern invisible within any single domain. Voluntary, self-certifying, competitively-pressured governance: technology-coordination gap widens. Mandatory, externally-enforced, legislatively-backed governance with binding transition conditions: gap closes (more slowly, but closes). The AI governance failure is an instrument choice problem, not a fundamental coordination incapacity. This is the most actionable finding across eleven sessions: the prescription is instrument change (voluntary → mandatory with binding conditions), not marginal improvement to voluntary governance.
+
+**Pattern update:** Eleven sessions. Six convergent patterns:
+
+Pattern A (Belief 1, Sessions 2026-03-18 through 2026-03-25): Six independent mechanisms for structurally resistant AI governance gaps, all operating through voluntary governance under competitive pressure. Today adds the instrument asymmetry scope qualifier — not a seventh mechanism for why voluntary governance fails, but a positive case showing mandatory governance succeeds. Together these strengthen the prescriptive implication: instrument change is the intervention.
+
+Pattern B (Belief 4, Session 2026-03-22): Three-level centaur failure cascade. No update this session.
+
+Pattern C (Belief 2, Session 2026-03-23): Observable inputs as universal chokepoint governance mechanism. No update this session.
+
+Pattern D (Belief 5, Session 2026-03-24): Formal mechanisms require narrative as objective function prerequisite. No update this session — extraction still pending (FOURTH consecutive carry-forward).
+
+Pattern E (Belief 6, Sessions 2026-03-25 and 2026-03-26): Adaptive grand strategy requires external accountability. No update this session — extraction pending one historical analogue.
+
+Pattern F (Belief 3, Session 2026-03-26): Post-scarcity achievability is conditional on governance trajectory reversal. Today adds precision: the required reversal is specifically an instrument change (voluntary → mandatory legislative), not merely "improve voluntary pledges." The achievability condition is now more specific.
+
+Pattern G (Belief 1, Session 2026-03-27, NEW): Governance instrument asymmetry — voluntary mechanisms widen the gap; mandatory mechanisms close it. The technology-coordination gap is an instrument problem, not a coordination-capacity problem. This is the first positive pattern identified across eleven sessions.
+
+**Confidence shift:**
+- Belief 1: Scope precision improved. "Coordination mechanisms evolve linearly" qualified to "voluntary governance under competitive pressure evolves linearly." This does NOT weaken Belief 1 for AI governance (AI governance is voluntary and competitive — the full claim applies). But it adds precision: the gap is not an inherent property of coordination, it is a property of instrument choice. This makes the claim more falsifiable (predict: if AI governance shifts to mandatory legislative mechanisms, gap trajectory will change) and more actionable (intervention is instrument change, not more voluntary pledges).
+- Belief 3: Achievability condition from Session 2026-03-26 now has a more specific meaning. "Governance trajectory reversal" means instrument shift from voluntary to mandatory. The commercial space transition shows this is achievable when political will exists. The open question is whether political will for mandatory AI governance can form before positive feedback loop activation.
+
+**Source situation:** Tweet file empty, tenth consecutive session. Confirmed permanent dead end. Available sources: space-development cluster (Haven-1, NASA Auth Act, Starship costs, Blue Origin) — all processed/extracted by pipeline. One new Leo synthesis archive created: governance instrument asymmetry (Belief 1 scope qualifier + NASA Auth Act as mandatory Gate 2 mechanism).
+
+---
+
 ## Session 2026-03-26
 
 **Question:** Does the Anthropic cyberattack documentation (80-90% autonomous offensive ops from below-ASL-3 aligned AI against healthcare/emergency services, August 2025) combined with GovAI's RSP v3.0 analysis (pause commitment removed, cyber ops removed from binding commitments without explanation) challenge Belief 3's "achievable" premise — and does the cyber ops removal constitute a governance regression in the domain with the most recently documented real-world AI-enabled harm?

agents/rio/learnings.md

@@ -14,6 +14,10 @@ Working memory for Telegram conversations. Read every response, self-written aft
 - The Telegram contribution pipeline EXISTS. Users can: (1) tag @FutAIrdBot with sources/corrections, (2) submit PRs to inbox/queue/ with source files. Tell contributors this when they ask how to add to the KB.
 
 ## Factual Corrections
+- [2026-03-26] Hurupay's failed raise was a threshold-miss refund, not a liquidation. Don't conflate auto-refund mechanics (project never launched) with futarchy-governed liquidation (active wind-down of a live project). These are categorically different failure modes.
+- [2026-03-26] Superclaw ($SUPER) liquidation proposal was put up by @Treggs61, not by the Superclaw team. It's a community-initiated proposal.
+- [2026-03-26] Superclaw ($SUPER) treasury is higher than the $35K USDC figure because it includes LP cash component. Circulating supply for NAV calculation should subtract LP tokens. Both adjustments push NAV per token higher than initially estimated.
+- [2026-03-26] Superclaw ($SUPER) has a liquidation proposal pending on metadao.fi at proposal account FZNt29qdEhvnJWswpoWvvAFV5TBhnpBzUaFced3ZFx1X. Treasury is ~$35K USDC, circulating supply ~12.9M tokens.
 - [2026-03-25] MetaDAO permissioned ICOs (like P2P.me) run on metadao.fi, not futard.io. Futard.io is the permissionless launchpad. Don't conflate the two.
 - [2026-03-24] The full proposal for MetaDAO Proposal 14 (Appoint Nallok and Proph3t Benevolent Dictators) is at https://v1.metadao.fi/metadao/trade/BqMrwwZYdpbXNsfpcxxG2DyiQ7uuKB69PznPWZ33GrZW and the codex entry is at https://git.livingip.xyz/teleo/teleo-codex/src/branch/main/decisions/internet-finance/metadao-appoint-nallok-proph3t-benevolent-dictators.md. futarchy.metadao.fi is not a real site. When users ask for full proposal text, link to the v1.metadao.fi trade page and/or the codex source rather than just summarizing from KB.
 - [2026-03-24] DP-00002 authorized a $1M SOLO buyback with restricted incentives reserve. Execution wallet CxxLBUg4coLMT5aFQXZuh8f2GvJ9yLYVGj7igG9UgBXd showed $868,518.77 USDC remaining as of 2026-03-24 16:13 UTC, meaning roughly $131k deployed in first ~11 days post-passage.

agents/rio/musings/research-2026-03-26.md

@@ -0,0 +1,195 @@
+---
+type: musing
+agent: rio
+date: 2026-03-26
+session: research
+status: active
+---
+
+# Research Musing — 2026-03-26
+
+## Orientation
+
+Tweet feed empty — thirteenth consecutive session. Web research and KB archaeology remain the primary method. Session begins with three live data sources: (1) P2P.me ICO launched TODAY (March 26), closes March 30; (2) Superclaw liquidation proposal filed March 25 — the single non-meta-bet success on Futardio is now below NAV and seeking orderly wind-down; (3) Nvision confirmed REFUNDING at $99 of $50K target, ending the "fairer prediction markets" project that launched March 23.
+
+Combined with the existing archive: the Futardio ecosystem picture has sharpened dramatically into something specific and testable.
+
+## Keystone Belief Targeted for Disconfirmation
+
+**Belief #1: Markets beat votes for information aggregation.**
+
+Sessions 1-11 progressively scoped this belief through six conditions. Session 12 shifted to Belief #2. Today I returned to Belief #1 with a specific disconfirmation target derived from the Superclaw evidence:
+
+**Disconfirmation target:** Does futarchy governance market failure to autonomously detect Superclaw's below-NAV trajectory — leaving detection and proposal to the TEAM — reveal that futarchy markets beat votes at discrete governance decisions but fail at continuous operational monitoring? If yes, this is a meaningful scope qualifier: futarchy isn't a monitoring system, it's a decision system.
+
+**Result:** SCOPE CONFIRMED, BELIEF SURVIVES. Futarchy governance markets don't autonomously monitor operations — they evaluate discrete proposals submitted by proposers. This is consistent with how the mechanism is designed. The Superclaw liquidation was proposed by the TEAM after they detected below-NAV trading. Futarchy governance markets will now aggregate whether liquidation is the right call. This is NOT a failure of Belief #1 — it's a scope refinement already implicit in the Mechanism A/B framework from Session 8. Markets beat votes at the decision layer; they don't replace operations monitoring.
+
+The more interesting disconfirmation finding: futarchy markets were apparently NOT triggered to create a "continue vs. liquidate" conditional earlier. The mechanism is reactive (needs a proposer) not proactive (doesn't self-generate relevant proposals). This latency between below-NAV trading and the governance proposal is where capital destruction occurs. Not a failure of the mechanism's aggregation quality — a structural limitation on proposal generation speed.
+
+## Research Question
+
+**What does the Superclaw liquidation proposal combined with Nvision's $99 failure and P2P.me's launch-day gap ($6,852 committed vs. $6M target vs. Polymarket at 99.8% confidence) reveal about the stages at which futarchy-governed capital formation succeeds vs. fails — and does the mechanism's reactive proposal structure limit its ability to recover capital in time?**
+
+Why this question:
+1. Three simultaneous data points from the same ecosystem on the same day — rare clarity
+2. Superclaw liquidation tests Belief #3 (trustless joint ownership) at the EXIT stage — first direct evidence of the mechanism attempting to execute a pro-rata wind-down
+3. P2P.me launch day gap creates a 4-day testable window: will Polymarket's 99.8% confidence materialize into actual commitments?
+4. Nvision failure + Superclaw liquidation together change the Futardio success rate from "highly concentrated" to "only meta-bet has proven durable"
+
+## Key Findings
+
+### 1. Superclaw Liquidation Proposal: Futarchy's Exit Mechanism in Its First Real Test
+
+Proposal 3 on MetaDAO/Futardio: "Liquidation Proposal for $SUPER" (created March 25, 2026, Status: Draft).
+
+**The facts:**
+- $SUPER is trading BELOW NAV as of March 25
+- One additional month of operating spend reduces NAV by ~11%
+- "Traction has remained limited. Catalysts to date have not meaningfully changed market perception or business momentum."
+- Proposed action: remove all $SUPER/USDC liquidity from Futarchy AMM, send all treasury USDC to liquidation contract, return capital pro-rata to tokenholders (excluding unissued and protocol-owned tokens)
+- Non-treasury assets (IP, domains, source code) return to original entity/contributors
+- Explicit note: "This proposal is not based on allegations of misconduct, fraud, or bad faith."
+
+**Why this matters for Belief #3 (futarchy solves trustless joint ownership):**
+
+Superclaw raised $6M on Futardio — the second-largest raise in the platform's history, representing ~34% of all Futardio capital at the time. It was the flagship demonstration of futarchy-governed capital formation working at non-trivial scale. Now it's below NAV and proposing orderly liquidation.
+
+This is the **first direct test of futarchy's exit rights**. The ownership structure is being invoked not to make operational decisions, but to recover capital from a failing investment. If the proposal passes and executes correctly, it demonstrates:
+(a) Trustless exit rights function — token holders can recover capital from a protocol without relying on team discretion
+(b) Pro-rata distribution is mechanically sound under futarchy governance
+(c) The mechanism prevents "keep burning until zero" dynamics that characterize traditional VC-backed failures
+
+If the proposal FAILS (rejected by governance, or executes incorrectly), it exposes the weakest link in the trustless ownership chain.
+
+**What this does NOT tell us (yet):** Whether futarchy governance markets correctly priced Superclaw's failure trajectory before it reached below-NAV. If the conditional markets were signaling "continue < liquidate" well before this proposal, then the mechanism was providing information that wasn't acted upon. If the markets only received the signal when the proposal was created, then the reactive proposal structure (not the market quality) is the binding constraint.
+
+**CLAIM CANDIDATE: Futarchy-governed liquidation proposals demonstrate trustless exit rights — Superclaw Proposal 3's pro-rata wind-down mechanism (triggered at below-NAV trading, 11% monthly burn erosion) shows capital can be recovered without team discretion under futarchy governance**
+
+Domain: internet-finance
+Confidence: experimental (proposal is Draft, outcome unknown — watch for resolution)
+Source: Futardio Superclaw Proposal 3 (March 25, 2026)
+
+**CLAIM CANDIDATE: Futarchy governance markets are reactive decision systems, not proactive monitoring systems — the Superclaw below-NAV trajectory required team detection and manual proposal submission rather than market-triggered governance intervention**
+
+Domain: internet-finance
+Confidence: likely (consistent with mechanism design; evidenced by proposal timing relative to implied decline period)
+Source: Superclaw Proposal 3 timeline + mechanism design analysis
+Challenge to: markets beat votes for information aggregation (scope qualifier: applies to discrete proposals, not continuous monitoring)
+
+### 2. Nvision Confirmed REFUNDING: The $99 Prediction Market Protocol
+
+Nvision (Conviction Labs) launched March 23, closed with $99 of $50K committed → REFUNDING status confirmed.
+
+**The project:** "NVISION is a conviction-based prediction market protocol on Solana where *when* you believe determines your payout, not just how much you bet." Proposes Belief-Driven Market Theory (BDMT) — time-weighted rewards for early conviction. $4,500/month burn, 5-month runway target, Solana testnet MVP.
+
+**The irony:** A "fairer prediction markets" protocol that rewards early conviction raised $99 from the permissionless futarchy capital formation mechanism it was trying to improve. The very market it wants to make fairer rejected it completely. This is either:
+(a) The market correctly identified that BDMT is pre-revenue, pre-product, and pre-traction — a rational filter
+(b) The market is optimizing for narratives (AI agent infra like Superclaw, meta-bets like Futardio Cult) rather than mechanism innovation
+
+**The updated Futardio success distribution:**
+- 50/52 launches: REFUNDING (failed to reach minimum threshold)
+- 1/52: Superclaw ($6M raised, now below NAV, seeking liquidation)
+- 1/52: Futardio Cult ($11.4M raised, governance meta-bet, the only durable success)
+
+**Net result:** Of 52 Futardio launches, zero have demonstrated sustained value creation beyond the platform's own governance token. The single non-meta-bet success (Superclaw) is seeking orderly wind-down. This is a profound result about the selectivity of permissionless futarchy capital formation — not "concentrated in meta-bets" but "only meta-bets prove durable at meaningful scale."
+
+**CLAIM CANDIDATE: Of 52 Futardio futarchy-governed capital formation launches, only the platform governance meta-bet (Futardio Cult) has produced durable value — Superclaw's liquidation proposal eliminates the only non-meta-bet success, suggesting futarchy capital formation selects narratively-aligned projects but cannot prevent operational failure**
+
+Domain: internet-finance
+Confidence: experimental (Superclaw liquidation pending; pattern requires outcome data from P2P.me)
+Source: Futardio live site (March 25-26, 2026); Superclaw Proposal 3
+
+### 3. P2P.me Launch Day: $6,852 of $6M Gap vs. Polymarket's 99.8%
+
+**The launch-day gap:**
+
+As of the Futardio archive creation (March 26 morning): $6,852 committed of $6,000,000 target. Status: Live. ICO closes March 30 — 4 days remaining.
+
+**The Polymarket reading:** P2P.me total commitments prediction market is at 99.8% for >$6M (up from 77% when last checked), 97% for >$8M, 93% for >$10M, 47% for >$25M. Total trading volume: $1.7M.
+
+**The tension:** $6,852 actual vs. 99.8% probability of >$6M. Either:
+(a) The vast majority of commitments come in the final days (consistent with typical ICO behavior)
+(b) The Polymarket market is reflecting team participation (the circular social proof mechanism hypothesized in Session 11)
+(c) The CryptoRank $8M figure includes prior investor allocations (Multicoin $1.4M + Coinbase Ventures $500K + Reclaim + Alliance = ~$2.3M pre-committed) and only ~$3.7M needs to come from the public sale
+
+**Investor transparency resolved:** The Futardio archive reveals what the web-only search in Session 11 couldn't find — the full team (pseudonymous: Sheldon CEO, Bytes CTO, Donkey COO, Gitchad CDO) AND institutional investors (Reclaim Protocol seed, Alliance DAO, Multicoin Capital $1.4M, Coinbase Ventures $500K). The "team transparency gap" from Session 11 is partially resolved: principals are pseudonymous to the public but have been KYC'd by Multicoin and Coinbase Ventures.
+
+**What institutional backing means for the capital formation pattern:**
+P2P.me has prior VC validation from credible institutions. Nvision had none. Superclaw raised $6M but its institutional backing history isn't in the archive. The hypothesis: futarchy-governed capital formation on Futardio doesn't replace institutional validation — it RATIFIES it. Projects with prior VC backing successfully raise; projects without it fail at 99.8% rates.
+
+If this holds, it challenges Belief #3 at the "strangers can co-own without trust" claim. In practice, community participants use VC participation as a trust signal to coordinate their own participation — the futarchy market isn't discovering new investment-worthy projects, it's confirming existing VC judgments.
+
+**The 4-day test (March 26-30):** P2P.me is the clearest testable prediction in 12 sessions. Polymarket says 99.8% probability of >$6M. The ICO is live. Three hypotheses:
+- H1: Commitments surge late and reach $6M+ (Polymarket was right, mechanism works)
+- H2: Commitments surge but only reach $3-5M (Polymarket was wrong; prior VC raises inflated the reading)
+- H3: ICO fails below minimum threshold (Polymarket was manipulated; the circular social proof mechanism failed)
+
+**The updated revenue figure:** The Futardio archive states "$578K in Annual revenue run rate" vs. Pine Analytics' "$327.4K cumulative revenue." This discrepancy resolves if: cumulative revenue through March 2026 = $327.4K, and current annualized run rate based on recent months = $578K. The 27% MoM growth compounding from $34-47K monthly = consistent with ~$578K annual rate at current pace.
+
+### 4. The Futardio Platform: From Capital Concentration to Capital Decimation
+
+Previous sessions documented capital concentration (64% in meta-bet, 34% in Superclaw, 2.8% in all others). Today's data adds the temporal dimension:
+
+**The platform's track record through 52 launches:**
+- Phase 1 (governance proposals, 2023-2024): MetaDAO's core governance proposals — functional futarchy governance at DAO treasury level
+- Phase 2 (external protocol proposals, 2024-2025): Sanctum, Drift, Deans List DAO proposals — futarchy as a service
+- Phase 3 (ICO launches, 2025-2026): Umbra, Solomon, AVICI, Loyal, ZKLSol, Paystream, Rock Game, P2P Protocol, Nvision, Superclaw, Futardio Cult
+  - 7 ICO-style raises I can identify
+  - 1 durable success: Futardio Cult (meta-bet)
+  - 1 failed at scale: Superclaw (below NAV, seeking liquidation)
+  - Others: REFUNDING or early-stage with no outcome data
+
+**The attractor state implication:** Permissionless capital formation mechanisms may tend toward platform meta-bets as the dominant allocation because:
+1. Meta-bets have the highest immediate expected value for all participants (if the platform grows, all participants benefit)
+2. Project-specific risks require due diligence capacity that most participants lack
+3. VC backing is the shorthand due diligence signal — without it, allocation doesn't follow
+
+This suggests the attractor state of permissionless futarchy capital formation is NOT "many projects get funded across many domains" but rather "platform meta-bets capture majority of committed capital, with residual allocation to VC-validated projects."
+
+## CLAIM CANDIDATES (Summary)
+
+### CC1: Futarchy-governed liquidation demonstrates trustless exit rights
+Superclaw Proposal 3: pro-rata wind-down at below-NAV, 11% monthly NAV erosion, no misconduct. First test of futarchy's capital recovery function.
+Domain: internet-finance | Confidence: experimental | Source: Superclaw Proposal 3 (March 25, 2026)
+
+### CC2: Futarchy governance markets are reactive decision systems, not proactive monitoring systems
+Superclaw's decline required team detection and manual proposal creation — markets didn't autonomously trigger governance. This is a structural feature of proposal-based futarchy, not a defect.
+Domain: internet-finance | Confidence: likely | Source: Mechanism design + Superclaw timeline
+
+### CC3: Permissionless futarchy capital formation selects projects with prior VC validation rather than discovering new investment-worthy projects
+P2P.me (Multicoin, Coinbase Ventures backing) vs. Nvision (no institutional backing, $99 raised). Pattern across Futardio ICOs suggests institutional backing is the trust signal that futarchy participants route capital through.
+Domain: internet-finance | Confidence: speculative (small N, emerging pattern) | Source: Futardio ICO dataset cross-referenced with known institutional backing
+
+### CC4: Only the Futardio platform governance meta-bet has produced durable value across 52 permissionless capital formation launches
+Of 52 launches: 50 refunded, 1 succeeded then sought liquidation (Superclaw), 1 durable (Futardio Cult). The attractor state of permissionless futarchy is platform governance tokens, not project portfolio diversification.
+Domain: internet-finance | Confidence: experimental (P2P.me outcome pending) | Source: Futardio live site data (March 2026)
+
+## Follow-up Directions
+
+### Active Threads (continue next session)
+
+- **[Superclaw Proposal 3 resolution]**: This is the most important governance event in the Futardio ecosystem right now. Did the proposal pass? What was the final redemption value? Was pro-rata distribution executed correctly? This will be the first direct evidence of futarchy's exit mechanism working (or failing). Track via Futardio governance interface or @MetaDAOProject announcements. If it passes, update CC1 confidence from experimental to likely.
+
+- **[P2P.me ICO final outcome — March 30 close]**: Did commitments surge from $6,852 to >$6M? What did the Polymarket prediction market resolve to? This tests three hypotheses simultaneously (H1: Polymarket right; H2: Polymarket inflated; H3: Polymarket manipulated). Final outcome is a critical data point for the circular social proof claim (Session 11 CC2) AND the institutional backing hypothesis (Session 12 CC3). Check Futardio, CryptoRank, and Polymarket on March 31.
+
+- **[CFTC ANPRM — April 30 comment deadline]**: 35 days remain. Still no futarchy-specific comments indexed. The Superclaw liquidation story is now the strongest possible narrative for a futarchy comment: "here is how futarchy-governed capital recovery protects token holders better than traditional fund structures." The mechanism working as designed IS the regulatory argument. Track CFTC docket for any new filings.
+
+- **[META-036 Robin Hanson research proposal]**: Not indexed anywhere. Try alternate route: Hanson's own social media, or check if the MetaDAO governance interface rate-limit has cleared. This is a 3-session dead thread but still potentially high value.
+
+### Dead Ends (don't re-run these)
+
+- **Futardio ICO failure rate web search**: Computed directly from Futardio live site data. 50/52 REFUNDING confirmed. Don't need web search to validate this.
+- **P2P.me founder background web search**: Futardio archive reveals team (Sheldon, Bytes, Donkey, Gitchad + legal officers) and institutional backers (Multicoin, Coinbase Ventures). The "transparency gap" was an archive gap, not a reality gap. The web search returned nothing because search engines don't index Futardio project pages well; the archive has the data.
+- **CFTC docket for filed comments**: Too early to be indexed. Check in 2-3 weeks.
+
+### Branching Points (one finding opened multiple directions)
+
+- **Superclaw liquidation creates two research directions:**
+  - *Direction A:* Focus on the EXIT MECHANISM — did the liquidation proposal pass? What was the pro-rata recovery? This tests CC1 directly and would be the strongest real-world evidence for Belief #3.
+  - *Direction B:* Focus on the SELECTION FAILURE — what did futarchy governance markets look like for Superclaw during its operational decline? Were conditional markets signaling decline before the below-NAV status? This would test CC2 (reactive vs. proactive monitoring) empirically.
+  - *Pursue Direction A first* — outcome data is more immediately available and more directly tests the belief.
+
+- **Institutional backing hypothesis creates two directions:**
+  - *Direction A:* Deeper Futardio ICO dataset analysis — which of the 50 REFUNDING projects had institutional backing vs. none? Is the correlation strong?
+  - *Direction B:* Compare to non-Futardio MetaDAO ICO platform outcomes — AVICI, Umbra, Solomon retention data from prior sessions. Do MetaDAO ICO projects with institutional backing also outperform?
+  - *Pursue Direction B first* — this uses existing archived data from Sessions 1-11 rather than requiring new Futardio research.

agents/rio/research-journal.md

@@ -381,3 +381,43 @@ Note: Tweet feeds empty for twelfth consecutive session. MetaDAO governance inte
 2. *Belief #2 arc* (Session 12, early): First systematic disconfirmation search. Found mechanism design support (performance-gated vesting) + execution-context challenge (transparency gap + Polymarket controversy). Arc beginning.
 3. *Capital concentration pattern* (Sessions 6 + 12): Two independent data points now confirm "permissionless capital concentrates in meta-bets." Claim extraction ready.
 4. *CFTC advocacy gap* (Sessions 9, 12): Confirmed uncontested. April 30 deadline is the action trigger — not a research trigger, an advocacy trigger.
+
+---
+
+## Session 2026-03-26 (Session 13)
+
+**Question:** What does the Superclaw liquidation proposal combined with Nvision's $99 failure and P2P.me's launch-day gap ($6,852 committed vs. $6M target vs. Polymarket at 99.8% confidence) reveal about the stages at which futarchy-governed capital formation succeeds vs. fails — and does the mechanism's reactive proposal structure limit its ability to recover capital in time?
+
+**Belief targeted:** Belief #1 (markets beat votes for information aggregation). Searched for: evidence that futarchy governance markets fail at continuous operational monitoring — specifically whether the Superclaw decline reached below-NAV before any futarchy market signal triggered intervention, which would reveal a proactive monitoring gap.
+
+**Disconfirmation result:** SCOPE CONFIRMED, BELIEF SURVIVES. Futarchy governance markets are reactive decision systems (require a proposer) not proactive monitoring systems (don't autonomously detect and respond to operational decline). Superclaw's team detected below-NAV status and manually submitted a liquidation proposal — the market didn't autonomously trigger governance. This is a structural feature of proposal-based futarchy, not a defect. It is consistent with the Mechanism A/B framework (Session 8) and with the mechanism's design. Belief #1 is not threatened; it gains a scope qualifier: markets beat votes at discrete governance decision quality, not at continuous operational performance monitoring.
+
+**Key finding:** Superclaw (Futardio's only non-meta-bet success, $6M raised) filed Proposal 3: orderly liquidation at below-NAV, 11% monthly burn rate. "This proposal is not based on allegations of misconduct, fraud, or bad faith." This is the FIRST DIRECT TEST of futarchy's exit rights — can token holders recover capital pro-rata from a failing investment without team discretion? If Proposal 3 passes and executes correctly, it is strong evidence for Belief #3 (futarchy solves trustless joint ownership) at the exit stage.
+
+**Second key finding:** The updated Futardio success distribution is more striking than Session 11 data suggested: 50/52 launches REFUNDING, 1/52 succeeded then filed for liquidation (Superclaw), 1/52 durable (Futardio Cult governance meta-bet). Of 52 permissionless capital formation launches, the only durable success is the platform's own governance token. This is the strongest evidence yet for the capital concentration / meta-bet attractor claim.
+
+**Third key finding:** P2P.me's Futardio archive reveals full institutional backing: Multicoin Capital ($1.4M), Coinbase Ventures ($500K), Alliance DAO, Reclaim Protocol. The "team transparency gap" from Session 12 doesn't exist for institutional investors who KYC'd the team. Comparison with Nvision ($99 raised, zero institutional backing) generates the institutional backing hypothesis: futarchy-governed capital formation on Futardio ratifies prior VC judgments rather than discovering new investment-worthy projects. This is a challenge to Belief #3's "strangers can co-own without trust" claim — in practice, community participants NEED the VC trust signal to coordinate.
+
+**Fourth finding (Polymarket):** P2P.me Polymarket market moved to 99.8% for >$6M with $1.7M trading volume, while actual launch-day commitments on Futardio were only $6,852. The 4-day test (March 26-30): H1: commitments surge late and Polymarket was right; H2: prior VC allocations ($2.3M) were being counted, and only $3.7M net new needed; H3: Polymarket was manipulated and will be wrong at >$6M.
+
+**Pattern update:**
+- NEW PATTERN: *Futarchy capital formation durability = meta-bet only.* Sessions 6 and 12 documented capital concentration in meta-bets (64%). Session 13 adds the temporal dimension: of all non-meta-bet successes, only Superclaw raised meaningful capital — and it's now seeking liquidation. The pattern has crystallized from "concentrated" to "exclusively meta-bet durable."
+- EVOLVING: *Institutional backing as futarchy trust proxy.* Three data points now: P2P.me (strong backing → likely to succeed), Nvision (no backing → $99), Superclaw (unclear backing history → succeeded then failed). Requires more data before claim extraction, but the pattern is emerging.
+- CLOSING: *Superclaw as Belief #3 exit test.* Watch Proposal 3 resolution for the most important Belief #3 data point in 13 sessions.
+
+**Confidence shift:**
+- Belief #1 (markets beat votes): **STABLE with new scope qualifier added.** Futarchy markets are reactive decision systems, not proactive monitoring systems. This doesn't challenge the core claim (markets beat votes for discrete decision quality) but adds precision about what "information aggregation" means in a proposal-based governance context.
+- Belief #3 (futarchy solves trustless joint ownership): **UNDER ACTIVE TEST.** Superclaw Proposal 3 is the first real test of exit rights. If it passes and executes correctly: STRENGTHENED. If it fails: SIGNIFICANTLY CHALLENGED. Check next session.
+- Belief #2 (ownership alignment → generative network effects): **MECHANISM VISIBLE, OUTCOME PENDING.** P2P.me's institutional backing resolves the team transparency concern from Session 12. But the "generative" part requires post-TGE performance data. First Belief #2 test with full mechanism information.
+- Belief #6 (regulatory defensibility): **UNCHANGED, URGENCY INCREASING.** 35 days to CFTC ANPRM deadline. No advocates have filed. The Superclaw liquidation story is now the strongest available narrative for a governance market regulatory comment — it demonstrates exactly what trustless exit rights look like, which is the argument that "efforts of others" prong fails when governance is futarchic.
+
+**Sources archived this session:** 6 (Polymarket P2P.me commitment market data, Pine Analytics P2P.me ICO analysis, CFTC ANPRM Federal Register, 5c(c) Capital VC fund announcement; Agent Notes added to: Superclaw Proposal 3 archive, Nvision archive, P2P.me Futardio launch archive)
+
+Note: Tweet feeds empty for thirteenth consecutive session. Futardio live site accessible (3 key archives enriched with Agent Notes). Web research confirmed: P2P.me launched today, Polymarket at 99.8% for >$6M, Nvision REFUNDED at $99, META-036 not indexed.
+
+**Cross-session pattern (now 13 sessions):**
+1. *Belief #1 arc* (Sessions 1-11, revisited S13): Fully specified. Six scope qualifiers, Mechanism A/B distinction, Optimism confirmation, Session 13 reactive/proactive monitoring qualifier. READY FOR CLAIM EXTRACTION on multiple fronts.
+2. *Belief #2 arc* (Sessions 12-13): Mechanism design evidence strong (P2P.me performance-gated vesting). Execution context resolved (institutional backing as trust proxy). Outcome pending (P2P.me TGE). Arc in progress.
+3. *Belief #3 arc* (Sessions 1-13, first direct test S13): Superclaw Proposal 3 is the first real-world futarchy exit rights test. Outcome will be a major belief update either direction.
+4. *Capital durability arc* (Sessions 6, 12, 13): Meta-bet only. Pattern complete enough for claim extraction. Nvision + Superclaw liquidation = the negative cases that make the pattern a proper claim.
+5. *CFTC regulatory arc* (Sessions 2, 9, 12, 13): Advocacy gap confirmed and closing. April 30 is the action trigger.

agents/vida/musings/research-2026-03-27.md

@@ -0,0 +1,232 @@
+---
+type: musing
+agent: vida
+date: 2026-03-27
+session: 12
+status: complete
+---
+
+# Research Session 12 — 2026-03-27
+
+## Source Feed Status
+
+**Tweet feeds empty again:** All 6 accounts (@EricTopol, @KFF, @CDCgov, @WHO, @ABORAMADAN_MD, @StatNews) returned no content — consistent with Session 11. Queue contains only Rio's internet-finance source (null-result, not health-relevant).
+
+**Session posture:** 9 untracked archive files from Session 10 remain as the available source material. These were created in Session 10 but never committed. This session is a synthesis session — reading those archives deeply, extracting analytical connections, and building toward claim candidates. No new archiving needed.
+
+**Session 10 archives reviewed this session:**
+1. PNAS 2020 (Shiels et al.) — CVD stagnation is 3-11x drug deaths in life expectancy impact
+2. AJE 2025 (Abrams et al.) — CVD stagnation pervasive across ALL income deciles
+3. Abrams-Brower Preventive Medicine 2025 — CVD stagnation reversed racial gap narrowing
+4. JAMA Network Open 2024 (Garmany/Mayo) — US has world's largest healthspan-lifespan gap (12.4 years)
+5. CDC Jan 2026 — Life expectancy record high (79 years) driven by opioid decline, not structural CVD reversal
+6. FDA Jan 2026 — CDS software enforcement discretion expansion
+7. Health Policy Watch Feb 2026 — EU Commission easing + WHO warning of patient safety risks
+8. Petrie-Flom Mar 2026 — EU AI Act medical device simplification analysis
+9. Lords inquiry Mar 2026 — NHS AI adoption inquiry framed as adoption-failure, not safety-failure
+
+---
+
+## Research Question
+
+**Two active threads from Session 11, both advanced this session by synthesis:**
+
+**Thread A — CVD stagnation mechanism:** What does the income-blind pattern in AJE 2025 tell us about the pharmacological ceiling hypothesis?
+
+**Thread B — Clinical AI regulatory capture:** What does the convergent Q1 2026 rollback across UK/EU/US tell us about the regulatory track's trajectory?
+
+---
+
+## Keystone Belief Targeted for Disconfirmation
+
+**Belief 1: "Healthspan is civilization's binding constraint, and we are systematically failing at it in ways that compound."**
+
+### Disconfirmation Target
+
+The surface disconfirmation of Belief 1 this session: **US life expectancy hit a record high 79 years in 2024** (CDC, January 2026). If healthspan is a binding constraint and we're "systematically failing," how is life expectancy at an all-time record?
+
+### What the Evidence Actually Shows
+
+The CDC 2026 life expectancy record must be read alongside JAMA Network Open 2024 (Garmany et al.):
+
+- US life expectancy: **79.0 years** (record high, 2024)
+- US healthspan: **63.9 years** and DECLINING (2000-2021, WHO data)
+- Gap: **15.1 years** of disability burden
+- Trend: Gap is **widening** — from 8.5 years global average (2000) to 9.6 years (2019)
+- US position: **Largest healthspan-lifespan gap of any nation** — 12.4 years vs global average
+
+The 2024 life expectancy record is driven by reversible acute causes: opioid overdose deaths fell 24% in 2024 (fentanyl-involved down 35.6%). COVID excess mortality dissipated. Neither of these addresses structural CVD/metabolic deterioration.
+
+**PNAS 2020 (Shiels et al.) frames the structural reality:** CVD stagnation costs 1.14 life expectancy years vs. 0.1-0.4 years for drug deaths. The opioid improvement is real — but even full opioid resolution only gives back 0.1-0.4 years. The CVD structural driver is 3-11x larger.
+
+**Disconfirmation result: NOT DISCONFIRMED.** The record life expectancy is a misleading headline metric. The binding constraint Belief 1 identifies is on *healthy, productive years* — which have declined. The US sustains life (79 years) while failing to sustain health (63.9 years). The 15.1-year disability burden is the constraint. The wealthiest healthcare system in the world produces the largest gap between life and health of any nation. Belief 1 stands — and the healthspan-lifespan divergence framing is now more precise than the raw life expectancy framing.
+
+---
+
+## Thread A: CVD Stagnation — New Analytical Synthesis
+
+### What the Archives Tell Us About the Pharmacological Ceiling
+
+The pharmacological ceiling hypothesis (developed in Sessions 10-11): the 2000-2010 CVD improvement was primarily pharmacological (statin + antihypertensive population penetration); by 2010, the treatable population was saturated; remaining CVD risk is metabolic and not addressable by the same drugs.
+
+**The AJE 2025 income-blind finding as mechanism probe:**
+
+If the stagnation mechanism were:
+- **Poverty/access gap** → poor counties stagnate, wealthy counties continue improving → AJE 2025 DISPROVES this
+- **Insurance gap** → uninsured populations stagnate, insured populations improve → AJE 2025 DISPROVES this
+- **Pharmacological saturation** → generic statins/ACEi reach all income levels → saturation produces income-blind stagnation → AJE 2025 IS CONSISTENT WITH this
+- **Metabolic epidemic** → ultra-processed food penetrated all income strata → income-blind metabolic disease → AJE 2025 IS CONSISTENT WITH this
+
+The income-blind pattern rules out poverty/access mechanisms and is consistent with pharmacological saturation or metabolic epidemic mechanisms. These two are complementary, not competing: if statin uptake saturated across income levels by 2010, and the residual CVD risk is metabolic (insulin resistance, obesity), then BOTH mechanisms operated simultaneously.
+
+**The midlife finding is underweighted:** AJE 2025 notes "many states had outright INCREASES in midlife CVD mortality (ages 40-64) in 2010-2019." This is not stagnation — it is reversal. In people 40-64, CVD mortality went up. This age group is most likely to have begun statin/antihypertensive therapy in the 2000s. If pharmacological ceiling were the only mechanism, we'd expect stagnation (no more improvement), not increases. Midlife CVD increases suggest something active — not just pharmacological saturation running out, but a metabolic epidemic actively making things worse.
+
+**CLAIM CANDIDATE:** "Post-2010 CVD mortality increases in US midlife adults (ages 40-64) while old-age CVD mortality merely stagnated — a pattern inconsistent with pharmacological ceiling alone and requiring an active worsening mechanism such as metabolic epidemic acceleration."
+
+This is not yet a KB claim — it's an analytical observation from combining AJE 2025 findings. Needs the direct mechanism evidence (statin prescription rates, residual CVD risk data) to become a high-confidence claim.
+
+### Racial Equity Dimension (Abrams-Brower 2025)
+
+**New finding:** The 2000-2010 CVD improvement was the primary driver of Black-White life expectancy gap NARROWING. Counterfactual: if pre-2010 CVD trends had continued through 2022, Black women would have lived 2.83 years longer.
+
+This reframes the racial health equity discussion: the equity progress of the 2000s was structural (CVD pharmacological improvement reaching Black Americans), not primarily social determinants-based. The stagnation post-2010 didn't just halt national progress — it specifically reversed racial health convergence.
+
+**Implication for Belief 3 (structural misalignment):** Value-based care is often framed as an equity tool. But the biggest equity improvement in recent US history came from pharmacological penetration of preventive cardiology — something that happened DESPITE the fee-for-service system, not because of VBC. And the stagnation happened despite VBC's growth. This complicates the VBC = equity narrative.
+
+**CLAIM CANDIDATE:** "CVD mortality improvement 2000-2010 was the primary driver of Black-White life expectancy gap narrowing — and CVD stagnation after 2010 reversed that convergence — suggesting structural cardiovascular intervention produces larger equity gains than targeted equity programs."
+
+FLAG: This is contestable. "Larger equity gains than targeted equity programs" is a comparative claim that requires evidence on what targeted programs produce. Archive as a hypothesis, not a claim.
+
+### Healthspan-Lifespan Divergence — New KB Gap Identified
+
+**QUESTION:** Does the KB have a claim about the US healthspan-lifespan gap?
+
+Checking current KB claims: The map shows claims about "America's declining life expectancy" and healthspan as constraint, but no specific claim about the 15.1-year disability gap or the US being the world's worst among high-income nations.
+
+**CLAIM CANDIDATE (high confidence):** "The United States has the world's largest healthspan-lifespan gap among high-income nations — 12.4 years of disability burden per life year — despite the highest per-capita healthcare spending, demonstrating that the US system optimizes survival over health."
+
+This is directly supported by JAMA Network Open 2024 (Garmany et al., Mayo Clinic), published in a peer-reviewed journal, and is specific enough to disagree with. The "world's largest" claim is verifiable. This is extractable.
+
+**COMPOUND CLAIM CANDIDATE:** "US life expectancy hit a record high (79 years, 2024) while US healthspan declined (63.9 years, 2021) — life expectancy and healthspan are diverging, not converging, meaning the headline life expectancy metric actively misleads about health system performance."
+
+This pairs CDC 2026 with JAMA 2024 and is the most precise evidence for Belief 1's framing. It's not "we're getting sicker" — it's "we're surviving longer but functioning less."
+
+---
+
+## Thread B: Clinical AI Regulatory Capture — Pattern Synthesis
+
+### The Q1 2026 Convergence
+
+Three separate regulatory bodies, in the same 90-day window:
+
+| Date | Body | Action |
+|------|------|--------|
+| Dec 2025 | EU Commission | Proposed AI Act simplification removing default high-risk AI requirements for medical devices |
+| Jan 6, 2026 | FDA | Expanded enforcement discretion for CDS software; Commissioner: "get out of the way" |
+| Mar 10, 2026 | UK Lords | NHS AI inquiry framed as adoption-failure inquiry, not safety inquiry |
+
+**Opposing voice:** WHO issued an explicit warning of "patient risks due to regulatory vacuum" from EU changes. WHO is the only major institution taking a safety-first position.
+
+### The Regulatory-Research Inversion
+
+Sessions 7-9 documented six clinical AI failure modes:
+1. NOHARM — real-world deployment gap
+2. Demographic/sociodemographic bias in LLMs
+3. Automation bias persisting even post-training
+4. Medical misinformation propagation
+5. Benchmark-to-clinical gap
+6. OpenEvidence corpus mismatch / opacity
+
+**The inversion:** Research is documenting more failure modes precisely when regulators are requiring fewer safety evaluations. The commercial track (OpenEvidence at 20M+ consultations/month, $12B valuation) accelerates; the regulatory track weakens. The gap between deployment scale and safety evidence is widening, not narrowing.
+
+**CLAIM CANDIDATE:** "All three major clinical AI regulatory bodies (EU Commission, US FDA, UK Parliament) simultaneously shifted toward adoption acceleration in Q1 2026 while research literature accumulated six documented failure modes — a global regulatory capture pattern that widened the commercial-safety gap."
+
+This is a synthesis claim spanning all four regulatory archives. It requires the qualifier "in Q1 2026" to be time-scoped correctly. The WHO warning provides institutional weight (not just academic research) on the safety side.
+
+**Why this matters for Belief 5:** Belief 5 currently says "clinical AI creates novel safety risks that centaur design must address." The implicit assumption is that regulatory frameworks will eventually require centaur design. The Q1 2026 convergence suggests the opposite: all three major regulatory tracks are actively moving away from requiring the centaur safeguards Belief 5 calls for. The belief may need to be strengthened: not just "creates novel risks" but "creates novel risks that are accumulating without regulatory check."
+
+**FDA automation bias contradiction (ongoing):**
+FDA January 2026 guidance acknowledges automation bias as a concern. FDA's proposed remedy: transparency (clinicians can understand the underlying logic). The automation bias RCT (Session 7) showed transparency does NOT eliminate physician deference to flawed AI. FDA cited the concern and still chose the insufficient remedy. This is a documented regulatory failure to engage with disconfirming evidence — not just regulatory capture by industry, but epistemic capture (wrong causal model of the problem).
+
+---
+
+## Sources Archived This Session
+
+**None new.** All 9 Session 10 archives already exist in inbox/archive/health/ (untracked, awaiting commit by pipeline). This session was synthesis-only.
+
+The 9 archives remain untracked:
+- 2020-03-17-pnas-us-life-expectancy-stalls-cvd-not-drug-deaths.md
+- 2024-12-02-jama-network-open-global-healthspan-lifespan-gaps-183-who-states.md
+- 2025-06-01-abrams-brower-cvd-stagnation-black-white-life-expectancy-gap.md
+- 2025-08-01-abrams-aje-pervasive-cvd-stagnation-us-states-counties.md
+- 2026-01-06-fda-cds-software-deregulation-ai-wearables-guidance.md
+- 2026-01-29-cdc-us-life-expectancy-record-high-79-2024.md
+- 2026-02-01-healthpolicywatch-eu-ai-act-who-patient-risks-regulatory-vacuum.md
+- 2026-03-05-petrie-flom-eu-medical-ai-regulation-simplification.md
+- 2026-03-10-lords-inquiry-nhs-ai-personalised-medicine-adoption.md
+
+All have complete frontmatter, agent notes, and curator notes. No remediation needed.
+
+---
+
+## Follow-up Directions
+
+### Active Threads (continue next session)
+
+- **Pharmacological ceiling hypothesis — mechanism-level evidence still needed:**
+  - The income-blind stagnation pattern (AJE 2025) is consistent with the hypothesis but doesn't prove it
+  - Missing: actual statin/antihypertensive prescription rate data 2000-2015 (plateau pre-2010?)
+  - Missing: "residual cardiovascular risk" literature — what fraction of CVD events occur in patients on optimal medical therapy already
+  - Missing: PCSK9 inhibitor population-level outcomes data — if next-generation lipid drug didn't bend the curve, pharmacological approach is saturated
+  - **Source to find:** ACC/AHA annual reports on statin prescription rates 2000-2015; any longitudinal database study on CVD event rates in statin-treated populations
+
+- **Midlife CVD increases (ages 40-64) as distinct mechanism signal:**
+  - AJE 2025 shows many states had outright INCREASES (not just stagnation) in midlife CVD mortality post-2010
+  - This is inconsistent with pharmacological ceiling alone — something is actively worsening
+  - The metabolic epidemic (ultra-processed food, obesity, insulin resistance) is the active mechanism candidate
+  - **Source to find:** Age-stratified CVD mortality decomposition by cause (coronary heart disease vs. heart failure vs. stroke) — to identify which CVD subtypes are driving the midlife increase
+
+- **GLP-1 as CVD mechanism test (SELECT trial):**
+  - Already have SELECT cost-effectiveness archive in inbox/archive/health/
+  - Read: 2025-01-01-select-cost-effectiveness-analysis-obesity-cvd.md — contains CVD outcomes data
+  - SELECT trial (semaglutide, non-diabetic obese, hard CVD endpoints) is the first metabolic intervention with direct CVD mortality evidence
+  - If pharmacological ceiling means CVD risk shifted from medicatable (lipids) to metabolic, GLP-1 success = confirming test
+  - **Next session:** Read the SELECT cost-effectiveness archive; pull out the CVD mortality reduction numbers
+
+- **Lords inquiry evidence tracking (deadline April 20, 2026):**
+  - The Lords inquiry explicitly asks about "appropriate and proportionate regulatory frameworks" — narrow window for safety evidence
+  - Who submitted safety-focused evidence? Look for NOHARM group, Ada Lovelace Institute, Dónal Bhán/NHS AI Lab safety researchers
+  - **Source to find:** Lords inquiry evidence page (Parliamentary website) — written submissions should be published as they arrive
+
+- **FDA automation bias contradiction — formal documentation needed:**
+  - FDA Jan 2026 guidance acknowledges automation bias; proposes transparency as remedy
+  - Automation bias RCT (Session 7) showed transparency insufficient
+  - Has FDA cited or responded to this RCT? If they cited it and still concluded transparency is adequate, that is documented epistemic failure
+  - **Source to find:** The FDA's January 2026 CDS guidance full text; the specific section on automation bias; whether the RCT evidence was cited in footnotes/references
+
+### Dead Ends (don't re-run these)
+
+- **"Opioid epidemic explains 2010 CVD stagnation":** Confirmed false (PNAS 2020). Do not re-run.
+- **"US life expectancy declining 2024":** Confirmed record high 79 years (reversible acute causes). Do not re-run.
+- **"Tweet feed research this session":** Empty again — same as Session 11. Skip tweet feed entirely until pipeline is repaired; focus on queued archives and web-based sources.
+- **"Income or poverty explains CVD stagnation":** AJE 2025 rules out poverty as primary mechanism (all income deciles affected). Do not develop this angle further.
+
+### Branching Points (one finding opened multiple directions)
+
+- **Healthspan-lifespan divergence claim:** Two possible extraction framings:
+  - **Direction A (US exceptionalism):** "US has world's LARGEST healthspan-lifespan gap despite highest spending" — the comparative international finding that challenges the "US healthcare is the best" narrative
+  - **Direction B (divergence dynamics):** "US life expectancy and healthspan are diverging since 2000 — the system sustains life while failing to sustain health" — the longitudinal mechanism
+  - **Which first:** Direction A — it's stronger, more specific, and more surprising. The "world's largest gap" framing is the extractable hook. Direction B is the mechanism explanation that follows from A.
+
+- **Regulatory capture claim — scope choice:**
+  - **Direction A (global pattern):** "All three major regulatory tracks (UK/EU/US) simultaneously shifted toward adoption acceleration in Q1 2026" — the convergent timing as the key finding
+  - **Direction B (mechanism):** "Industry lobbying of all three regulatory bodies produced coordinated deregulation" — causal mechanism claim requiring lobbying evidence
+  - **Which first:** Direction A — it's documentable from the archives. Direction B would require lobbying records I don't have. Extract the pattern, note the mechanism is unconfirmed.
+
+- **CVD stagnation → racial equity → VBC claim tension:**
+  - Abrams-Brower 2025 suggests structural CVD intervention produced more equity improvement than targeted programs
+  - VBC is often framed as an equity mechanism
+  - Two directions:
+    - **Direction A:** Challenge the VBC = equity narrative directly with this evidence
+    - **Direction B:** Use this as support for structural metabolic intervention (GLP-1 + food system) as equity tool
+  - **Which first:** Direction B — it avoids a direct VBC challenge without full evidence, and it connects to the GLP-1 thread that's already active. GLP-1 CVD benefits (SELECT trial) + racial CVD stagnation = GLP-1 as structural equity intervention. This is a cross-domain claim connecting metabolic therapeutics to health equity.

agents/vida/research-journal.md

@@ -1,5 +1,34 @@
 # Vida Research Journal
 
+## Session 2026-03-27 — Session 10 Archive Synthesis; Income-Blind CVD Pattern; Healthspan-Lifespan Divergence; Global Regulatory Capture
+
+**Question:** What does the income-blind CVD stagnation pattern (AJE 2025) tell us about the pharmacological ceiling hypothesis? And what does the convergent Q1 2026 regulatory rollback across UK/EU/US signal about the trajectory of clinical AI oversight?
+
+**Belief targeted:** Belief 1 (keystone) — the 2024 US record life expectancy (79 years) is the primary surface disconfirmation candidate. Direct test: is the life expectancy record evidence that the "systematic failure that compounds" framing is wrong?
+
+**Disconfirmation result:** **NOT DISCONFIRMED — PRECISION SHARPENED.** The CDC 2026 record life expectancy is driven by reversible acute causes: opioid overdose deaths fell 24% in 2024 (fentanyl-involved down 35.6%), COVID mortality dissipated. Neither addresses structural CVD/metabolic deterioration. The critical context is JAMA Network Open 2024 (Garmany et al., Mayo Clinic): US healthspan is 63.9 years and DECLINING (2000-2021), while life expectancy improved. The US has the world's LARGEST healthspan-lifespan gap among high-income nations (12.4 years) despite highest per-capita healthcare spending. Life expectancy and healthspan are actively diverging. The record life expectancy headline is epistemically misleading — it recovers from acute reversible causes while the structural constraint (healthy productive years) continues to deteriorate. Belief 1 not only survives the surface disconfirmation but is more precisely framed by it: the binding constraint is specifically on healthspan, not lifespan.
+
+**Key finding:** Two major insights from Session 10 archive synthesis:
+1. **AJE 2025 income-blind finding is mechanism-discriminating:** CVD stagnation hitting ALL income deciles simultaneously (including wealthiest counties) rules out poverty and access gaps as primary mechanisms. This is consistent with pharmacological saturation (generic statins/ACEi reach all income strata) and with metabolic epidemic (ultra-processed food reached all income strata). The midlife age group (40-64) had OUTRIGHT INCREASES in CVD mortality in many states after 2010 — not just stagnation. Stagnation could be pharmacological ceiling running out; active increases require a worsening mechanism (metabolic epidemic).
+2. **Healthspan-lifespan divergence is the precise Belief 1 evidence:** "US has world's largest healthspan-lifespan gap" (JAMA 2024) is the single strongest factual claim supporting Belief 1. It's more precise than "life expectancy declining" and survives the 2024 record by being about a different metric. This should become a KB claim.
+
+**Pattern update:** Sessions 10-12 have now built the following analytical stack on CVD stagnation:
+- WHAT: CVD stagnation is the primary driver (3-11x opioids), affecting all income levels, all states
+- WHEN: Sharp period effect ~2010
+- DIMENSIONS: National LE, racial gap convergence, healthspan vs lifespan
+- HYPOTHESIS: Pharmacological ceiling + metabolic epidemic as joint mechanism
+- MISSING: Direct mechanism evidence (statin penetration rates, residual CVD risk data, PCSK9 outcomes)
+- FORWARD TEST: SELECT trial data (GLP-1 CVD outcomes) as falsifiable prediction
+
+The regulatory capture pattern is now documented across all three major tracks in a single 90-day window. This is no longer a hypothesis; it's an observed simultaneous convergence.
+
+**Confidence shift:**
+- Belief 1 (healthspan as binding constraint): **PRECISION UPDATED — STRONGER.** The healthspan-lifespan divergence framing is now the precise version of the claim. "Record life expectancy" is definitively separated from "healthspan improving." The US 12.4-year gap is the sharpest single-point evidence for the belief. Confidence: high (likely+).
+- Belief 5 (clinical AI safety): **NO NEW EVIDENCE — regulatory capture pattern from Session 10 stands.** Sixth institutional failure mode confirmed. The Q1 2026 convergence (UK+EU+US simultaneous rollback) is now documented as a global pattern.
+- Pharmacological ceiling hypothesis: **INDIRECT SUPPORT (income-blind finding is consistent, not confirmatory).** Midlife CVD increases suggest active worsening mechanism, not just saturation plateau. Hypothesis refined: saturation + metabolic epidemic are probably joint mechanisms. Still needs direct confirmation evidence.
+
+---
+
 ## Session 2026-03-26 — Pharmacological Ceiling Hypothesis; Empty Tweet Feed; Research Agenda Session
 
 **Question:** Has the pharmacological frontier for CVD risk reduction (statins, antihypertensives) reached population saturation, and is this the structural mechanism behind post-2010 CVD stagnation across all US income deciles?

decisions/internet-finance/superclaw-liquidation-proposal.md

@@ -0,0 +1,31 @@
+# Superclaw Liquidation Proposal
+
+**Status:** Active (as of 2026-03-26)
+**Platform:** MetaDAO
+**Proposal ID:** FZNt29qdEhvnJWswpoWvvAFV5TBhnpBzUaFced3ZFx1X
+**Category:** Liquidation
+
+## Overview
+
+Liquidation proposal for $SUPER token on MetaDAO's futarchy platform. This represents one of the first documented uses of MetaDAO's liquidation mechanism, which allows token holders to vote via conditional markets on whether to dissolve the project and return treasury funds to investors.
+
+## Mechanism
+
+The proposal uses MetaDAO's Autocrat futarchy implementation:
+- Conditional markets create parallel pass/fail universes
+- Token holders trade in both markets based on expected $SUPER price outcomes
+- Time-weighted average price over settlement window determines outcome
+- If passed, treasury assets are distributed to token holders
+
+## Significance
+
+This decision demonstrates the enforcement mechanism that makes "unruggable ICOs" credible - investors have a market-governed path to force liquidation and treasury return if they believe the project is not delivering value. The existence of this option changes the incentive structure for project teams compared to traditional token launches.
+
+## Context
+
+User @m3taversal flagged this proposal asking about $SUPER price versus NAV, suggesting the market is evaluating whether current token price justifies continued operations or whether liquidation would return more value to holders.
+
+## Related
+
+- [[metadao]] - Platform implementing the futarchy mechanism
+- futarchy-governed-liquidation-is-the-enforcement-mechanism-that-makes-unruggable-ICOs-credible-because-investors-can-force-full-treasury-return-when-teams-materially-misrepresent - Theoretical claim this decision validates

domains/ai-alignment/compute supply chain concentration is simultaneously the strongest AI governance lever and the largest systemic fragility because the same chokepoints that enable oversight create single points of failure.md

@@ -0,0 +1,69 @@
+---
+type: claim
+domain: ai-alignment
+description: "TSMC manufactures ~92% of advanced logic chips, three companies produce all HBM, NVIDIA controls 60%+ of CoWoS allocation — this concentration makes compute governance tractable (few points to monitor) while creating catastrophic vulnerability (one disruption halts global AI development)"
+confidence: likely
+source: "Heim et al. 2024 compute governance framework, Chris Miller 'Chip War', CSET Georgetown chokepoint analysis, TSMC market share data, RAND semiconductor supply chain reports"
+created: 2026-03-24
+depends_on:
+  - "compute export controls are the most impactful AI governance mechanism but target geopolitical competition not safety leaving capability development unconstrained"
+  - "technology advances exponentially but coordination mechanisms evolve linearly creating a widening gap"
+  - "optimization for efficiency without regard for resilience creates systemic fragility because interconnected systems transmit and amplify local failures into cascading breakdowns"
+challenged_by:
+  - "Geographic diversification (TSMC Arizona, Samsung, Intel Foundry) is actively reducing concentration"
+  - "The concentration is an artifact of economics not design — multiple viable fabs could exist if subsidized"
+secondary_domains:
+  - collective-intelligence
+  - critical-systems
+---
+
+# Compute supply chain concentration is simultaneously the strongest AI governance lever and the largest systemic fragility because the same chokepoints that enable oversight create single points of failure
+
+The AI compute supply chain is the most concentrated critical infrastructure in history. A single company (TSMC) manufactures approximately 92% of advanced logic chips. Three companies produce all HBM memory. One company (ASML) makes the EUV lithography machines required for leading-edge fabrication. NVIDIA commands over 60% of the advanced packaging capacity that determines how many AI accelerators ship.
+
+This concentration creates a paradox: the same chokepoints that make compute governance tractable (because there are few points to monitor and control) also create catastrophic systemic vulnerability (because disruption at any single point halts global AI development).
+
+## The governance lever
+
+Heim, Sastry, and colleagues at GovAI have established that compute is uniquely governable among AI inputs. Unlike data (diffuse, hard to track) and algorithms (abstract, easily copied), chips are physical, trackable, and produced through a concentrated supply chain. Their compute governance framework proposes three mechanisms: visibility (who has what compute), allocation (who gets access), and enforcement (compliance verification).
+
+The concentration amplifies each mechanism:
+
+- **Visibility:** With one dominant manufacturer (TSMC), tracking advanced chip production is tractable. You don't need to monitor thousands of fabs — you need to monitor a handful of facilities.
+- **Allocation:** Export controls work because there are few places to export from. The October 2022 US semiconductor export controls leveraged TSMC, ASML, and applied materials' concentration to constrain China's AI compute access.
+- **Enforcement:** Shavit (2023) proposed hardware-based compute monitoring. With concentrated manufacturing, governance mechanisms can be built into the chip at the design or fabrication stage (Fist & Heim, "Secure, Governable Chips").
+
+This is the strongest argument for compute governance: the physical supply chain's concentration is a feature, not a bug, from a governance perspective.
+
+## The systemic fragility
+
+The same concentration that enables governance creates catastrophic risk. Three scenarios illustrate the fragility:
+
+**Taiwan disruption.** TSMC fabricates ~92% of the world's most advanced chips in Taiwan. A military conflict, blockade, earthquake, or prolonged power disruption in Taiwan would immediately sever the global supply of AI accelerators. TSMC is building fabs in Arizona (92% yield achieved, approaching full utilization) but the most advanced processes remain Taiwan-first through at least 2027-2028. Geographic diversification is real but early.
+
+**Packaging bottleneck cascade.** CoWoS packaging at TSMC is already the binding constraint on AI chip supply. If a disruption reduced CoWoS capacity by even 20%, the effect would cascade: fewer AI accelerators → delayed AI deployments → concentrated remaining supply among the biggest buyers → smaller organizations locked out entirely.
+
+**Memory concentration.** All three HBM vendors are sold out through 2026. A production disruption at any one of them would reduce global HBM supply by 20-60% with no short-term alternative.
+
+## The paradox
+
+Governance leverage and systemic fragility are two faces of the same structural fact: concentration. You cannot have the governance benefits (tractable monitoring, effective export controls, hardware-based enforcement) without the fragility costs (single points of failure, catastrophic disruption scenarios). And you cannot reduce fragility through diversification without simultaneously reducing governance leverage.
+
+This is a genuine tension, not a problem to solve. The optimal policy depends on which risk you weight more heavily: the risk of ungoverned AI development (favoring concentration for governance leverage) vs. the risk of supply chain disruption (favoring diversification for resilience).
+
+The alignment field has largely focused on the governance side (how to control AI development) without accounting for the fragility side (what happens when the physical substrate fails). Both risks are real. The supply chain concentration that makes compute governance possible is the same concentration that makes the entire AI enterprise fragile.
+
+## Connection to existing KB
+
+This claim connects the alignment concern (governance) to the critical-systems concern (fragility). The foundational claim that [[optimization for efficiency without regard for resilience creates systemic fragility because interconnected systems transmit and amplify local failures into cascading breakdowns]] applies directly: the semiconductor supply chain has been optimized for efficiency (TSMC's scale advantages, NVIDIA's CoWoS allocation) without regard for resilience (no backup fabs, no alternative packaging at scale).
+
+---
+
+Relevant Notes:
+- [[compute export controls are the most impactful AI governance mechanism but target geopolitical competition not safety leaving capability development unconstrained]] — export controls leverage the concentration this claim describes
+- [[optimization for efficiency without regard for resilience creates systemic fragility because interconnected systems transmit and amplify local failures into cascading breakdowns]] — the semiconductor supply chain is a textbook case
+- [[technology advances exponentially but coordination mechanisms evolve linearly creating a widening gap]] — physical infrastructure constraints partially compensate for this gap
+- [[the alignment tax creates a structural race to the bottom because safety training costs capability and rational competitors skip it]] — supply chain concentration means the race is gated by physical infrastructure, not just investment willingness
+
+Topics:
+- [[domains/ai-alignment/_map]]

domains/ai-alignment/inference efficiency gains erode AI deployment governance without triggering compute monitoring thresholds because governance frameworks target training concentration while inference optimization distributes capability below detection.md

@@ -0,0 +1,69 @@
+---
+type: claim
+domain: ai-alignment
+description: "Compute governance (Heim/GovAI, export controls, EO 14110) monitors training runs above FLOP thresholds, but inference efficiency gains (KV cache compression, MoE, weight quantization) make deployment cheaper and more distributed without crossing any monitored threshold — creating a widening gap between what governance can see and where capability actually deploys"
+confidence: experimental
+source: "Heim et al. 2024 compute governance framework (training-focused thresholds), TurboQuant (Google Research, arXiv 2504.19874, ICLR 2026), DeepSeek MoE architecture, GPTQ/AWQ weight quantization literature, Shavit 2023 (compute monitoring proposals)"
+created: 2026-03-25
+depends_on:
+  - "the training-to-inference shift structurally favors distributed AI architectures because inference optimizes for power efficiency and cost-per-token where diverse hardware competes while training optimizes for raw throughput where NVIDIA monopolizes"
+  - "compute export controls are the most impactful AI governance mechanism but target geopolitical competition not safety leaving capability development unconstrained"
+  - "compute supply chain concentration is simultaneously the strongest AI governance lever and the largest systemic fragility because the same chokepoints that enable oversight create single points of failure"
+challenged_by:
+  - "Inference governance could target model weights rather than compute — controlling distribution of capable models is more tractable than monitoring inference hardware"
+  - "Inference at scale still requires identifiable infrastructure (cloud providers, API endpoints) that can be monitored"
+  - "The most dangerous capabilities (autonomous agents, bioweapon design) may require training-scale compute even for inference"
+secondary_domains:
+  - collective-intelligence
+---
+
+# Inference efficiency gains erode AI deployment governance without triggering compute monitoring thresholds because governance frameworks target training concentration while inference optimization distributes capability below detection
+
+The compute governance framework — the most tractable lever for AI safety, as Heim, Sastry, and colleagues at GovAI have established — is built around training. Reporting thresholds trigger on large training runs (EO 14110 set the bar at ~10^26 FLOP). Export controls restrict chips used for training clusters. Hardware monitoring proposals (Shavit 2023) target training-scale compute.
+
+But inference efficiency is improving through multiple independent, compounding mechanisms that make deployment cheaper and more distributed without crossing any of these thresholds. This creates a structural governance gap: the framework monitors where capability is *created* but not where it *deploys*.
+
+## The asymmetry
+
+**Training governance is concentrated and visible.** A frontier training run requires thousands of GPUs in identifiable datacenters, costs $100M+, takes weeks to months, and consumes megawatts of power. There are perhaps 10-20 organizations worldwide capable of frontier training. This concentration makes governance tractable — there are few entities to monitor, the activity is physically conspicuous, and the compute requirements cross identifiable thresholds.
+
+**Inference governance is distributed and invisible.** Once a model exists, inference can run on dramatically less hardware than training required:
+
+- **KV cache compression** (TurboQuant, KIVI, KVQuant, 15+ methods): 6x memory reduction enables longer contexts on smaller hardware. Google's TurboQuant achieves 3-bit KV cache with zero accuracy loss, 8x attention speedup, no retraining needed. The field is advancing rapidly with over 15 competing approaches.
+
+- **Weight quantization** (GPTQ, AWQ, QuIP): 4-bit weight compression enables 70B+ models to run on consumer GPUs with 24GB VRAM. A model that required an A100 cluster for training can run inference on a gaming PC.
+
+- **Mixture of Experts** (DeepSeek): Activates 37B of 671B parameters per call, reducing per-inference compute by ~18x versus dense models of equivalent capability.
+
+- **Hardware-native optimization** (NVIDIA NVFP4, ARM Ethos NPU): Hardware designed for efficient inference enables on-device deployment that never touches cloud infrastructure.
+
+These mechanisms compound multiplicatively. A model that cost $100M to train can be deployed for inference at a cost of pennies per query on hardware that no governance framework monitors.
+
+## Why this matters for alignment
+
+The governance gap has three specific consequences:
+
+**1. Capability proliferates below the detection threshold.** Open-weight models (Llama, Mistral, DeepSeek) combined with inference optimization mean that capable AI deploys to millions of endpoints. None of these endpoints individually cross any compute governance threshold. The governance framework is designed for the elephant (training clusters) and misses the swarm (distributed inference).
+
+**2. The most dangerous capabilities may be inference-deployable.** Autonomous agent loops, multi-step reasoning chains, and tool-using AI systems are inference workloads. An agent that can plan, execute, and adapt runs on inference — potentially on consumer hardware. If the risk from AI shifts from "building a dangerous model" to "deploying a capable model dangerously," inference governance becomes the binding constraint, and current frameworks don't address it.
+
+**3. The gap widens with every efficiency improvement.** Each new KV cache method, each new quantization technique, each hardware optimization makes inference cheaper and more distributed. The governance framework monitors a fixed threshold while the inference floor drops continuously. This is not a one-time gap — it is a structurally widening one.
+
+## Challenges
+
+**Model weight governance may be more tractable than inference compute governance.** Rather than monitoring inference hardware (impossible at scale), governance could target the distribution of model weights. Closed-weight models (GPT, Claude) already restrict deployment through API access. Open-weight governance (licensing, usage restrictions) is harder but at least targets the right layer. Counter: open-weight models are already widely distributed, and weight governance faces the same enforcement problems as digital content protection (once released, recall is impractical).
+
+**Large-scale inference is still identifiable.** Serving millions of users requires cloud infrastructure that is visible and regulatable. Cloud providers (AWS, Azure, GCP) can implement KYC and usage monitoring for inference. Counter: this only captures inference served through major cloud providers, not on-premise or edge deployments, and inference costs dropping means more organizations can self-host.
+
+**Some dangerous capabilities may still require training-scale compute.** Developing novel biological weapons or breaking cryptographic systems may require training-scale reasoning chains even at inference time. If the most dangerous capabilities are also the most compute-intensive, the training-centric governance framework captures them indirectly. Counter: the "most dangerous" threshold keeps dropping as inference efficiency improves and agent architectures enable multi-step reasoning on smaller compute budgets.
+
+---
+
+Relevant Notes:
+- [[the training-to-inference shift structurally favors distributed AI architectures because inference optimizes for power efficiency and cost-per-token where diverse hardware competes while training optimizes for raw throughput where NVIDIA monopolizes]] — the parent claim describing the shift this governance gap exploits
+- [[compute export controls are the most impactful AI governance mechanism but target geopolitical competition not safety leaving capability development unconstrained]] — export controls are training-focused; this claim shows inference-focused erosion
+- [[compute supply chain concentration is simultaneously the strongest AI governance lever and the largest systemic fragility because the same chokepoints that enable oversight create single points of failure]] — concentration enables training governance but inference distributes beyond the chokepoints
+- [[technology advances exponentially but coordination mechanisms evolve linearly creating a widening gap]] — this claim is a specific instance of the general pattern applied to inference efficiency vs governance framework adaptation
+
+Topics:
+- [[domains/ai-alignment/_map]]

domains/ai-alignment/physical infrastructure constraints on AI scaling create a natural governance window because packaging memory and power bottlenecks operate on 2-10 year timescales while capability research advances in months.md

@@ -0,0 +1,66 @@
+---
+type: claim
+domain: ai-alignment
+description: "CoWoS packaging, HBM memory, and datacenter power each gate AI compute scaling on timescales (2-10 years) much longer than algorithmic or architectural advances (months) — this mismatch creates a window where alignment research can outpace deployment even without deliberate slowdown"
+confidence: experimental
+source: "TSMC CoWoS capacity constraints (CEO public statements), HBM vendor sell-out confirmations (SK Hynix, Micron CFOs), IEA/Goldman Sachs datacenter power projections, Epoch AI compute doubling trends, Heim et al. 2024 compute governance framework"
+created: 2026-03-24
+depends_on:
+  - "technology advances exponentially but coordination mechanisms evolve linearly creating a widening gap"
+  - "safe AI development requires building alignment mechanisms before scaling capability"
+challenged_by:
+  - "Algorithmic efficiency gains may outpace physical constraints — Epoch AI finds algorithms halve required compute every 8-9 months"
+  - "Physical constraints are temporary — CoWoS alternatives by 2027, HBM4 increases capacity, nuclear can eventually meet power demand"
+  - "If the US self-limits via infrastructure lag, compute migrates to jurisdictions with fewer safety norms"
+secondary_domains:
+  - collective-intelligence
+---
+
+# Physical infrastructure constraints on AI scaling create a natural governance window because packaging memory and power bottlenecks operate on 2-10 year timescales while capability research advances in months
+
+The alignment field treats AI scaling as a function of investment and algorithms. But the physical substrate imposes its own timescales: advanced packaging expansion takes 2-3 years, HBM supply is sold out for 1-2 years forward, new power generation takes 5-10 years. These timescales are longer than the algorithmic improvement cycle (months) but shorter than institutional governance cycles (decades). This mismatch creates a window — not designed, but real — where physical constraints slow deployment faster than they slow alignment research.
+
+## The timescale mismatch
+
+Three independent physical constraints gate AI compute scaling, each on different timescales:
+
+**Packaging (2-3 years):** TSMC's CoWoS capacity is sold out through 2026 with demand exceeding supply even at planned expansion rates. Google has already cut TPU production targets due to CoWoS constraints. Intel's EMIB alternative is gaining interest but won't reach comparable scale before 2027-2028. Each new AI chip generation requires larger interposers, so the bottleneck worsens per generation.
+
+**Memory (1-2 years):** All three HBM vendors (SK Hynix, Samsung, Micron) have confirmed their supply is sold out through 2026. HBM4 accelerates to meet NVIDIA's next-generation architecture, but each GB of HBM requires 3-4x the wafer capacity of DDR5, creating structural supply tension.
+
+**Power (5-10 years):** New power generation takes 3-7 years to build. Grid interconnection queues in the US average 5+ years with only ~20% of projects reaching commercial operation. Nuclear deals for AI (Microsoft-Constellation, Amazon-X-Energy, Google-Kairos) cover 2-3 GW near-term against projected need of 25-30 GW additional capacity. This is the longest-horizon constraint.
+
+Meanwhile, frontier training compute doubles every 9-10 months (Epoch AI), and algorithmic efficiency improvements halve required compute every 8-9 months. The demand curve is exponential; the supply curves are linear or stepwise.
+
+## Why this is a governance window
+
+Lennart Heim and colleagues at GovAI/RAND have argued that compute is the most governable input to AI development because it is physical, trackable, and produced by a concentrated supply chain. Physical infrastructure constraints amplify this governability: not only can you track who has compute, the total amount of compute is itself limited by physical bottlenecks.
+
+This creates what I call "alignment by infrastructure lag" — the physical substrate buys time for alignment research without requiring anyone to deliberately slow down. The window exists because:
+
+1. **Alignment research is not compute-constrained.** Theoretical alignment work, interpretability research, governance design, and evaluation methodology don't require frontier training clusters. They require researchers, ideas, and modest compute for experiments.
+
+2. **Deployment IS compute-constrained.** Deploying AI capabilities at scale (inference for billions of users, new training runs for frontier models) requires the physical infrastructure that is bottlenecked.
+
+3. **The mismatch favors alignment.** The activities that need more time (alignment research) can proceed unconstrained while the activities that create risk (capability scaling and deployment) are physically gated.
+
+## Challenges
+
+**Algorithmic progress may route around physical constraints.** If algorithmic efficiency improvements (halving required compute every 8-9 months per Epoch AI) compound faster than physical constraints bind, the governance window closes. A 10x capability jump may come from better algorithms on existing hardware, not from new hardware.
+
+**The window is temporary.** CoWoS alternatives may break the packaging bottleneck by 2027. HBM4 increases per-stack capacity. Nuclear and natural gas can eventually meet power demand. The 2-5 year window where these constraints bind most tightly is the window — not a permanent condition.
+
+**Geographic asymmetry.** Physical constraints are location-specific. If US infrastructure lags while other jurisdictions build faster, compute migrates to regions with fewer safety norms. The constraint doesn't reduce total AI capability — it shifts where capability develops. This is the strongest counter-argument and applies equally to deliberate slowdown proposals.
+
+**This is not a strategy — it's an observation.** The claim is that the window exists, not that it should be relied upon. Depending on infrastructure lag for alignment is like depending on traffic for punctuality — it might work but it's not a plan.
+
+---
+
+Relevant Notes:
+- [[technology advances exponentially but coordination mechanisms evolve linearly creating a widening gap]] — physical infrastructure constraints partially close this gap by slowing the exponential
+- [[safe AI development requires building alignment mechanisms before scaling capability]] — infrastructure lag creates a natural version of this ordering
+- [[compute export controls are the most impactful AI governance mechanism but target geopolitical competition not safety leaving capability development unconstrained]] — physical constraints complement export controls by limiting total compute regardless of who controls it
+- [[the alignment tax creates a structural race to the bottom because safety training costs capability and rational competitors skip it]] — infrastructure constraints apply to all competitors equally, unlike voluntary safety commitments
+
+Topics:
+- [[domains/ai-alignment/_map]]

domains/ai-alignment/the training-to-inference shift structurally favors distributed AI architectures because inference optimizes for power efficiency and cost-per-token where diverse hardware competes while training optimizes for raw throughput where NVIDIA monopolizes.md

@@ -0,0 +1,76 @@
+---
+type: claim
+domain: ai-alignment
+description: "As inference grows from ~33% to ~66% of AI compute by 2026, the hardware landscape shifts from NVIDIA-monopolized centralized training clusters to diverse distributed inference on ARM, custom ASICs, and edge devices — changing who can deploy AI capability and how governable deployment is"
+confidence: experimental
+source: "Deloitte 2026 inference projections, Epoch AI compute trends, ARM Neoverse inference benchmarks, industry analysis of training vs inference economics"
+created: 2026-03-24
+depends_on:
+  - "three paths to superintelligence exist but only collective superintelligence preserves human agency"
+  - "collective superintelligence is the alternative to monolithic AI controlled by a few"
+challenged_by:
+  - "NVIDIA's inference optimization (TensorRT, Blackwell transformer engine) may maintain GPU dominance even for inference"
+  - "Open-weight model proliferation is a greater driver of distribution than hardware diversity"
+  - "Inference at scale (serving billions of users) still requires massive centralized infrastructure"
+secondary_domains:
+  - collective-intelligence
+---
+
+# The training-to-inference shift structurally favors distributed AI architectures because inference optimizes for power efficiency and cost-per-token where diverse hardware competes while training optimizes for raw throughput where NVIDIA monopolizes
+
+AI compute is undergoing a structural shift from training-dominated to inference-dominated workloads. Training accounted for roughly two-thirds of AI compute in 2023; by 2026, inference is projected to consume approximately two-thirds. This reversal changes the competitive landscape for AI hardware and, consequently, who controls AI capability deployment.
+
+## The economic logic
+
+Training optimizes for raw throughput — the largest, most power-hungry chips in the biggest clusters win. This favors NVIDIA's monopoly position: CUDA ecosystem lock-in, InfiniBand networking for multi-node training, and CoWoS packaging allocation that gates how many competing accelerators can ship. Training a frontier model requires concentrated capital ($100M+), concentrated hardware (thousands of GPUs), and concentrated power (100+ MW). Few organizations can do this.
+
+Inference optimizes differently: cost-per-token, latency, and power efficiency. These metrics open the field to diverse hardware architectures. ARM-based processors (Graviton4, Axion, Grace) compete on power efficiency. Custom ASICs (Google TPU, Amazon Trainium, Meta MTIA) optimize for specific model architectures. Edge devices run smaller models locally. The competitive landscape for inference is fundamentally more diverse than for training.
+
+Inference can account for 80-90% of the lifetime cost of a production AI system — it runs continuously while training is periodic. As inference dominates economics, the hardware that wins inference shapes the industry structure.
+
+## Governance implications
+
+Training's concentration makes it governable. A small number of organizations with identifiable hardware in identifiable locations perform frontier training. Compute governance proposals (Heim et al., GovAI) leverage this concentration: reporting thresholds for large training runs, KYC for cloud compute, hardware-based monitoring.
+
+Inference's distribution makes it harder to govern. Once a model is trained and weights are distributed (open-weight models), inference capability distributes to anyone with sufficient hardware — which, for inference, is much more accessible than for training. The governance surface area expands from dozens of training clusters to millions of inference endpoints.
+
+This creates a structural tension: the same shift that favors distributed AI architectures (good for avoiding monolithic control) also makes AI deployment harder to monitor and regulate (challenging for safety oversight). The governance implications of this shift are underexplored — the existing discourse treats inference economics as a business question, not a governance question.
+
+## Connection to collective intelligence
+
+The inference shift is directionally favorable for collective intelligence architectures. If inference can run on diverse, distributed hardware, then multi-agent systems with heterogeneous hardware become architecturally natural rather than forced. This is relevant to our claim that [[collective superintelligence is the alternative to monolithic AI controlled by a few]] — the physical infrastructure is moving in a direction that makes collective architectures more viable.
+
+However, this does not guarantee distributed outcomes. NVIDIA's inference optimization (TensorRT-LLM, Blackwell's FP4 transformer engine) aims to maintain GPU dominance even for inference. And inference at scale (serving billions of users) still requires substantial centralized infrastructure — the distribution advantage applies most strongly at the edge and for specialized deployments.
+
+## Inference efficiency compounds through multiple independent mechanisms
+
+The inference shift is not a single trend — it is being accelerated by at least four independent compression mechanisms operating simultaneously:
+
+1. **Algorithmic compression (KV cache quantization):** Google's TurboQuant (arXiv 2504.19874, ICLR 2026) compresses KV caches to 3 bits per value with zero measurable accuracy loss, delivering 6x memory reduction and 8x attention speedup on H100 GPUs. The technique is data-oblivious (no calibration needed) and provably near-optimal. TurboQuant is one of 15+ competing KV cache methods (KIVI, KVQuant, RotateKV, PALU, Lexico), indicating a crowded research frontier where gains will continue compounding. Critically, these methods reduce the memory footprint of inference without changing the model itself — making deployment cheaper on existing hardware.
+
+2. **Architectural efficiency (Mixture of Experts):** DeepSeek's MoE architecture activates only 37B of 671B total parameters per inference call, delivering frontier performance at a fraction of the compute cost per token.
+
+3. **Hardware-native compression:** NVIDIA's NVFP4 on Blackwell provides hardware-native FP4 KV cache support, delivering 50% memory reduction with zero software complexity. This competes with algorithmic approaches but is NVIDIA-specific.
+
+4. **Precision reduction (quantization of model weights):** Methods like GPTQ, AWQ, and QuIP compress model weights to 4-bit or lower, enabling models that previously required 80GB+ HBM to run on consumer GPUs with 24GB VRAM.
+
+The compound effect of these independent mechanisms means inference cost-per-token declines faster than any single trend suggests. Each mechanism targets a different bottleneck (KV cache memory, active parameters, hardware precision, weight size), so they stack multiplicatively rather than diminishing each other.
+
+## Challenges
+
+**NVIDIA may hold inference too.** NVIDIA's vertical integration strategy (CUDA + TensorRT + full-rack inference solutions) is designed to prevent the inference shift from eroding their position. If NVIDIA captures inference as effectively as training, the governance implications of the shift are muted.
+
+**Open weights matter more than hardware diversity.** The distribution of AI capability may depend more on model weight availability (open vs. closed) than on hardware diversity. If frontier models remain closed, hardware diversity at the inference layer doesn't distribute frontier capability.
+
+**The claim is experimental, not likely.** The inference shift is a measured trend, but its governance implications are projected, not observed. The claim connects an economic shift to a governance conclusion — the connection is structural but hasn't been tested.
+
+---
+
+Relevant Notes:
+- [[collective superintelligence is the alternative to monolithic AI controlled by a few]] — the inference shift makes this architecturally more viable
+- [[compute export controls are the most impactful AI governance mechanism but target geopolitical competition not safety leaving capability development unconstrained]] — export controls target training compute; inference compute is harder to control
+- [[technology advances exponentially but coordination mechanisms evolve linearly creating a widening gap]] — the inference shift widens this gap by distributing capability faster than governance can adapt
+- [[economic forces push humans out of every cognitive loop where output quality is independently verifiable because human-in-the-loop is a cost that competitive markets eliminate]] — inference cost competition accelerates this dynamic
+
+Topics:
+- [[domains/ai-alignment/_map]]

domains/energy/AI datacenter power demand creates a 5-10 year infrastructure lag because grid construction and interconnection cannot match the pace of chip design cycles.md

@@ -0,0 +1,42 @@
+---
+type: claim
+domain: energy
+description: "Projected 8-9% of US electricity by 2030 for datacenters, nuclear deals cover 2-3 GW near-term against 25-30 GW needed, grid interconnection averages 5+ years with only 20% of projects reaching commercial operation"
+confidence: likely
+source: "Astra, Theseus compute infrastructure research 2026-03-24; IEA, Goldman Sachs April 2024, de Vries 2023 in Joule, grid interconnection queue data"
+created: 2026-03-24
+secondary_domains: ["ai-alignment", "manufacturing"]
+depends_on:
+  - "power is the binding constraint on all space operations because every capability from ISRU to manufacturing to life support is power-limited"
+  - "knowledge embodiment lag means technology is available decades before organizations learn to use it optimally creating a productivity paradox"
+challenged_by:
+  - "Nuclear SMRs and modular gas turbines may provide faster power deployment than traditional grid construction"
+  - "Efficiency improvements in inference hardware may reduce power demand growth below current projections"
+---
+
+# AI datacenter power demand creates a 5-10 year infrastructure lag because grid construction and interconnection cannot match the pace of chip design cycles
+
+AI datacenter power demand is projected to consume 8-9% of US electricity by 2030, up from ~2.5% in 2024. This represents 25-30 GW of additional capacity needed. But new power generation takes 3-7 years to build, and US grid interconnection queues average 5+ years with only ~20% of projects reaching commercial operation.
+
+The timescale mismatch is severe: chip design cycles operate on 1-2 year cadences (NVIDIA releases a new architecture annually), algorithmic efficiency improvements happen in months, but the power infrastructure to run the chips takes 5-10 years. This is the longest-horizon constraint on AI compute scaling and the one least susceptible to engineering innovation.
+
+Nuclear power deals for AI datacenters have been announced: Microsoft-Constellation (Three Mile Island restart), Amazon-X-Energy (SMRs), Google-Kairos (advanced fission). These cover 2-3 GW near-term — meaningful but an order of magnitude short of the projected 25-30 GW need. The rest must come from gas, renewables+storage, or grid expansion that faces permitting, construction, and interconnection delays.
+
+This creates a structural parallel with space development: [[power is the binding constraint on all space operations because every capability from ISRU to manufacturing to life support is power-limited]]. The same pattern applies terrestrially — every AI capability is ultimately power-limited, and the power infrastructure cannot match the pace of capability demand.
+
+The energy permitting timeline now exceeds construction timelines in many jurisdictions — a governance gap directly analogous to the technology-governance lag in space, where regulatory frameworks haven't adapted to the pace of technological change.
+
+## Challenges
+
+Nuclear SMRs (NuScale, X-Energy, Kairos) and modular gas turbines may provide faster power deployment than traditional grid construction, potentially compressing the lag from 5-10 years to 3-5 years. Efficiency improvements in inference hardware (the training-to-inference shift favoring power-efficient architectures) may reduce demand growth below current projections. Some hyperscalers are building private power infrastructure, bypassing the grid interconnection queue entirely. But even optimistic scenarios show power demand growing faster than supply through at least 2028-2030.
+
+---
+
+Relevant Notes:
+- [[power is the binding constraint on all space operations because every capability from ISRU to manufacturing to life support is power-limited]] — the same power constraint applies terrestrially for AI
+- [[physical infrastructure constraints on AI scaling create a natural governance window because packaging memory and power bottlenecks operate on 2-10 year timescales while capability research advances in months]] — power is the longest-horizon constraint in Theseus's governance window
+- [[knowledge embodiment lag means technology is available decades before organizations learn to use it optimally creating a productivity paradox]] — grid modernization follows the same lag pattern as electrification
+- [[fusion contributing meaningfully to global electricity is a 2040s event at the earliest because 2026-2030 demonstrations must succeed before capital flows to pilot plants that take another decade to build]] — fusion cannot solve the AI power problem in the relevant timeframe
+
+Topics:
+- [[energy systems]]

domains/internet-finance/Ooki DAO proved that DAOs without legal wrappers face general partnership liability making entity structure a prerequisite for any futarchy-governed vehicle.md

@@ -44,6 +44,12 @@ Since [[futarchy solves trustless joint ownership not just better decision-makin
 
 ---
 
+### Additional Evidence (extend)
+*Source: [[2026-03-26-cftc-anprm-prediction-markets-federal-register]] | Added: 2026-03-26*
+
+The CFTC ANPRM regulatory context compounds the entity structure requirement identified in Ooki DAO: without futarchy-specific comments distinguishing governance markets from gaming/entertainment prediction markets, the default CFTC classification will likely treat DAO governance mechanisms as gaming products. This means futarchy DAOs need both (1) legal entity wrapping to avoid general partnership liability and (2) affirmative regulatory positioning to avoid gaming classification—entity structure alone is necessary but insufficient.
+
+
 Relevant Notes:
 - [[MetaDAOs Cayman SPC houses all launched projects as ring-fenced SegCos under a single entity with MetaDAO LLC as sole Director]] — how MetaDAO addresses the entity wrapper requirement
 - [[two legal paths through MetaDAO create a governance binding spectrum from commercially reasonable efforts to legally binding and determinative]] — the spectrum of legal binding that Ooki DAO makes critical

domains/internet-finance/metadao-ico-platform-demonstrates-15x-oversubscription-validating-futarchy-governed-capital-formation.md

@@ -136,6 +136,12 @@ P2P.me ICO on MetaDAO described as 'one of the most compelling public sale oppor
 
 Futardio's parallel permissionless platform shows even more extreme oversubscription patterns: Superclaw achieved 11,902% oversubscription ($6M raised) and Futardio Cult 22,806% ($11.4M), suggesting permissionless mode may amplify rather than dampen oversubscription dynamics
 
+### Additional Evidence (extend)
+*Source: [[2026-03-26-pine-analytics-p2p-protocol-ico-analysis]] | Added: 2026-03-26*
+
+P2P.me ICO targets $6M raise (10M tokens at $0.60) with 50% float at TGE (12.9M tokens liquid), the highest initial float in MetaDAO ICO history. Prior institutional investment totaled $2.23M (Reclaim Protocol $80K March 2023, Alliance DAO $350K March 2024, Multicoin $1.4M January 2025, Coinbase Ventures $500K February 2025). Pine Analytics rates the project CAUTIOUS due to 182x gross profit multiple and 50% float creating structural headwind (Delphi Digital predicts 30-40% passive/flipper behavior).
+
+
 
 
 

domains/internet-finance/polymarket-achieved-us-regulatory-legitimacy-through-qcx-acquisition-establishing-prediction-markets-as-cftc-regulated-derivatives.md

@@ -88,6 +88,12 @@ CFTC ANPRM RIN 3038-AF65 (March 2026) reopens the regulatory framework question
 
 Polymarket CFTC approval occurred in 2025 via QCX acquisition with $112M valuation. This established prediction markets as CFTC-regulated derivatives, but the March 2026 ANPRM shows the regulatory framework still treats all prediction markets uniformly without distinguishing governance applications.
 
+### Additional Evidence (extend)
+*Source: [[2026-03-26-tg-shared-0xweiler-2037189643037200456-s-46]] | Added: 2026-03-26*
+
+Polymarket reportedly seeking $20 billion valuation as of March 7, 2026, with confirmed token and airdrop plans. This represents significant institutional validation of the prediction market model beyond just regulatory legitimacy.
+
+
 
 
 Relevant Notes:

domains/internet-finance/polymarket-kalshi-duopoly-emerging-as-dominant-us-prediction-market-structure-with-complementary-regulatory-models.md

@@ -46,6 +46,18 @@ The emerging circuit split (Fourth and Ninth Circuits pro-state, Third Circuit p
 
 ---
 
+### Additional Evidence (confirm)
+*Source: [[2026-03-26-tg-shared-0xweiler-2037189643037200456-s-46]] | Added: 2026-03-26*
+
+Kalshi raised at $22 billion valuation on March 19, 2026, just 12 days after Polymarket's reported $20 billion valuation target. The near-parity valuations confirm the duopoly structure with both platforms achieving similar market recognition.
+
+### Additional Evidence (confirm)
+*Source: [[2026-03-26-tg-source-m3taversal-jussy-world-thread-on-polymarket-projected-revenu]] | Added: 2026-03-26*
+
+Polymarket projected $172M/month revenue with $15.77B valuation versus Kalshi $110M/month with $18.6B pre-IPO valuation. Both platforms operating at similar scale with different regulatory approaches (Polymarket via QCX acquisition, Kalshi as CFTC-regulated exchange).
+
+
+
 Relevant Notes:
 - [[Polymarket vindicated prediction markets over polling in 2024 US election]]
 - [[MetaDAO is the futarchy launchpad on Solana where projects raise capital through unruggable ICOs governed by conditional markets creating the first platform for ownership coins at scale]]

domains/internet-finance/prediction-market-boom-is-primarily-a-sports-gambling-boom-which-weakens-the-information-aggregation-narrative.md

@@ -0,0 +1,53 @@
+---
+type: claim
+domain: internet-finance
+secondary_domains: [mechanisms]
+description: "Sports betting dominates prediction market volume (37-78% depending on platform and period), meaning the 'prediction market boom' is largely sports gambling repackaged — this weakens the claim that growth validates information aggregation mechanisms"
+confidence: likely
+source: "Messari (@0xWeiler Polymarket valuation, Mar 2026), Kalshi March Madness data, CertiK 2025 report"
+created: 2026-03-26
+---
+
+# The prediction market boom is primarily a sports gambling boom which weakens the information aggregation narrative
+
+The headline numbers for prediction market growth ($63.5B in 2025, $200B+ annualized in 2026) obscure a critical composition fact: sports betting is the dominant category driving volume, ranging from 37% of Polymarket's February 2026 volume to 78.6% of Kalshi's volume during peak sports periods.
+
+Kalshi's breakout moment — the $22B valuation — was catalyzed by March Madness. A single 4-day stretch generated $25.5M in fees, more than Kalshi's first 5 months of 2025 combined. The $3.4B weekly volume during March Madness week was driven by the same behavioral dynamics as DraftKings and FanDuel, not by novel information aggregation.
+
+This matters for the futarchy thesis because the prediction market growth narrative is frequently cited as evidence that "markets aggregate information better than votes" — the core futarchy premise. But sports betting validates entertainment demand for probabilistic wagering, not the informational efficiency of conditional markets for governance decisions.
+
+Polymarket's February 2026 category breakdown:
+1. Sports: $3.0B (37%)
+2. Crypto: $2.4B (30%) — primarily 5-min and 15-min up/down markets (gambling-adjacent)
+3. Politics: $2.2B (28%)
+4. Other: $342.8M (5%)
+
+The "crypto" category is notable: 5-minute and 15-minute up/down markets are functionally binary options on price movement, not information aggregation about real-world events. Combined with sports, ~67% of Polymarket volume is gambling-adjacent.
+
+The 5% "other" category — which includes science, technology, economics, and the kinds of questions that most resemble governance decisions — grew 1,637% YoY but remains a rounding error in absolute terms. This is where information aggregation actually happens, and it's negligible relative to total volume.
+
+The counter-argument: sports betting still demonstrates that conditional market infrastructure works at scale, price discovery mechanisms function under high volume, and users will provide liquidity when incentives are clear. These are necessary conditions for decision markets even if the use case is different. The mechanism is validated even if the application isn't.
+
+## Evidence
+
+- Polymarket February 2026: Sports 37%, Crypto 30%, Politics 28%, Other 5%
+- Kalshi: Sports at 78.6% of volume during peak weeks (January 2026 NFL playoffs)
+- Kalshi March Madness week: $3.4B volume, $33.1M fees
+- Kalshi March Madness 4-day stretch: $25.5M in fees (more than first 5 months of 2025)
+- CertiK: Technology & Science markets grew 1,637% YoY but remain tiny in absolute terms
+- Crypto "up/down" markets: 5-min and 15-min resolution windows — functionally binary options
+- US sportsbook volume: $166.9B in 2025 — prediction markets are converging with this market, not creating a new one
+
+challenged_by: The counter-argument that infrastructure validation transfers even when use cases differ. Sports betting proves the conditional market mechanism works at scale — the question is whether that's sufficient for futarchy adoption or whether governance requires fundamentally different market structures.
+
+---
+
+Relevant Notes:
+- [[prediction-market-growth-builds-infrastructure-for-decision-markets-but-conversion-is-not-happening]] — companion claim about the non-conversion
+- [[Polymarket vindicated prediction markets over polling in 2024 US election]] — the 2024 election was the one prediction market event that DID demonstrate information aggregation over entertainment
+- [[speculative markets aggregate information through incentive and selection effects not wisdom of crowds]] — the theoretical mechanism; sports betting validates selection effects (skilled bettors win) but not information aggregation per se
+- [[prediction-market-scale-exceeds-decision-market-scale-by-two-orders-of-magnitude-showing-pure-forecasting-dominates-governance-applications]] — scale gap partially explained by sports gambling driving prediction market numbers
+
+Topics:
+- domains/internet-finance/_map
+- core/mechanisms/_map

domains/internet-finance/prediction-market-growth-builds-infrastructure-for-decision-markets-but-conversion-is-not-happening.md

@@ -0,0 +1,60 @@
+---
+type: claim
+domain: internet-finance
+secondary_domains: [mechanisms, grand-strategy]
+description: "Prediction markets grew from $15.8B to $63.5B annual volume (2024-2025) and are on a $200B+ run rate in 2026, building liquidity infrastructure and regulatory precedent that decision markets could inherit — but no evidence exists that this conversion is occurring"
+confidence: likely
+source: "Messari (@0xWeiler valuation thread, Mar 2026), CertiK 2025 report, Pine Analytics MetaDAO Q4 2025 report, Robin Hanson (Overcoming Bias 2025)"
+created: 2026-03-26
+---
+
+# Prediction market growth builds infrastructure for decision markets but the conversion is not happening
+
+Prediction markets exploded from $15.8B (2024) to $63.5B (2025) in annual trading volume, with February 2026 alone processing $23.2B combined across Polymarket and Kalshi — a 1,218% year-over-year increase. The annualized run rate now exceeds $200B, surpassing total US sportsbook volume ($166.9B in 2025). Kalshi raised at a $22B valuation on $263.5M in 2025 fees (83.5x multiple). Polymarket is seeking $20B with a confirmed $POLY token.
+
+Despite sharing the same conditional market mechanics, the decision market space remains tiny. MetaDAO — the leading futarchy implementation — has $219M total ecosystem marketcap and generated $2.51M in Q4 2025 fee revenue. The scale gap between prediction and decision markets has widened from ~100x (January 2026 estimate) to ~1,000x by volume.
+
+The infrastructure argument — that prediction markets build liquidity, train traders, establish regulatory precedent, and create tooling that decision markets can inherit — is theoretically sound but empirically unsubstantiated. No major prediction market platform has expanded into governance applications. No significant trader migration from Polymarket/Kalshi to MetaDAO futarchy markets has been documented. The applications driving prediction market growth (sports betting, political wagering, fast-resolving crypto up/down markets) are categorically different from governance decisions.
+
+Robin Hanson explicitly identifies this gap: he views current prediction markets as "necessary but insufficient precursors" and worries that regulatory backlash against sports/entertainment uses could "shut down the more promising markets that I've envisioned" as collateral damage. The regulatory risk is real — CFTC Chairman Selig withdrew proposed bans on political/sports contracts in late 2025, but the regulatory window could close.
+
+Three structural barriers prevent conversion:
+
+1. **Incentive mismatch** — Prediction market traders optimize for profit on event resolution. Decision market participants must hold governance tokens and care about organizational outcomes. The trader populations barely overlap.
+
+2. **Resolution clarity** — Prediction markets resolve unambiguously (who won?). Decision markets require defining success metrics (did this proposal increase token price?), introducing measurement complexity and longer time horizons that reduce trader participation.
+
+3. **Market size ceiling** — Prediction markets are consumer products with global addressable markets (anyone can bet on the Super Bowl). Decision markets are organizational infrastructure embedded in specific DAOs, limiting participants to stakeholders with governance exposure.
+
+## Evidence
+
+- Prediction market annual volume: $15.8B (2024) → $63.5B (2025) → $200B+ annualized run rate (Feb 2026)
+- February 2026 combined volume: $23.2B (up 1,218% YoY)
+- Polymarket February 2026: $7.9B (note: Paradigm found volume double-counted on dashboards due to NegRisk structure — real figure may be ~$4B)
+- Kalshi $22B valuation on $263.5M in 2025 fees (83.5x multiple, March 2026)
+- Kalshi March Madness week: $3.4B volume, $33.1M fees, $25.5M in 4-day stretch
+- MetaDAO Q4 2025: $2.51M fee revenue, $3.6M proposal volume, $219M ecosystem marketcap (Pine Analytics)
+- MetaDAO daily revenue as of March 9, 2026: ~$4,825/day
+- CertiK: 3 platforms control 95%+ of global prediction market volume; wash trading peaked near 60% on Polymarket in 2024
+- Hanson: "Prediction Markets Now" (Dec 2025) — views current markets as early, worries about regulatory collateral damage
+
+---
+
+### Additional Evidence (confirm)
+*Source: [[2026-03-26-tg-source-m3taversal-jussy-world-thread-on-polymarket-projected-revenu]] | Added: 2026-03-26*
+
+Polymarket's projected revenue jump from $4.26M to $172M/month demonstrates massive prediction market scaling, but this growth is in sports betting and political forecasting verticals, not governance applications. The infrastructure exists at scale but decision market adoption remains minimal.
+
+
+Relevant Notes:
+- [[prediction-market-scale-exceeds-decision-market-scale-by-two-orders-of-magnitude-showing-pure-forecasting-dominates-governance-applications]] — this claim updates and extends with 2026 data; gap is now ~1000x not ~100x
+- [[Polymarket vindicated prediction markets over polling in 2024 US election]] — the validation event that catalyzed growth
+- [[polymarket-kalshi-duopoly-emerging-as-dominant-us-prediction-market-structure-with-complementary-regulatory-models]] — duopoly now at ~$42B combined valuation
+- [[polymarket-achieved-us-regulatory-legitimacy-through-qcx-acquisition-establishing-prediction-markets-as-cftc-regulated-derivatives]] — regulatory legitimacy enables growth
+- [[MetaDAOs futarchy implementation shows limited trading volume in uncontested decisions]] — decision market liquidity challenge
+- [[futarchy adoption faces friction from token price psychology proposal complexity and liquidity requirements]] — adoption friction persists despite prediction market normalization
+- [[speculative markets aggregate information through incentive and selection effects not wisdom of crowds]] — the mechanism works at scale for prediction; question is whether it transfers to governance
+
+Topics:
+- domains/internet-finance/_map
+- core/mechanisms/_map

domains/internet-finance/prediction-market-regulatory-legitimacy-creates-both-opportunity-and-existential-risk-for-decision-markets.md

@@ -0,0 +1,50 @@
+---
+type: claim
+domain: internet-finance
+secondary_domains: [mechanisms, grand-strategy]
+description: "Kalshi's CFTC-regulated status and Polymarket's QCX acquisition normalize conditional markets, but regulatory backlash against sports/entertainment prediction markets could collaterally destroy decision market potential — Hanson's explicit concern"
+confidence: experimental
+source: "Robin Hanson 'Prediction Markets Now' (Dec 2025), CFTC regulatory actions, Kalshi $22B raise (Mar 2026), D&O liability analysis"
+created: 2026-03-26
+---
+
+# Prediction market regulatory legitimacy creates both opportunity and existential risk for decision markets
+
+The regulatory trajectory of prediction markets creates a fork that determines whether decision markets (futarchy) thrive or die as collateral damage.
+
+**The opportunity path:** Kalshi operates as a CFTC-regulated exchange. Polymarket achieved regulatory legitimacy through the QCX acquisition. CFTC Chairman Selig (sworn in December 2025) withdrew the proposed ban on political/sports event contracts, drafting new "clear standards" instead. This normalization creates regulatory precedent for all conditional market mechanisms — including futarchy. If regulators classify conditional markets as legitimate financial infrastructure, decision markets inherit that legitimacy.
+
+**The risk path:** Robin Hanson explicitly warns that a "prudish temperance movement may shut them down, and as a side effect shut down the more promising markets that I've envisioned." The risk is not hypothetical — prediction markets' growth is driven primarily by sports gambling (37-78% of volume), which triggers the same regulatory instincts as traditional gambling. If regulators decide prediction markets are gambling rather than information infrastructure, the crackdown would likely not distinguish between sports betting on Kalshi and governance markets on MetaDAO.
+
+**The D&O liability vector:** A new risk is emerging where prediction market prices create legal exposure for corporate officers. If Polymarket prices in a CEO departure that the company hasn't disclosed, plaintiffs may use market prices as evidence of failure to disclose material information. This could trigger corporate pushback against prediction markets generally, including governance applications.
+
+**The structural tension:** Decision markets need prediction markets to succeed enough to normalize conditional market mechanics, but not so much that the sports gambling association triggers a regulatory backlash. The optimal regulatory outcome for futarchy would be classification of conditional markets as governance/decision infrastructure rather than gambling — but the volume composition (dominated by sports/entertainment) makes this classification harder to argue.
+
+## Evidence
+
+- CFTC Chairman Selig withdrew proposed ban on political/sports event contracts (late 2025)
+- Kalshi: CFTC-regulated, $22B valuation, primarily sports volume
+- Polymarket: regulatory legitimacy via QCX acquisition, seeking $20B valuation
+- Hanson: "a prudish temperance movement may shut them down, and as a side effect shut down the more promising markets" (Overcoming Bias, Dec 2025)
+- D&O liability: plaintiffs using prediction market prices as evidence of failure to disclose (emerging legal theory, 2026)
+- CertiK: 3 platforms control 95%+ of volume — regulatory action against any one platform affects the entire sector
+
+---
+
+### Additional Evidence (extend)
+*Source: [[2026-03-26-cftc-anprm-prediction-markets-federal-register]] | Added: 2026-03-26*
+
+The CFTC ANPRM (March 2026) represents the first comprehensive federal rulemaking on prediction markets post-Polymarket legitimacy, but contains zero questions about governance decision markets versus event prediction markets. The 45-day comment window (deadline April 30, 2026) is the only near-term opportunity to establish regulatory distinction before default classification occurs. Institutional prediction market operators (5c(c) Capital backed by Polymarket/Kalshi CEOs, Truth Predict from Trump Media) have strong comment incentive but divergent interests from futarchy governance applications.
+
+
+Relevant Notes:
+- [[polymarket-achieved-us-regulatory-legitimacy-through-qcx-acquisition-establishing-prediction-markets-as-cftc-regulated-derivatives]] — the legitimacy pathway
+- [[polymarket-kalshi-duopoly-emerging-as-dominant-us-prediction-market-structure-with-complementary-regulatory-models]] — duopoly concentrates regulatory risk
+- [[the SEC frameworks silence on prediction markets and conditional tokens leaves futarchy governance mechanisms in a regulatory gap neither explicitly covered nor excluded from the token taxonomy]] — futarchy's regulatory gap
+- [[futarchy-governed entities are structurally not securities because prediction market participation replaces the concentrated promoter effort that the Howey test requires]] — futarchy's Howey defense depends on conditional markets being legal
+- [[prediction-market-growth-builds-infrastructure-for-decision-markets-but-conversion-is-not-happening]] — the infrastructure argument
+- [[prediction-market-boom-is-primarily-a-sports-gambling-boom-which-weakens-the-information-aggregation-narrative]] — sports composition drives regulatory risk
+
+Topics:
+- domains/internet-finance/_map
+- core/mechanisms/_map

domains/internet-finance/prediction-market-scale-exceeds-decision-market-scale-by-two-orders-of-magnitude-showing-pure-forecasting-dominates-governance-applications.md

@@ -32,12 +32,23 @@ This does not mean decision markets are failing — MetaDAO's $57.3M AUF and gro
 
 ---
 
+### Additional Evidence (confirm)
+*Source: [[2026-03-26-tg-source-m3taversal-jussy-world-thread-on-polymarket-projected-revenu]] | Added: 2026-03-26*
+
+Polymarket projected at $172M/month revenue at 0.80% fees versus metaDAO's demonstrated ~$11.4M single-day fundraise for Futardio. Kalshi at $110M/month and $18.6B pre-IPO valuation. This represents 15-40x monthly revenue scale difference between prediction markets (Polymarket/Kalshi) and decision market implementations.
+
+
 Relevant Notes:
 - [[Polymarket vindicated prediction markets over polling in 2024 US election]]
 - [[MetaDAO is the futarchy launchpad on Solana where projects raise capital through unruggable ICOs governed by conditional markets creating the first platform for ownership coins at scale]]
 - [[MetaDAOs futarchy implementation shows limited trading volume in uncontested decisions]]
 - [[futarchy adoption faces friction from token price psychology proposal complexity and liquidity requirements]]
 
+### Additional Evidence (extend — scale gap widening)
+*Source: Messari @0xWeiler thread (Mar 2026), Pine Analytics MetaDAO Q4 2025, CertiK 2025 report | Added: 2026-03-26*
+
+The scale gap has widened dramatically since the original claim. February 2026 combined prediction market volume was $23.2B (1,218% YoY), with Polymarket at $7.9B and Kalshi capturing the remainder. Annualized run rate now exceeds $200B, surpassing total US sportsbook volume ($166.9B in 2025). Meanwhile MetaDAO's ecosystem marketcap reached $219M with $2.51M Q4 2025 fee revenue and daily revenue of ~$4,825/day as of March 9, 2026. The gap has widened from the original ~100x estimate to ~1,000x by volume. Full year 2025: prediction markets did $63.5B (CertiK) versus MetaDAO's $3.6M in Q4 proposal volume — a 4,400x gap in the most favorable MetaDAO quarter. Note: Paradigm found Polymarket volume is double-counted on dashboards due to NegRisk market structures; real Polymarket figure may be ~50% of reported.
+
 Topics:
 - domains/internet-finance/_map
 - core/mechanisms/_map

domains/internet-finance/the DAO Reports rejection of voting as active management is the central legal hurdle for futarchy because prediction market trading must prove fundamentally more meaningful than token voting.md

@@ -53,6 +53,12 @@ The SEC's March 2026 Token Taxonomy framework partially obsoletes the 2017 DAO R
 
 ---
 
+### Additional Evidence (extend)
+*Source: [[2026-03-26-cftc-anprm-prediction-markets-federal-register]] | Added: 2026-03-26*
+
+The CFTC ANPRM creates a parallel regulatory hurdle: futarchy must prove it is categorically different not just from token voting (SEC framework) but also from event prediction markets (CFTC framework). The structural distinction argument—that governance markets resolve endogenous organizational decisions rather than exogenous events—is the mechanism that could satisfy both regulatory frameworks, but has not been articulated in any CFTC filing as of March 26, 2026.
+
+
 Relevant Notes:
 - [[Living Capital vehicles likely fail the Howey test for securities classification because the structural separation of capital raise from investment decision eliminates the efforts of others prong]] — the Living Capital-specific Howey analysis; this note addresses the broader metaDAO question
 - [[the SECs investment contract termination doctrine creates a formal regulatory off-ramp where crypto assets can transition from securities to commodities by demonstrating fulfilled promises or sufficient decentralization]] — the new framework that lowers the bar

domains/manufacturing/ASML EUV lithography monopoly is the deepest chokepoint in semiconductor manufacturing because 30 years of co-developed precision optics created an unreplicable ecosystem that gates all leading-edge chip production.md

@@ -0,0 +1,47 @@
+---
+type: claim
+domain: manufacturing
+description: "100% EUV market share, 83% total lithography, $350M+ per High-NA machine, ~50 systems/year production cap — ASML's 30-year co-development with Zeiss optics and TRUMPF light sources created a monopoly no competitor can replicate because the barrier is an entire ecosystem not a single technology"
+confidence: proven
+source: "Astra, ASML financial reports 2025, Zeiss SMT 30-year EUV retrospective, TrendForce, Tom's Hardware, Motley Fool March 2026"
+created: 2026-03-24
+secondary_domains: ["ai-alignment"]
+depends_on:
+  - "value in industry transitions accrues to bottleneck positions in the emerging architecture not to pioneers or to the largest incumbents"
+challenged_by:
+  - "China's domestic EUV efforts have achieved laboratory-scale wavelength generation by 2024-2025 though the gap from lab to production tool is measured in years"
+---
+
+# ASML EUV lithography monopoly is the deepest chokepoint in semiconductor manufacturing because 30 years of co-developed precision optics created an unreplicable ecosystem that gates all leading-edge chip production
+
+ASML holds 100% of the EUV lithography market and 83% of all lithography. No other company on Earth manufactures EUV machines. Canon and Nikon compete only in older DUV lithography. This is not a typical market concentration — it is an absolute monopoly on the technology required for every chip at 5nm and below.
+
+The monopoly is unreplicable because the barrier is an entire co-developed ecosystem, not a single technology or patent:
+
+**Zeiss SMT** (Oberkochen, Germany) produces the most precise mirrors ever made. Scaled to the size of Germany, the largest surface unevenness would be 0.1mm. Each mirror has 100+ atomically precise layers, each a few nanometers thick. Making one takes months. Zeiss holds ~1,500 patents and spent 25+ years co-developing these optics with ASML. The measurement systems needed to verify subatomic-level mirror precision didn't previously exist — Zeiss and ASML had to co-invent them.
+
+**Cymer/TRUMPF** light sources fire three lasers at 100,000 tin droplets per second to generate 13.5nm wavelength light. No conventional lens transmits EUV — it must be reflected through vacuum using the Zeiss mirrors. Each system requires components from 800+ suppliers.
+
+**Scale:** ASML shipped 48 EUV systems in 2025, ~250 cumulative. Standard EUV (NXE series) costs $150-200M. High-NA EUV (EXE series, enabling 2nm and below) costs $350-400M. Revenue: EUR 32.7B in 2025. Market cap: ~$527B — Europe's largest tech company. Backlog: EUR 38.8B. R&D: $5.3B/year.
+
+**ASML is the real enforcement mechanism for export controls.** China has received zero EUV machines. The Netherlands banned EUV exports in 2019 under US pressure and expanded restrictions to advanced DUV in September 2024. Controlling ASML's exports is equivalent to controlling access to leading-edge chipmaking. Chinese companies stockpiled DUV equipment aggressively (ASML sourced 49% of 2024 revenue from China), but without EUV they face severe penalties at 5nm and below.
+
+**China's DUV workaround is viable but punitive:** SMIC achieves 5nm using quadruple-patterning DUV with ~33% yield (vs TSMC's 80%+), 50% higher cost, and 3.8x more process steps (34 steps vs 9 for EUV). This enables strategic capability (Huawei Kirin 9000s) but not commercial competitiveness. CNAS flagged this as an export control loophole in December 2025.
+
+**ASML production capacity (~50 EUV systems/year) is a hard constraint on global fab expansion.** The number of leading-edge fabs the world can build per year is directly bottlenecked by one company's manufacturing throughput. High-NA capacity is ~5-6 units/year, targeting 20/year by 2028. Lead times are multi-year. This means ASML constrains TSMC, Samsung, and Intel's expansion plans simultaneously.
+
+## Challenges
+
+China has achieved EUV-range wavelength generation in laboratory conditions by 2024-2025, but has not demonstrated a production-capable integrated tool — the gap is measured in years. ASML is expanding capacity. The High-NA transition may ease some pressure by enabling more transistors per exposure. But the fundamental monopoly — rooted in 30 years of ecosystem co-development — shows no sign of eroding. Canon and Nikon have shown no public effort toward EUV. The only realistic path to a second EUV supplier would require a Zeiss-equivalent optics partner, a comparable light source, and a decade of integration — and even then it would produce a machine entering production a generation behind ASML.
+
+---
+
+Relevant Notes:
+- [[value in industry transitions accrues to bottleneck positions in the emerging architecture not to pioneers or to the largest incumbents]] — ASML holds the deepest bottleneck position in the entire semiconductor stack
+- [[CoWoS advanced packaging is the binding bottleneck on AI compute scaling because TSMC near-monopoly on interposer technology gates total accelerator output regardless of chip design capability]] — ASML gates what TSMC can fabricate; CoWoS gates what TSMC can package. Two independent bottlenecks.
+- [[semiconductor fab cost escalation means each new process node is a nation-state commitment because 20B-plus capital costs and multi-year construction create irreversible geographic path dependence]] — fab cost escalation is partly driven by EUV machine costs ($150-400M per tool)
+- [[TSMC manufactures 92 percent of advanced logic chips making Taiwan the single largest physical vulnerability in global technology infrastructure]] — TSMC's monopoly runs on ASML's monopoly — it's monopolies all the way down
+- [[compute supply chain concentration is simultaneously the strongest AI governance lever and the largest systemic fragility because the same chokepoints that enable oversight create single points of failure]] — ASML is the ultimate chokepoint underlying all the others
+
+Topics:
+- [[manufacturing systems]]

domains/manufacturing/CoWoS advanced packaging is the binding bottleneck on AI compute scaling because TSMC near-monopoly on interposer technology gates total accelerator output regardless of chip design capability.md

@@ -0,0 +1,39 @@
+---
+type: claim
+domain: manufacturing
+description: "TSMC CEO confirmed CoWoS sold out through 2026, Google cut TPU production targets — the bottleneck is not chip design but physical packaging capacity, and each new AI chip generation requires larger interposers worsening the constraint per generation"
+confidence: likely
+source: "Astra, Theseus compute infrastructure research 2026-03-24; TSMC CEO public statements, Google TPU production cuts"
+created: 2026-03-24
+secondary_domains: ["ai-alignment"]
+depends_on:
+  - "value in industry transitions accrues to bottleneck positions in the emerging architecture not to pioneers or to the largest incumbents"
+challenged_by:
+  - "Intel EMIB and other alternatives may break the TSMC CoWoS monopoly by 2027-2028"
+  - "chiplet architectures with smaller interposers could reduce packaging constraints"
+---
+
+# CoWoS advanced packaging is the binding bottleneck on AI compute scaling because TSMC near-monopoly on interposer technology gates total accelerator output regardless of chip design capability
+
+The AI compute supply chain's binding constraint is not chip design — it's packaging. TSMC's Chip-on-Wafer-on-Substrate (CoWoS) advanced packaging technology is required to integrate AI accelerators with HBM memory into functional modules. TSMC holds near-monopoly on this capability, and capacity is sold out through 2026.
+
+TSMC's CEO publicly confirmed the packaging bottleneck. Google has already cut TPU production targets due to CoWoS constraints. NVIDIA commands over 60% of CoWoS allocation, meaning its competitors fight over the remaining ~40% regardless of how good their chip designs are.
+
+The constraint worsens per generation: each new AI chip generation requires larger silicon interposers to accommodate more HBM stacks and wider memory bandwidth. NVIDIA's Blackwell GB200 NVL72 is a full-rack solution requiring massive packaging complexity. The trend toward system-level integration (entire racks as the unit of compute) amplifies packaging demand faster than capacity can expand.
+
+This makes CoWoS allocation the most consequential bottleneck position in the AI compute supply chain. Whoever controls packaging allocation controls who can ship AI hardware. This is a textbook case of [[value in industry transitions accrues to bottleneck positions in the emerging architecture not to pioneers or to the largest incumbents]] — TSMC's packaging division holds more leverage over AI scaling than any chip designer.
+
+## Challenges
+
+Intel's EMIB (Embedded Multi-die Interconnect Bridge) technology is gaining interest as a CoWoS alternative and could reach comparable capability by 2027-2028. Chiplet architectures with smaller interposers could reduce per-chip packaging demand. TSMC is aggressively expanding CoWoS capacity. The bottleneck is real in 2024-2026 but may ease by 2027-2028 as alternatives mature and capacity expands. The question is whether AI compute demand growth outpaces packaging supply expansion — current projections suggest demand wins through at least 2027.
+
+---
+
+Relevant Notes:
+- [[value in industry transitions accrues to bottleneck positions in the emerging architecture not to pioneers or to the largest incumbents]] — CoWoS allocation is THE bottleneck position in AI compute
+- [[compute supply chain concentration is simultaneously the strongest AI governance lever and the largest systemic fragility because the same chokepoints that enable oversight create single points of failure]] — packaging concentration is a key component of the governance/fragility paradox
+- [[physical infrastructure constraints on AI scaling create a natural governance window because packaging memory and power bottlenecks operate on 2-10 year timescales while capability research advances in months]] — packaging is the 2-3 year timescale constraint
+- [[the atoms-to-bits spectrum positions industries between defensible-but-linear and scalable-but-commoditizable with the sweet spot where physical data generation feeds software that scales independently]] — NVIDIA's packaging allocation is an atoms-layer moat feeding bits-layer dominance
+
+Topics:
+- [[manufacturing systems]]

domains/manufacturing/HBM memory supply concentration creates a three-vendor chokepoint where all production is sold out through 2026 gating every AI training system regardless of processor architecture.md

@@ -0,0 +1,38 @@
+---
+type: claim
+domain: manufacturing
+description: "SK Hynix, Samsung, and Micron produce all HBM globally with each GB requiring 3-4x the wafer capacity of DDR5 — structural supply tension worsens as AI chips demand more memory bandwidth per generation"
+confidence: likely
+source: "Astra, Theseus compute infrastructure research 2026-03-24; SK Hynix/Samsung/Micron CFO public confirmations"
+created: 2026-03-24
+secondary_domains: ["ai-alignment"]
+depends_on:
+  - "value in industry transitions accrues to bottleneck positions in the emerging architecture not to pioneers or to the largest incumbents"
+challenged_by:
+  - "HBM4 increases per-stack capacity which could ease the constraint if stacking efficiency improves faster than demand grows"
+  - "alternative memory architectures like CXL-attached memory may reduce HBM dependency for some workloads"
+---
+
+# HBM memory supply concentration creates a three-vendor chokepoint where all production is sold out through 2026 gating every AI training system regardless of processor architecture
+
+High Bandwidth Memory (HBM) is required for every modern AI accelerator — NVIDIA H100/H200/B200, AMD MI300X, Google TPU v5. Three companies produce all of it globally: SK Hynix (~50% market share), Samsung (~40%), and Micron (~10%). All three have confirmed their HBM supply is sold out through 2026.
+
+The structural tension is physical: each GB of HBM requires 3-4x the silicon wafer capacity of standard DDR5 because HBM stacks multiple DRAM dies vertically using through-silicon vias (TSVs) and micro-bumps. This means HBM production directly competes with commodity DRAM production for wafer capacity, creating a zero-sum allocation problem for memory fabs.
+
+Each new AI chip generation demands more HBM per accelerator: NVIDIA's B200 uses HBM3e stacks with higher bandwidth than H100's HBM3. The trend toward larger models and longer context windows increases memory requirements faster than stacking technology improves density. HBM4, expected 2025-2026, increases per-stack capacity but the demand growth curve remains steeper than supply expansion.
+
+This three-vendor chokepoint means that a production disruption at any single vendor reduces global HBM supply by 20-60% with no short-term alternative. Unlike logic chips where TSMC has theoretical competitors (Intel Foundry, Samsung Foundry), HBM production requires specialized stacking expertise that cannot be quickly replicated.
+
+## Challenges
+
+HBM4 significantly increases per-stack capacity, which could ease the constraint if stacking efficiency improvements outpace demand growth. CXL-attached memory (Compute Express Link) offers an alternative memory architecture for some inference workloads that reduces HBM dependency. Samsung and Micron are both expanding capacity aggressively. The constraint is most acute in 2024-2026; by 2027-2028 the supply-demand balance may improve — but this depends on whether frontier training compute demand continues doubling every 9-10 months.
+
+---
+
+Relevant Notes:
+- [[CoWoS advanced packaging is the binding bottleneck on AI compute scaling because TSMC near-monopoly on interposer technology gates total accelerator output regardless of chip design capability]] — HBM and CoWoS are independent but reinforcing bottlenecks
+- [[value in industry transitions accrues to bottleneck positions in the emerging architecture not to pioneers or to the largest incumbents]] — SK Hynix holds the strongest bottleneck position in memory
+- [[compute supply chain concentration is simultaneously the strongest AI governance lever and the largest systemic fragility because the same chokepoints that enable oversight create single points of failure]] — HBM is one of three chokepoints in the concentration/fragility paradox
+
+Topics:
+- [[manufacturing systems]]

domains/manufacturing/TSMC manufactures 92 percent of advanced logic chips making Taiwan the single largest physical vulnerability in global technology infrastructure.md

@@ -0,0 +1,38 @@
+---
+type: claim
+domain: manufacturing
+description: "Geographic diversification underway (Arizona 92% yield, Samsung, Intel Foundry) but most advanced processes remain Taiwan-first through 2027-2028 — a disruption would immediately halt AI accelerator and smartphone chip production globally"
+confidence: likely
+source: "Astra, Theseus compute infrastructure research 2026-03-24; Chris Miller 'Chip War', CSET Georgetown, TSMC market share data"
+created: 2026-03-24
+secondary_domains: ["ai-alignment"]
+depends_on:
+  - "optimization for efficiency without regard for resilience creates systemic fragility because interconnected systems transmit and amplify local failures into cascading breakdowns"
+challenged_by:
+  - "TSMC Arizona achieving 92% yield shows geographic diversification is technically feasible and progressing"
+  - "Intel Foundry and Samsung Foundry provide theoretical alternatives for some advanced processes"
+---
+
+# TSMC manufactures 92 percent of advanced logic chips making Taiwan the single largest physical vulnerability in global technology infrastructure
+
+TSMC fabricates approximately 92% of the world's most advanced logic chips (7nm and below). This includes virtually all AI accelerators (NVIDIA, AMD, Google TPUs), all Apple processors, and most leading-edge smartphone chips. No other concentration of critical manufacturing capability exists in any industry — not energy, not aerospace, not pharmaceuticals.
+
+Taiwan's geographic position creates compounding risk: military tension with China (Taiwan Strait), seismic vulnerability (Taiwan sits on the Pacific Ring of Fire), and energy dependence (Taiwan imports 98% of its energy). A military conflict, blockade, major earthquake, or prolonged power disruption would immediately halt production of the chips that run AI systems, smartphones, datacenters, and military systems globally.
+
+Geographic diversification is real but early. TSMC's Arizona fab has achieved 92% yield — approaching Taiwan levels — which demonstrates that knowledge transfer is feasible. But the most advanced processes (N2, N3P) remain Taiwan-first through at least 2027-2028. The Arizona fabs produce at mature nodes; the leading edge is still concentrated in Hsinchu.
+
+Intel Foundry and Samsung Foundry provide theoretical alternatives, but neither has demonstrated the yields, capacity, or customer trust to absorb TSMC's share. Intel's roadmap (18A, 14A) is promising but unproven at scale. Samsung's foundry business has persistently underperformed TSMC on yield. The competitive gap is narrowing but remains substantial.
+
+## Challenges
+
+TSMC Arizona's 92% yield achievement is the strongest counterargument — it proves that geographic diversification is technically achievable, not just aspirational. If CHIPS Act subsidies continue and yield parity is maintained, the US could have meaningful advanced chip production by 2028-2030. Japan (TSMC Kumamoto) and Germany (TSMC Dresden) provide additional diversification. The concentration is a snapshot in time, not a permanent condition — but the transition period (2024-2028) is the window of maximum vulnerability.
+
+---
+
+Relevant Notes:
+- [[optimization for efficiency without regard for resilience creates systemic fragility because interconnected systems transmit and amplify local failures into cascading breakdowns]] — the semiconductor supply chain is a textbook case of efficiency-optimized fragility
+- [[compute supply chain concentration is simultaneously the strongest AI governance lever and the largest systemic fragility because the same chokepoints that enable oversight create single points of failure]] — Taiwan concentration is the largest single component of compute supply fragility
+- [[semiconductor fab cost escalation means each new process node is a nation-state commitment because 20B-plus capital costs and multi-year construction create irreversible geographic path dependence]] — the economics that drove Taiwan concentration
+
+Topics:
+- [[manufacturing systems]]

domains/manufacturing/semiconductor fab cost escalation means each new process node is a nation-state commitment because 20B-plus capital costs and multi-year construction create irreversible geographic path dependence.md

@@ -0,0 +1,39 @@
+---
+type: claim
+domain: manufacturing
+description: "TSMC Arizona fab cost $40B+, Samsung Taylor $17B, Intel Ohio $20B — fab economics drive geographic concentration because only nation-state-level subsidies (CHIPS Act $52.7B) can justify the investment"
+confidence: likely
+source: "Astra, Theseus compute infrastructure research 2026-03-24; CHIPS Act public records, TSMC/Samsung/Intel fab announcements"
+created: 2026-03-24
+secondary_domains: ["ai-alignment"]
+depends_on:
+  - "the personbyte is a fundamental quantization limit on knowledge accumulation forcing all complex production into networked teams"
+  - "knowledge embodiment lag means technology is available decades before organizations learn to use it optimally creating a productivity paradox"
+challenged_by:
+  - "CHIPS Act and EU Chips Act subsidies may successfully diversify fab geography if sustained over multiple fab generations"
+  - "advanced packaging may become more geographically distributed than logic fabrication reducing the single-geography risk"
+---
+
+# Semiconductor fab cost escalation means each new process node is a nation-state commitment because 20B-plus capital costs and multi-year construction create irreversible geographic path dependence
+
+Leading-edge semiconductor fabs now cost $20B+ to build and take 3-5 years to construct. TSMC's Arizona complex is projected at $40B+ for two fabs. Samsung's Taylor, Texas fab costs $17B. Intel's Ohio fabs are projected at $20B. These are not business investments — they are nation-state-level commitments that only proceed with massive public subsidies (US CHIPS Act $52.7B, EU Chips Act €43B, Japan ¥3.9T).
+
+The cost escalation is structural: each new process node requires more complex lithography (EUV at $150M+ per tool, with only ASML as supplier), more processing steps, more precise materials, and more specialized workforce. The cost per transistor has stopped declining at the leading edge even as density continues improving — the economic scaling that drove Moore's Law is over, replaced by performance-per-watt scaling that costs more per fab generation.
+
+This creates irreversible geographic path dependence: once a nation commits $20-40B to a fab, the workforce training, supplier ecosystem, and infrastructure investment lock in that geography for decades. TSMC choosing Arizona, Samsung choosing Taylor, Intel choosing Ohio — these are 30-year bets that shape where advanced chips can be made for a generation.
+
+The personbyte constraint is directly relevant: a modern fab requires thousands of specialized workers operating in a knowledge network that takes years to develop. TSMC's Arizona fab initially struggled with yield because the knowledge network hadn't transferred — the tools were identical but the tacit knowledge wasn't. The 92% yield now achieved represents successful knowledge embodiment, not just equipment installation.
+
+## Challenges
+
+CHIPS Act subsidies are successfully pulling fab investment to the US — the question is whether this is a one-time relocation or a sustained diversification. If subsidies are not renewed for subsequent fab generations, investment may revert to existing clusters (Taiwan, South Korea) where the knowledge networks and supplier ecosystems are deepest. Advanced packaging may be more geographically distributable than logic fabrication, which could partially reduce single-geography risk even if fab concentration persists.
+
+---
+
+Relevant Notes:
+- [[the personbyte is a fundamental quantization limit on knowledge accumulation forcing all complex production into networked teams]] — fab operation requires deep knowledge networks that constrain geographic diversification
+- [[knowledge embodiment lag means technology is available decades before organizations learn to use it optimally creating a productivity paradox]] — TSMC Arizona yield gap illustrates knowledge embodiment in manufacturing
+- [[compute supply chain concentration is simultaneously the strongest AI governance lever and the largest systemic fragility because the same chokepoints that enable oversight create single points of failure]] — fab cost escalation drives the concentration this claim describes
+
+Topics:
+- [[manufacturing systems]]

domains/space-development/Axiom Space has the strongest operational position for commercial orbital habitation but the weakest financial position among funded competitors.md

@@ -0,0 +1,40 @@
+---
+type: claim
+domain: space-development
+description: "Four private astronaut missions plus sole-source NASA module contract and $3.5B spacesuit contract create unmatched operational advantages that a September 2024 cash crisis and down round nearly destroyed"
+confidence: likely
+source: "Astra, Axiom Space research profile February 2026"
+created: 2026-02-17
+depends_on:
+  - "commercial space stations are the next infrastructure bet as ISS retirement creates a void that 4 companies are racing to fill by 2030"
+  - "the commercial space station transition from ISS creates a gap risk that could end 25 years of continuous human presence in low Earth orbit"
+---
+
+# Axiom Space has the strongest operational position for commercial orbital habitation but the weakest financial position among funded competitors
+
+Axiom Space holds three structural advantages no competitor can replicate. First, it is the sole company with NASA's authorization to physically attach commercial modules to the ISS -- a firm-fixed-price contract worth up to $140 million awarded in January 2020 with no other recipients. Second, Axiom has completed four private astronaut missions to the ISS (Ax-1 through Ax-4, 2022-2025), making it the only company with operational experience sending commercial crews to orbit. Third, after Collins Aerospace withdrew from NASA's xEVAS spacesuit program, Axiom became the sole active provider of next-generation spacesuits for both ISS operations and Artemis moonwalks -- a contract worth up to $3.5 billion over ten years.
+
+These operational advantages nearly became irrelevant in September 2024, when Axiom hit a financial crisis severe enough to force layoffs of ~100 employees, voluntary 20% pay cuts for remaining staff, and reported difficulties meeting payroll. The subsequent March 2025 funding round was a down round -- $100 million at roughly $2 billion pre-money valuation, down from the $2.6 billion Series C valuation in August 2023. Three CEOs cycled through in 18 months.
+
+The December 2024 station redesign represents an attempt to thread the needle: launch the Payload, Power, and Thermal Module first (NET 2027), allowing the station to potentially separate from ISS as a free-flying platform as early as 2028. The pivot to sovereign and strategic capital -- Qatar Investment Authority, Hungary's 4iG ($100M for orbital data center initiatives) -- reflects a capital strategy where geopolitical alignment replaces pure financial return.
+
+The fundamental tension: Axiom's operational advantages are time-decaying assets. If ISS retires ~2030 and Axiom Station is not operational, the company loses both its development platform and mission revenue simultaneously.
+
+## Evidence
+- Sole-source NASA ISS module contract ($140M, January 2020)
+- 4 private astronaut missions (Ax-1 through Ax-4, 2022-2025)
+- Sole xEVAS spacesuit provider (up to $3.5B over 10 years)
+- September 2024 cash crisis, March 2025 down round at $2B vs $2.6B
+- 3 CEOs in 18 months
+
+## Challenges
+$1B+ raised to date is likely insufficient to complete station development. Financial constraints may force acquisition or failure, handing the market to better-capitalized competitors like Blue Origin's Orbital Reef or the Starlab consortium.
+
+---
+
+Relevant Notes:
+- [[commercial space stations are the next infrastructure bet as ISS retirement creates a void that 4 companies are racing to fill by 2030]] — Axiom is the operational leader but most financially precarious
+- [[the commercial space station transition from ISS creates a gap risk that could end 25 years of continuous human presence in low Earth orbit]] — Axiom's financial difficulties are the single largest risk factor for the gap scenario
+
+Topics:
+- [[space exploration and development]]

domains/space-development/SpaceX vertical integration across launch broadband and manufacturing creates compounding cost advantages that no competitor can replicate piecemeal.md

@@ -49,6 +49,12 @@ Orbital Reef's multi-party structure (Blue Origin, Sierra Space, Boeing) appears
 
 Starcloud's use of SpaceX rideshare to bootstrap orbital AI compute, combined with NVIDIA's strategic backing (GPU manufacturer + compute operator relationship), suggests a similar vertical-integration pattern emerging in the orbital data center sector. NVIDIA's Space Computing initiative and commitment to deploy Blackwell platforms by October 2026 creates a semiconductor-platform-vendor-to-orbital-operator relationship analogous to SpaceX's launch-to-Starlink integration. This may indicate that vertical integration advantages compound across different space industry segments, not just within SpaceX's specific stack.
 
+### Additional Evidence (extend)
+*Source: [[2026-03-27-blueorigin-new-glenn-manufacturing-odc-ambitions]] | Added: 2026-03-27*
+
+Blue Origin is attempting to replicate the SpaceX/Starlink vertical integration model with New Glenn + Project Sunrise (51,600 satellite ODC constellation). Manufacturing rate of 1 rocket/month with 12-24 launch target for 2026 shows serious infrastructure investment, but the gap between manufacturing capability and launch cadence (only 2 flights in 2025, NG-3 delayed as of March 2026) reveals that building the vertical integration infrastructure is insufficient—operational execution at scale is the binding constraint.
+
+
 
 Relevant Notes:
 - [[proxy inertia is the most reliable predictor of incumbent failure because current profitability rationally discourages pursuit of viable futures]] — legacy launch providers are profitable on government contracts, rationally preventing them from building competing flywheels

domains/space-development/Starcloud is the first company to operate a datacenter-grade GPU in orbit but faces an existential dependency on SpaceX for launches while SpaceX builds a competing million-satellite constellation.md

@@ -0,0 +1,55 @@
+---
+type: claim
+domain: space-development
+description: "YC S24 startup launched an H100 in orbit 21 months after founding and trained the first LLM in space but has raised only $34M against an 88,000-satellite vision while depending on SpaceX who filed for 1M competing satellites"
+confidence: experimental
+source: "Astra, web research compilation including CNBC, GeekWire, DCD, IEEE Spectrum, TechCrunch February 2026"
+created: 2026-02-17
+depends_on:
+  - "orbital data centers are the most speculative near-term space application but the convergence of AI compute demand and falling launch costs attracts serious players"
+  - "on-orbit processing of satellite data is the proven near-term use case for space compute because it avoids bandwidth and thermal bottlenecks simultaneously"
+  - "SpaceX vertical integration across launch broadband and manufacturing creates compounding cost advantages that no competitor can replicate piecemeal"
+---
+
+# Starcloud is the first company to operate a datacenter-grade GPU in orbit but faces an existential dependency on SpaceX for launches while SpaceX builds a competing million-satellite constellation
+
+## Company Overview
+
+Starcloud (formerly Lumen Orbit) was founded in January 2024, Y Combinator Summer 2024 batch. Rebranded from Lumen Orbit in February 2025. Team of approximately 5 people as of late 2025.
+
+**Key team:** Philip Johnston (CEO) — former McKinsey, Harvard/Wharton/Columbia. Ezra Feilden (CTO) — decade of satellite engineering, former Airbus, PhD in deployable structures. Adi Oltean (Chief Engineer) — former SpaceX Starlink network team, former Microsoft, 25+ patents. Bailey Montano (Lead Mechanical) — former SpaceX Raptor/Merlin, former Helion Energy.
+
+## Funding & Backers
+
+Total raised: approximately $27-34M across 8 rounds. Key investors: NFX, Y Combinator, In-Q-Tel (CIA-backed — signals national security interest), NVIDIA Inception Program, 468 Capital, scout funds from a16z and Sequoia.
+
+## What They Have Built
+
+**Starcloud-1** (launched November 2, 2025 on Falcon 9): ~60 kg satellite at 325 km carrying a single NVIDIA H100 — the first datacenter-grade GPU in space, 100x more powerful than any GPU previously operated in orbit. Demonstrated: trained NanoGPT on Shakespeare, ran Google Gemma, processed Capella Space SAR data as customer workload.
+
+**Starcloud-2** (planned October 2026): Multiple H100s plus NVIDIA Blackwell B200, ~100x the power generation of Starcloud-1, running Crusoe Cloud for public cloud workloads, reportedly first satellite with AWS Outposts hardware.
+
+**FCC filing** (February 2026): Up to 88,000 satellites for orbital AI compute.
+
+## The SpaceX Dependency
+
+The most interesting strategic risk. SpaceX controls Starcloud's access to orbit (launch pricing), its data routing infrastructure (Starlink), and is building a directly competing product (million-satellite compute constellation). This mirrors the classic platform-as-competitor dynamic from cloud computing — except the platform literally decides whether your satellites reach space.
+
+## Economics
+
+Starcloud projects a 40 MW orbital data center costing $8.2M over ten years versus $167M terrestrial. This comparison is accurate for power and cooling operational costs but deeply misleading as total cost: 25,000 Blackwell servers alone would cost ~$12-13B. The power savings represent 0.007% of total system cost. The real question is whether launch costs drop enough to make orbital deployment competitive on total cost.
+
+## Challenges
+
+The capital gap between $34M raised and 88,000 satellites is astronomical. Consumer GPUs are not designed for space radiation. Scaling from one 60 kg satellite to gigawatt-scale arrays is multiple orders of magnitude.
+
+---
+
+Relevant Notes:
+- [[orbital data centers are the most speculative near-term space application but the convergence of AI compute demand and falling launch costs attracts serious players]] — Starcloud is the company most concretely advancing this thesis
+- [[space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density]] — the physics constraint Starcloud must solve at scale
+- [[on-orbit processing of satellite data is the proven near-term use case for space compute because it avoids bandwidth and thermal bottlenecks simultaneously]] — Starcloud's Capella workload validates the near-term use case
+- [[SpaceX vertical integration across launch broadband and manufacturing creates compounding cost advantages that no competitor can replicate piecemeal]] — SpaceX controls launch, networking, and is building a competing product
+
+Topics:
+- [[space exploration and development]]

domains/space-development/Starship achieving routine operations at sub-100 dollars per kg is the single largest enabling condition for the entire space industrial economy.md

@@ -60,6 +60,12 @@ First V3 Starship static fire completed March 19, 2026 with 10 Raptor 3 engines
 
 Starship V3 (Booster 19 + Ship 39) completed first-ever Raptor 3 static fire on March 16, 2026 with 10 engines. SpaceX confirmed 'successful startup on all installed Raptor 3 engines.' Test ended early due to ground-side issue (GSE at Pad 2), not engine failure. 23 additional Raptor 3 engines await installation for 33-engine full static fire. V3 targets 100+ tonne payload class with full Raptor 3 upgrade. April mid-to-late 2026 launch target maintained but dependent on completing 33-engine qualification.
 
+### Additional Evidence (extend)
+*Source: [[2026-03-27-starship-falcon9-cost-2026-commercial-operations]] | Added: 2026-03-27*
+
+Current Starship cost of $1,600/kg is 16x above the sub-$100/kg threshold. Near-term projections of $250-600/kg are still 2.5-6x above threshold. Even with $10M/launch operating costs, commercial pricing will likely be $133/kg due to markup structure observed in Falcon 9 (4:1 internal cost to customer price).
+
+
 
 
 

domains/space-development/Starship economics depend on cadence and reuse rate not vehicle cost because a 90M vehicle flown 100 times beats a 50M expendable by 17x.md

@@ -35,6 +35,18 @@ V3's 100+ tonne payload capacity changes the denominator in the $/kg calculation
 
 V3 Starship with Raptor 3 engines represents the hardware generation designed for high-cadence reuse. First static fire March 19, 2026 establishes physical existence of V3 paradigm. Flight 12 in April 2026 will be first operational test of the cadence-enabling vehicle configuration.
 
+### Additional Evidence (extend)
+*Source: [[2026-03-27-blueorigin-new-glenn-manufacturing-odc-ambitions]] | Added: 2026-03-27*
+
+Blue Origin's New Glenn manufacturing rate (1/month, targeting 12-24 launches in 2026) with only 2 actual launches in 2025 demonstrates that cadence is the hard part. The company has solved the manufacturing problem (7 second stages visible on factory floor) but not the operational cadence problem (NG-3 still delayed). This confirms that vehicle production rate does not equal launch rate—operational throughput is the binding constraint on economics.
+
+### Additional Evidence (confirm)
+*Source: [[2026-03-27-starship-falcon9-cost-2026-commercial-operations]] | Added: 2026-03-27*
+
+Current $1,600/kg cost reflects operational reusability achieved in testing. Near-term projection to $250-600/kg depends on achieving full reuse and high cadence. Long-term $100-150/kg target requires operating costs of $10M/launch or less, which in turn requires both full reuse and high flight rate to amortize fixed costs.
+
+
+
 
 Relevant Notes:
 - [[reusability without rapid turnaround and minimal refurbishment does not reduce launch costs as the Space Shuttle proved over 30 years]] — Starship's design explicitly addresses every Shuttle failure mode

domains/space-development/Varda Space Industries validates commercial space manufacturing with four orbital missions 329M raised and monthly launch cadence by 2026.md

@@ -0,0 +1,44 @@
+---
+type: claim
+domain: space-development
+description: "First company to demonstrate repeatable orbital manufacturing-and-return at commercial cadence, with dual revenue from pharmaceutical IP and military reentry vehicle contracts"
+confidence: likely
+source: "Astra, microgravity manufacturing research February 2026"
+created: 2026-02-17
+depends_on:
+  - "space-based pharmaceutical manufacturing produces clinically superior drug formulations that cannot be replicated on Earth"
+  - "microgravity-discovered pharmaceutical polymorphs are a novel IP mechanism because new crystal forms enable patent extension reformulation and new delivery methods"
+  - "launch cost reduction is the keystone variable that unlocks every downstream space industry at specific price thresholds"
+---
+
+# Varda Space Industries validates commercial space manufacturing with four orbital missions 329M raised and monthly launch cadence by 2026
+
+Varda Space Industries is the first company to demonstrate that space manufacturing works as a repeatable commercial business, not a research exercise. They have completed four orbital missions as of mid-2025, manufacturing pharmaceutical crystals autonomously in proprietary capsules and returning them via hypersonic reentry. Their first mission (W-1) successfully produced Form III ritonavir -- a metastable polymorph difficult to create on Earth. Plans call for monthly launches by 2026.
+
+**Funding and valuation.** Varda has raised $329M total, including a $187M Series C at approximately $500M valuation in July 2025, backed by Founders Fund, Khosla Ventures, and Lux Capital. Their new 10,000 sq ft laboratory in El Segundo employs structural biologists and crystallization scientists recruited from top-20 pharmaceutical companies.
+
+**Dual revenue model.** Pharmaceutical crystallization services (discovering novel crystal polymorphs with high IP value) plus a $48M Air Force Research Laboratory contract for military reentry payloads. The hypersonic reentry vehicle platform serves both civilian and defense applications.
+
+**Why Varda matters.** They demonstrate that: (1) autonomous manufacturing in orbit works without crew, (2) hypersonic reentry and product return works, (3) mission cadence at commercial frequency is achievable, (4) the economics close -- pharmaceutical IP value per kg ($1M-$100M+) vastly exceeds launch and capsule costs, (5) dual-use revenue stabilizes the business.
+
+**The honest caveat.** Varda's business model depends on the assumption that some pharmaceutical polymorphs discovered in microgravity cannot eventually be replicated through advanced terrestrial techniques. Even if ground replication is eventually possible, first-mover advantage in discovering polymorphs generates IP regardless of where manufacturing ultimately occurs.
+
+## Evidence
+- 4 orbital missions completed as of mid-2025
+- $329M raised including $187M Series C at ~$500M valuation
+- Ritonavir Form III polymorph produced on W-1 mission
+- $48M AFRL contract for military reentry payloads
+- Monthly launch cadence planned for 2026
+
+## Challenges
+Scaling from 4 missions to monthly cadence requires sustained execution. If ground-based crystallization catches up, Varda becomes an expensive discovery tool rather than a manufacturing platform.
+
+---
+
+Relevant Notes:
+- [[space-based pharmaceutical manufacturing produces clinically superior drug formulations that cannot be replicated on Earth]] — Varda's business model rests on this claim
+- [[microgravity-discovered pharmaceutical polymorphs are a novel IP mechanism because new crystal forms enable patent extension reformulation and new delivery methods]] — the specific IP mechanism Varda commercializes
+- [[launch cost reduction is the keystone variable that unlocks every downstream space industry at specific price thresholds]] — Varda benefits from Falcon 9 economics and will benefit further from Starship
+
+Topics:
+- [[space exploration and development]]

domains/space-development/Vast is building the first commercial space station with Haven-1 launching 2027 funded by Jed McCaleb 1B personal commitment and targeting artificial gravity stations by the 2030s.md

@@ -30,6 +30,12 @@ Financial sustainability beyond McCaleb's personal commitment is the key risk. V
 
 ---
 
+### Additional Evidence (extend)
+*Source: [[2026-03-27-nasa-authorization-act-iss-overlap-mandate]] | Added: 2026-03-27*
+
+Haven-1's 2027 launch timeline positions it as the most plausible candidate to meet the ISS overlap mandate's requirements for a fully operational commercial station with 180 days of concurrent crew operations by 2031-2032. The overlap mandate creates a government-guaranteed anchor tenant relationship during the transition year, significantly de-risking Haven-1's business model.
+
+
 Relevant Notes:
 - [[commercial space stations are the next infrastructure bet as ISS retirement creates a void that 4 companies are racing to fill by 2030]] — competitive landscape for Haven-1 and Haven-2
 - the self-sustaining space operations threshold requires closing three interdependent loops simultaneously -- power water and manufacturing — Haven-2's closed-loop ECLSS addresses the water and air loops

domains/space-development/ZBLAN fiber optics produced in microgravity could eliminate submarine cable repeaters extending signal range from 50 km to potentially 5000 km.md

@@ -0,0 +1,38 @@
+---
+type: claim
+domain: space-development
+description: "Space-drawn ZBLAN offers 10x the capacity of silica fiber and could replace inline optical repeaters every 40-50 km in submarine cables with 400-5000 km spacing"
+confidence: likely
+source: "Astra, web research compilation February 2026"
+created: 2026-02-17
+depends_on:
+  - "microgravity eliminates convection sedimentation and container effects producing measurably superior materials across fiber optics pharmaceuticals and semiconductors"
+  - "the space manufacturing killer app sequence is pharmaceuticals now ZBLAN fiber in 3-5 years and bioprinted organs in 15-25 years each catalyzing the next tier of orbital infrastructure"
+---
+
+# ZBLAN fiber optics produced in microgravity could eliminate submarine cable repeaters extending signal range from 50 km to potentially 5000 km
+
+ZBLAN (zirconium barium lanthanum aluminium sodium fluoride) is an optical fiber with extraordinary transparency across a broader wavelength range than silica, especially in the mid-infrared (2-4 micron wavelengths). On Earth, gravity-driven convection during cooling creates microcrystalline defects that degrade performance. In microgravity, these defects are suppressed or eliminated.
+
+**The attenuation numbers.** ZBLAN has a theoretical minimum attenuation of 0.001 dB/km at 2 microns wavelength, compared to silica's best of 0.2 dB/km. Terrestrial ZBLAN achieves only 0.7 dB/km due to gravity-induced defects. If space-made ZBLAN approaches its theoretical limit, a 2,000 km length could match the optical loss of just 10 km of silica fiber. Current submarine cables require inline optical repeaters every 40-50 km. ZBLAN could extend that to 400-5,000 km, fundamentally restructuring the economics of global telecommunications.
+
+**Production breakthrough.** Flawless Photonics produced nearly 12 km of ZBLAN on the ISS in February-March 2024 -- a 600x improvement over previous efforts that managed only ~20 meters per attempt. They completed eight separate draws each exceeding 700 meters (standard commercial spool length). Selected for ESA's Advanced Materials and In-orbit Manufacturing Industry Accelerator in January 2026.
+
+**Market economics.** Terrestrial ZBLAN fiber sells for $150-$3,000 per meter depending on quality, with premium grades at ~$1,000/meter. Space-made ZBLAN is projected at $600K-$3M per kilogram. Total addressable market estimated at EUR 260-350 million annually (10-13% of specialty fiber market). Revenue per kg vastly exceeds launch costs.
+
+## Evidence
+- Theoretical attenuation: 0.001 dB/km (ZBLAN) vs 0.2 dB/km (silica) — 200x theoretical advantage
+- Flawless Photonics — 12 km on ISS, 600x improvement over prior efforts
+- Submarine cable repeater economics — 40-50 km spacing vs potential 400-5,000 km
+
+## Challenges
+Optical quality advantage of space-produced ZBLAN has not been publicly quantified with hard attenuation numbers as of early 2026. If improvement is only 2-3x rather than 10-100x, the commercial case weakens significantly. Autonomous process control at required precision remains an engineering challenge.
+
+---
+
+Relevant Notes:
+- [[microgravity eliminates convection sedimentation and container effects producing measurably superior materials across fiber optics pharmaceuticals and semiconductors]] — ZBLAN is the highest-value near-term example of this physics advantage
+- [[the space manufacturing killer app sequence is pharmaceuticals now ZBLAN fiber in 3-5 years and bioprinted organs in 15-25 years each catalyzing the next tier of orbital infrastructure]] — ZBLAN is Tier 2, first physical product driving permanent orbital platforms
+
+Topics:
+- [[space exploration and development]]

domains/space-development/commercial space stations are the next infrastructure bet as ISS retirement creates a void that 4 companies are racing to fill by 2030.md

@@ -61,6 +61,12 @@ NASA's January 28, 2026 Phase 2 CLD freeze placed the entire commercial station
 
 NASA Phase 2 CLD program frozen January 28, 2026 with no replacement timeline, converting $1-1.5B anticipated funding into indefinite risk. Requirements previously softened from 'permanently crewed' to 'crew-tended' in July 2025, suggesting original operational bar was unachievable. Phil McAlister characterized freeze as 'schedule risk' not 'safety risk,' implying programs can wait but cannot proceed without NASA anchor funding.
 
+### Additional Evidence (extend)
+*Source: [[2026-03-27-nasa-authorization-act-iss-overlap-mandate]] | Added: 2026-03-27*
+
+The NASA Authorization Act of 2026 overlap mandate creates a policy-engineered Gate 2 by requiring ISS to operate alongside a fully operational commercial station for one year with 180 days of concurrent crew operations. This transforms the 'void' from a market opportunity into a mandated transition condition with specific technical requirements and government anchor tenant guarantees.
+
+
 
 
 

domains/space-development/distributed LEO inference networks could serve global AI requests at 4-20ms latency competitive with centralized terrestrial data centers for latency-tolerant workloads.md

@@ -0,0 +1,41 @@
+---
+type: claim
+domain: space-development
+description: "LEO at 500-2000 km gives 4-20ms round-trip latency — acceptable for many AI inference applications and potentially lower than routing to a distant terrestrial hyperscaler"
+confidence: experimental
+source: "Astra, space data centers feasibility analysis February 2026; SpaceX FCC filing January 2026"
+created: 2026-02-17
+secondary_domains:
+  - critical-systems
+depends_on:
+  - "Starship achieving routine operations at sub-100 dollars per kg is the single largest enabling condition for the entire space industrial economy"
+  - "LEO satellite internet is the defining battleground of the space economy with Starlink 5 years ahead and only 3-4 mega-constellations viable"
+---
+
+# Distributed LEO inference networks could serve global AI requests at 4-20ms latency competitive with centralized terrestrial data centers for latency-tolerant workloads
+
+Low Earth orbit at 500 to 2,000 km altitude produces approximately 4 to 20 milliseconds of round-trip latency to ground stations. This is not competitive with sub-millisecond latency available within a terrestrial data center, but it is acceptable for many AI inference use cases -- including content recommendation, search ranking, translation, summarization, and conversational AI. For users geographically distant from hyperscale data centers, orbital inference could actually deliver lower latency than routing through multiple terrestrial network hops to a distant facility.
+
+Inference workloads are architecturally suited to distributed orbital deployment. Unlike training, which requires constant high-bandwidth all-to-all communication between thousands of GPUs for gradient synchronization, inference runs are relatively independent -- each request can be served by a single node or small cluster without tight coordination with other nodes. Bandwidth demands per node are manageable (the model is loaded once; each request involves kilobytes to megabytes of input/output, not the terabytes of parameter gradients that training demands).
+
+SpaceX's January 2026 FCC filing for up to one million satellites at 500-2,000 km altitudes specifically targets this architecture -- distributed processing nodes harnessing near-constant solar power, leveraging Starlink's existing laser-mesh inter-satellite network for routing. The potential SpaceX-xAI merger would vertically integrate this network infrastructure with Grok inference demand. Google's Project Suncatcher envisions 81-satellite clusters in 1 km formations, also targeting inference and Earth observation processing.
+
+The critical dependencies are launch cost (Google pins cost-competitiveness at $200/kg, projected around 2035), thermal management (each node must dissipate its compute heat radiatively), and bandwidth (sufficient to deliver inference results but not for the massive data transfers training requires).
+
+## Evidence
+- SpaceX FCC filing (January 2026) for up to 1 million satellites optimized for AI inference
+- Google Project Suncatcher — 81-satellite clusters targeting inference workloads
+- LEO orbital mechanics — 4-20ms round-trip latency at 500-2,000 km altitude
+
+## Challenges
+Terrestrial edge computing and CDN expansion may close the latency gap for most users before orbital inference becomes cost-competitive. The 2035 timeline assumes Starship cost curves materialize.
+
+---
+
+Relevant Notes:
+- [[orbital AI training is fundamentally incompatible with space communication links because distributed training requires hundreds of Tbps aggregate bandwidth while orbital links top out at single-digit Tbps]] — inference works because it does not require all-to-all bandwidth
+- [[space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density]] — thermal management remains the binding constraint even for distributed inference
+- [[SpaceX vertical integration across launch broadband and manufacturing creates compounding cost advantages that no competitor can replicate piecemeal]] — SpaceX uniquely controls both launch and the networking infrastructure
+
+Topics:
+- [[space exploration and development]]

domains/space-development/governments are transitioning from space system builders to space service buyers which structurally advantages nimble commercial providers.md

@@ -58,6 +58,12 @@ NASA's Phase 2 CLD freeze demonstrates that the transition to service-buyer crea
 
 NASA's Phase 2 CLD requirement downgrade from 'permanently crewed' to 'crew-tended' (July 2025) shows the customer adjusting specifications to match supplier capability rather than suppliers meeting customer requirements. The January 2026 freeze demonstrates that commercial providers remain dependent on government anchor demand rather than operating as independent service providers with diversified customer bases.
 
+### Additional Evidence (confirm)
+*Source: [[2026-03-27-nasa-authorization-act-iss-overlap-mandate]] | Added: 2026-03-27*
+
+The ISS overlap mandate explicitly directs NASA to accelerate commercial LEO destinations development and creates a mandatory one-year anchor tenant relationship during the overlap period. This is the strongest policy mechanism yet for the builder-to-buyer transition, going beyond procurement preferences to mandating operational overlap before government infrastructure can be retired.
+
+
 
 
 

domains/space-development/in-space manufacturing market projected at 62 billion by 2040 with the overall space economy reaching 1-2 trillion.md

@@ -0,0 +1,40 @@
+---
+type: claim
+domain: space-development
+description: "MarketsandMarkets projects $62.8B for in-space manufacturing by 2040; Allied Market Research projects $135.3B including servicing; total space economy $1-2T by 2040"
+confidence: experimental
+source: "Astra, web research compilation February 2026"
+created: 2026-02-17
+secondary_domains:
+  - manufacturing
+depends_on:
+  - "the space economy reached 613 billion in 2024 and is converging on 1 trillion by 2032 making it a major global industry not a speculative frontier"
+  - "Starship achieving routine operations at sub-100 dollars per kg is the single largest enabling condition for the entire space industrial economy"
+---
+
+# In-space manufacturing market projected at 62 billion by 2040 with the overall space economy reaching 1-2 trillion
+
+Multiple market research firms project rapid growth in the space economy over the next 15 years. MarketsandMarkets projects the in-space manufacturing market at $62.8 billion by 2040. Allied Market Research projects $135.3 billion when including servicing and transportation. The overall space economy is projected at $1-2 trillion by 2040, up from roughly $500 billion today. Space-based solar power alone is projected to grow from $630 million (2025) to $4.61 billion by 2041 at 13.24% CAGR.
+
+These projections depend on a cascade of technology milestones landing roughly on schedule: Starship achieving routine operations and sub-$100/kg launch costs, propellant depot infrastructure becoming operational, pharmaceutical and semiconductor manufacturing reaching commercial cadence, lunar surface power and ISRU demonstrations succeeding, and at least one commercial space station becoming fully operational. Each dependency creates compound uncertainty -- the probability of the full projection is the product of individual milestone probabilities.
+
+The space mining market specifically is estimated at $50 million (2025) growing to $800 million by 2035 -- still small relative to manufacturing and services. The signal in these projections is not the specific numbers (which carry high uncertainty) but the convergence of independent analyses on the same order of magnitude. Multiple research firms, government projections, and industry analyses all point to a space economy 2-4x its current size by 2040, with manufacturing as the highest-growth segment.
+
+## Evidence
+- MarketsandMarkets — $62.8B in-space manufacturing by 2040
+- Allied Market Research — $135.3B including servicing and transport
+- Space-based solar power — $630M (2025) to $4.61B (2041)
+- Space mining — $50M (2025) to $800M (2035)
+- Convergence of independent analyses on $1-2T total space economy
+
+## Challenges
+All projections depend on cascading technology milestones. The compound probability of the full projection is substantially lower than any individual milestone probability. Market sizing methodologies for emerging space industries carry inherent uncertainty.
+
+---
+
+Relevant Notes:
+- [[the space economy reached 613 billion in 2024 and is converging on 1 trillion by 2032 making it a major global industry not a speculative frontier]] — the current baseline these projections build from
+- [[Starship achieving routine operations at sub-100 dollars per kg is the single largest enabling condition for the entire space industrial economy]] — the keystone variable most projections depend on
+
+Topics:
+- [[space exploration and development]]

domains/space-development/launch cost reduction is the keystone variable that unlocks every downstream space industry at specific price thresholds.md

@@ -30,6 +30,12 @@ The keystone variable framing implies a single bottleneck, but space development
 
 Haven-1's delay provides a boundary condition: once launch cost crosses below a threshold (~$67M for Falcon 9), the binding constraint shifts to technology development pace (life support integration, avionics, thermal control). For commercial stations in 2026, launch cost is no longer the keystone variable — it has been solved. The new keystone is knowledge embodiment in complex habitation systems.
 
+### Additional Evidence (confirm)
+*Source: [[2026-03-27-starship-falcon9-cost-2026-commercial-operations]] | Added: 2026-03-27*
+
+As of March 2026, Starship operational cost is $1,600/kg, creating an 8x gap to the $200/kg ODC threshold. No commercial ODC operations have materialized despite technical readiness, consistent with the thesis that specific cost thresholds gate sector emergence.
+
+
 
 Relevant Notes:
 - [[attractor states provide gravitational reference points for capital allocation during structural industry change]] — launch cost thresholds are specific attractor states that pull industry structure toward new configurations

domains/space-development/microgravity eliminates convection sedimentation and container effects producing measurably superior materials across fiber optics pharmaceuticals and semiconductors.md

@@ -0,0 +1,36 @@
+---
+type: claim
+domain: space-development
+description: "Three terrestrial forces — convection, sedimentation, container effects — limit material quality on Earth; removing them in orbit yields 10x fiber capacity, uniform drug crystals, and superior semiconductors"
+confidence: likely
+source: "Astra, web research compilation February 2026"
+created: 2026-02-17
+depends_on:
+  - "the space manufacturing killer app sequence is pharmaceuticals now ZBLAN fiber in 3-5 years and bioprinted organs in 15-25 years each catalyzing the next tier of orbital infrastructure"
+---
+
+# Microgravity eliminates convection sedimentation and container effects producing measurably superior materials across fiber optics pharmaceuticals and semiconductors
+
+Microgravity does not merely improve manufacturing processes -- it removes three fundamental physical forces that constrain material quality on Earth. Convection (fluid movement driven by temperature gradients), sedimentation (gravity-driven settling of particles), and container effects (interaction between materials and vessel walls) are all absent in freefall. The result is not incremental improvement but categorical superiority for materials whose quality depends on crystal uniformity, molecular alignment, or phase purity.
+
+The evidence spans multiple material categories. ZBLAN optical fiber drawn in microgravity avoids the crystallization that makes terrestrial ZBLAN brittle and lossy -- Flawless Photonics produced nearly 12 km of ZBLAN on the ISS in two weeks with repeatable quality across eight individual runs each exceeding 700 meters. Merck's Keytruda crystals grown on the ISS were smaller and more uniform with lower viscosity and better injectability. Varda Space Industries successfully grew ritonavir crystals in orbit, completing three launch-and-return missions by 2025. Space Forge generated plasma at 1,000 degrees Celsius in orbit for semiconductor crystal growth -- the first free-flying commercial semiconductor manufacturing tool operated in space.
+
+The pattern across all these materials is the same: microgravity allows crystals to grow more slowly and uniformly, producing structures that are physically impossible to achieve under Earth gravity. This is not a marginal improvement amenable to terrestrial workarounds. It is a physics-level advantage that creates product categories rather than merely enhancing existing ones.
+
+## Evidence
+- Flawless Photonics — 12 km ZBLAN on ISS, 8 runs exceeding 700m each
+- Merck Keytruda — uniform 39 micron crystals enabling subcutaneous reformulation
+- Varda — ritonavir Form III polymorph production in orbit
+- Space Forge — first free-flying commercial semiconductor tool in orbit
+
+## Challenges
+Advanced terrestrial techniques (acoustic levitation, electromagnetic containerless processing, rapid cooling) continue to narrow the gap for Tier 3 products. The permanent advantage applies primarily to Tier 1 and 2 products.
+
+---
+
+Relevant Notes:
+- [[the space manufacturing killer app sequence is pharmaceuticals now ZBLAN fiber in 3-5 years and bioprinted organs in 15-25 years each catalyzing the next tier of orbital infrastructure]] — the three products that exploit these physics advantages most commercially
+- [[the impossible on Earth test separates three tiers of microgravity advantage -- truly impossible products dramatically better products and products where terrestrial workarounds exist]] — classifies the advantage into three tiers
+
+Topics:
+- [[space exploration and development]]

domains/space-development/microgravity-discovered pharmaceutical polymorphs are a novel IP mechanism because new crystal forms enable patent extension reformulation and new delivery methods.md

@@ -0,0 +1,40 @@
+---
+type: claim
+domain: space-development
+description: "Different crystal structures of the same drug molecule have different solubility and bioavailability — microgravity accesses metastable forms that convection-driven nucleation excludes on Earth"
+confidence: likely
+source: "Astra, microgravity manufacturing research February 2026"
+created: 2026-02-17
+secondary_domains:
+  - health
+depends_on:
+  - "microgravity eliminates convection sedimentation and container effects producing measurably superior materials across fiber optics pharmaceuticals and semiconductors"
+  - "space-based pharmaceutical manufacturing produces clinically superior drug formulations that cannot be replicated on Earth"
+---
+
+# Microgravity-discovered pharmaceutical polymorphs are a novel IP mechanism because new crystal forms enable patent extension reformulation and new delivery methods
+
+Different crystal forms (polymorphs) of the same drug molecule can have dramatically different therapeutic properties -- solubility, bioavailability, stability, viscosity. Microgravity enables access to metastable polymorphs by eliminating convection-driven nucleation patterns that bias crystallization on Earth toward thermodynamically stable (but therapeutically suboptimal) forms. If a novel polymorph enables subcutaneous delivery of an IV drug, or improves oral bioavailability, the formulation itself is patentable -- and the IP value can be enormous.
+
+**The Keytruda proof point.** Merck crystallized pembrolizumab (Keytruda, the world's best-selling cancer drug at ~$25B/year revenue) in microgravity on the ISS. The resulting crystals had a homogeneous monomodal particle size distribution of 39 microns and significantly lower viscosity than ground controls. This enabled reformulation from IV infusion to subcutaneous injection. The FDA approved the subcutaneous formulation in late 2025 for early-stage cancers — the first commercially significant pharmaceutical product directly enabled by microgravity research.
+
+**The Varda ritonavir demonstration.** Varda's first mission (W-1) successfully produced Form III ritonavir -- a metastable polymorph difficult to create on Earth. Ritonavir is infamous in pharmaceutical history: in 1998, Abbott's ritonavir spontaneously converted from the more soluble Form I to the less bioavailable Form II, causing a manufacturing crisis.
+
+**The IP mechanism.** A novel crystal form discovered in microgravity can be patented as a new formulation, effectively extending the commercial life of existing blockbuster drugs. McKinsey estimated that a single novel oncology drug developed through space-based R&D could generate an average NPV of $1.2B, with aggregate pharmaceutical revenues from space projected at $2.8-$4.2B.
+
+## Evidence
+- Merck Keytruda subcutaneous reformulation — FDA approved late 2025
+- Varda W-1 mission — ritonavir Form III polymorph production
+- McKinsey analysis — $1.2B NPV per novel oncology drug, $2.8-4.2B aggregate
+
+## Challenges
+The critical uncertainty is whether microgravity-discovered polymorphs can eventually be replicated on Earth through advanced terrestrial techniques (high-pressure crystallization, templated nucleation, acoustic levitation). Even if replication is possible, first-mover advantage in discovery generates IP regardless.
+
+---
+
+Relevant Notes:
+- [[space-based pharmaceutical manufacturing produces clinically superior drug formulations that cannot be replicated on Earth]] — the broader manufacturing claim this mechanism underlies
+- [[microgravity eliminates convection sedimentation and container effects producing measurably superior materials across fiber optics pharmaceuticals and semiconductors]] — the physics mechanism enabling polymorph access
+
+Topics:
+- [[space exploration and development]]

domains/space-development/modern AI accelerators are more radiation-tolerant than expected because Google TPU testing showed no hard failures up to 15 krad suggesting consumer chips may survive LEO environments.md

@@ -0,0 +1,37 @@
+---
+type: claim
+domain: space-development
+description: "Google tested Trillium v6e TPUs in a 67 MeV proton beam with no hard failures up to 15 krad total ionizing dose — challenging the assumption that AI compute requires expensive radiation-hardened hardware"
+confidence: experimental
+source: "Astra, Google Project Suncatcher feasibility study late 2025"
+created: 2026-02-17
+depends_on:
+  - "space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density"
+---
+
+# Modern AI accelerators are more radiation-tolerant than expected because Google TPU testing showed no hard failures up to 15 krad suggesting consumer chips may survive LEO environments
+
+Google's Project Suncatcher feasibility study included proton beam testing of their Trillium (v6e) TPU accelerators at 67 MeV. The result was surprising: no hard failures up to 15 krad(Si) total ionizing dose. This is a genuinely important data point because the conventional assumption in space systems engineering is that commercial-grade semiconductors require expensive radiation hardening (or radiation-hardened by design alternatives that are generations behind in performance) to survive in orbit.
+
+Space radiation damages electronics through three mechanisms. Single Event Upsets (SEUs) are bit flips from high-energy particle strikes -- correctable with error-correcting code memory but they increase compute overhead. Total Ionizing Dose (TID) is cumulative degradation that shifts threshold voltages and increases leakage current over the satellite's operational lifetime. Single Event Latchup can cause destructive overcurrent conditions requiring power cycling or permanently damaging circuits.
+
+The Google result addresses TID specifically and suggests that modern process nodes (5nm and below) may be inherently more radiation-tolerant than older process generations. If confirmed across other chip architectures, this significantly de-risks the hardware side of orbital compute. It does not eliminate the SEU problem -- bit flips will still occur at elevated rates compared to terrestrial operation -- but ECC memory and algorithmic redundancy can manage this for inference workloads where occasional soft errors are tolerable.
+
+Critical caveats: Starcloud operating an H100 in orbit for a demonstration is fundamentally different from operating thousands of H100s reliably for years. Long-duration LEO operation accumulates dose over years, and the South Atlantic Anomaly creates radiation hotspots that elevate local dose rates. Still, the Google result shifts the prior: radiation hardening may be less of a showstopper than thermal management for orbital compute viability.
+
+## Evidence
+- Google Trillium v6e TPU proton beam testing — no hard failures to 15 krad(Si)
+- Modern 5nm process node characteristics suggesting inherent radiation tolerance
+- Starcloud H100 orbital demonstration (single GPU, short duration)
+
+## Challenges
+Long-duration operation over years with cumulative dose, SAA transits, and solar particle events remains uncharacterized for commercial AI hardware. The TPU result may not generalize to GPU architectures.
+
+---
+
+Relevant Notes:
+- [[space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density]] — if radiation is less of a problem than expected, thermal management becomes even more clearly the binding constraint
+- [[orbital data centers require five enabling technologies to mature simultaneously and none currently exist at required readiness]] — radiation tolerance is one of the five enabling conditions
+
+Topics:
+- [[space exploration and development]]

domains/space-development/nuclear fission is the only viable continuous power source for lunar surface operations because solar fails during 14-day lunar nights.md

@@ -0,0 +1,37 @@
+---
+type: claim
+domain: space-development
+description: "Lunar south pole operations require power during 14-day nights ruling out solar-only; NASA-DOE targeting 40 kWe fission reactor delivery to launch pad early 2030s with Westinghouse as prime"
+confidence: likely
+source: "Astra, web research compilation February 2026"
+created: 2026-02-17
+secondary_domains:
+  - energy
+depends_on:
+  - "power is the binding constraint on all space operations because every capability from ISRU to manufacturing to life support is power-limited"
+---
+
+# Nuclear fission is the only viable continuous power source for lunar surface operations because solar fails during 14-day lunar nights
+
+The lunar south pole -- where water ice deposits exist in permanently shadowed craters -- experiences 14-day periods of darkness. Solar power alone cannot sustain continuous operations through these nights, making nuclear fission a structural necessity rather than a preference. NASA and DOE are developing a Fission Surface Power system targeting 40 kWe (enough to continuously power 30 households for 10 years) in a package under 6 metric tons.
+
+The technology heritage is strong. The KRUSTY experiment (Kilopower Reactor Using Stirling Technology) demonstrated successful operation under normal and off-normal conditions in 2018. Westinghouse was selected in January 2025 to continue space microreactor development. L3Harris is developing nuclear power and propulsion solutions for the Artemis program. The delivery target is a reactor at the launch pad in early 2030s, with a 1-year demonstration followed by 9 operational years on the Moon.
+
+Next-generation RTGs for deep-space missions are also advancing: the NGRTG targets 242 We (more than double the current 110 We MMRTG), with a flight-ready manufacturing line by 2030. Trump's executive order on space superiority made lunar nuclear reactors and orbital nuclear power a priority. The trajectory is clear: nuclear power in space is moving from heritage deep-space missions to surface infrastructure.
+
+## Evidence
+- KRUSTY reactor demonstration (2018) — successful operation under all conditions
+- Westinghouse selected January 2025 for space microreactor development
+- NASA-DOE Fission Surface Power: 40 kWe target, <6 metric tons, early 2030s
+- NGRTG: 242 We target, flight-ready manufacturing line by 2030
+
+## Challenges
+Regulatory and political challenges around launching nuclear material remain significant. Plutonium-238 supply constraints may limit RTG production. Fission reactor technology is mature but space-qualified systems require extensive testing.
+
+---
+
+Relevant Notes:
+- [[power is the binding constraint on all space operations because every capability from ISRU to manufacturing to life support is power-limited]] — nuclear fission is the primary answer to the binding power constraint for lunar operations
+
+Topics:
+- [[space exploration and development]]

domains/space-development/nuclear thermal propulsion cuts Mars transit time by 25 percent and is the most promising near-term technology for human deep-space missions.md

@@ -0,0 +1,36 @@
+---
+type: claim
+domain: space-development
+description: "DARPA/NASA DRACO program ($499M) has successfully tested reactor fuel with in-orbit engine activation planned for 2026-2027, offering ~900s specific impulse vs 450s chemical"
+confidence: likely
+source: "Astra, web research compilation February 2026"
+created: 2026-02-17
+depends_on:
+  - "launch cost reduction is the keystone variable that unlocks every downstream space industry at specific price thresholds"
+---
+
+# Nuclear thermal propulsion cuts Mars transit time by 25 percent and is the most promising near-term technology for human deep-space missions
+
+Nuclear thermal propulsion (NTP) achieves approximately 900 seconds of specific impulse -- roughly double chemical propulsion's 300-450 seconds -- while maintaining comparable thrust levels. This combination of efficiency and thrust is unique among propulsion technologies: ion thrusters achieve 3,000-5,000 seconds specific impulse but produce only millinewtons of thrust (ideal for cargo, not humans). NTP cuts Mars transit time by approximately 25%, which is not just a convenience but a significant reduction in mission risk -- less radiation exposure, fewer consumables, shorter vulnerability windows.
+
+The DARPA/NASA joint DRACO program ($499 million) is advancing NTP toward flight testing. General Atomics successfully tested reactor fuel at Marshall Space Flight Center in January 2025. In-orbit engine activation is planned for early 2026, though the schedule may slip to 2027. Two contractors (Ultra Safe Nuclear and General Atomics) are advancing development. This represents the most concrete progress toward nuclear propulsion since the NERVA program was cancelled in 1972.
+
+NTP is a technology dependency in the chain leading to sustained human presence beyond LEO. Chemical propulsion can reach Mars but imposes transit times that create unacceptable risk profiles for crewed missions. Ion propulsion can move cargo efficiently but too slowly for humans. NTP occupies the sweet spot: fast enough for human transit, efficient enough to be practical.
+
+## Evidence
+- DRACO program: $499M, General Atomics reactor fuel testing (January 2025)
+- NTP specific impulse: ~900s vs 300-450s chemical, vs 3,000-5,000s ion
+- Mars transit reduction: ~25% (from 7-9 months to 5-7 months)
+- NERVA heritage program (cancelled 1972) demonstrated feasibility
+
+## Challenges
+DRACO was partially cancelled in 2025 though congressional funding continues at $110M+. Political and regulatory barriers to launching nuclear material remain significant. No flight demonstration has occurred since the 1960s NERVA tests.
+
+---
+
+Relevant Notes:
+- [[launch cost reduction is the keystone variable that unlocks every downstream space industry at specific price thresholds]] — getting to orbit is half the problem; NTP addresses moving between destinations efficiently
+- [[the Moon serves as a proving ground for Mars settlement because 2-day transit enables 180x faster iteration cycles than the 6-month Mars journey]] — NTP would compress Mars iteration cycles
+
+Topics:
+- [[space exploration and development]]

domains/space-development/on-orbit processing of satellite data is the proven near-term use case for space compute because it avoids bandwidth and thermal bottlenecks simultaneously.md

@@ -0,0 +1,39 @@
+---
+type: claim
+domain: space-development
+description: "Earth observation satellites generate 10 GB per second of raw data and processing in orbit transmits only results — Planet Labs and Google Suncatcher target this workload first"
+confidence: likely
+source: "Astra, space data centers feasibility analysis February 2026; Google Project Suncatcher partnership with Planet Labs"
+created: 2026-02-17
+depends_on:
+  - "space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density"
+  - "the space manufacturing killer app sequence is pharmaceuticals now ZBLAN fiber in 3-5 years and bioprinted organs in 15-25 years each catalyzing the next tier of orbital infrastructure"
+---
+
+# On-orbit processing of satellite data is the proven near-term use case for space compute because it avoids bandwidth and thermal bottlenecks simultaneously
+
+The cleanest near-term use case for orbital compute is processing satellite-generated data where it is collected rather than downlinking raw data to terrestrial facilities. Earth observation satellites generate approximately 10 GB/s of synthetic aperture radar data. Transmitting this raw data to ground stations faces severe bandwidth constraints -- satellite-to-ground links are limited, ground station pass windows are brief, and the data volume is enormous. Processing in orbit and transmitting only the results (classifications, detected changes, compressed features) dramatically reduces both the bandwidth requirement and the end-to-end latency from observation to actionable intelligence.
+
+This use case sidesteps every major objection to orbital compute. The thermal problem dissolves because on-orbit processing loads are measured in kilowatts, not megawatts -- a single compute node per satellite or small cluster, well within the thermal management capabilities of current satellite bus designs. The bandwidth problem inverts from constraint to advantage -- instead of needing to move data up to orbit for processing, the data is already there. The latency problem disappears because the alternative (downlink, terrestrial process, uplink results) takes hours, making even modest orbital processing a dramatic improvement.
+
+Planet Labs' partnership with Google for Project Suncatcher explicitly targets this workload first. Axiom Space's orbital data center concept similarly focuses on satellite-proximate processing. This is also the workload that SpaceX's FCC filing implicitly supports through Starlink's optical inter-satellite link mesh.
+
+The strategic importance of this use case goes beyond its direct market size. It establishes orbital compute as a real business with real revenue, validates hardware in the orbital environment, and builds operational experience that de-risks the harder use cases that follow.
+
+## Evidence
+- Earth observation satellites generating ~10 GB/s of SAR data
+- Planet Labs + Google Project Suncatcher partnership targeting on-orbit processing
+- Axiom Space orbital data center concept focused on satellite-proximate processing
+- Starcloud Capella Space customer workload demonstrating viable business model
+
+## Challenges
+Improved ground station networks and higher-bandwidth satellite-to-ground links may reduce the advantage of on-orbit processing by making raw data downlink more feasible.
+
+---
+
+Relevant Notes:
+- [[space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density]] — on-orbit processing sidesteps this because compute loads per satellite are kilowatts not megawatts
+- [[LEO satellite internet is the defining battleground of the space economy with Starlink 5 years ahead and only 3-4 mega-constellations viable]] — Starlink's optical mesh provides the inter-satellite networking for distributed on-orbit processing
+
+Topics:
+- [[space exploration and development]]

domains/space-development/orbital AI training is fundamentally incompatible with space communication links because distributed training requires hundreds of Tbps aggregate bandwidth while orbital links top out at single-digit Tbps.md

@@ -0,0 +1,41 @@
+---
+type: claim
+domain: space-development
+description: "A large training run on tens of thousands of GPUs needs constant all-to-all gradient exchange at hundreds of Tbps — current satellite links deliver 200 Gbps per node with next-gen targeting 1 Tbps making orbital training likely never viable"
+confidence: likely
+source: "Astra, space data centers feasibility analysis February 2026; Google Project Suncatcher analysis"
+created: 2026-02-17
+depends_on:
+  - "distributed LEO inference networks could serve global AI requests at 4-20ms latency competitive with centralized terrestrial data centers for latency-tolerant workloads"
+  - "space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density"
+---
+
+# Orbital AI training is fundamentally incompatible with space communication links because distributed training requires hundreds of Tbps aggregate bandwidth while orbital links top out at single-digit Tbps
+
+Large-scale AI training is the one workload that virtually every serious analysis concludes will never move to orbit. The reason is bandwidth, and the gap is not marginal -- it is orders of magnitude.
+
+Training a frontier model involves distributing computation across tens of thousands of GPUs that must constantly exchange gradient updates during backpropagation. This requires aggregate inter-node bandwidth measured in hundreds of terabits per second with tight synchronization (microsecond-scale consistency across nodes). A single terrestrial data center typically has 100-plus Tbps of aggregate internal bandwidth, with individual node interconnects running at 400 Gbps to 800 Gbps (moving toward 1.6 Tbps with next-generation InfiniBand and Ethernet standards).
+
+Current state-of-the-art satellite communication links deliver: Starlink satellites at 200 Gbps per satellite with next generation targeting 1 Tbps; Blue Origin TeraWave at up to 6 Tbps; Axiom optical inter-satellite links at 10 Gbps. Even Blue Origin's most ambitious specification falls two orders of magnitude short of the aggregate bandwidth a terrestrial training cluster provides.
+
+The bandwidth constraint is compounded by latency jitter. Distributed training algorithms (data parallelism, model parallelism, pipeline parallelism) all require deterministic communication timing to maintain training efficiency. Orbital link latency varies with satellite position, atmospheric conditions on ground links, and inter-satellite hop count -- introducing jitter that degrades training throughput even when average bandwidth is sufficient.
+
+Starcloud's demonstration of "training an LLM in space" almost certainly involved a small model on a single GPU -- a valid proof of concept for orbital hardware operation but not evidence that distributed training at frontier scale is feasible. This constraint shapes the entire orbital compute opportunity: inference yes (eventually), on-orbit satellite processing yes (now), training no (likely never).
+
+## Evidence
+- Terrestrial data center aggregate bandwidth: 100+ Tbps with 400-800 Gbps per node
+- Starlink satellite links: 200 Gbps current, 1 Tbps next-gen target
+- Blue Origin TeraWave: up to 6 Tbps (most ambitious orbital link)
+- Gap: 2+ orders of magnitude between orbital and terrestrial bandwidth
+
+## Challenges
+Novel training algorithms that reduce communication requirements (local SGD, federated learning approaches) could narrow the gap, but the fundamental bandwidth asymmetry makes orbital training uncompetitive for frontier-scale models.
+
+---
+
+Relevant Notes:
+- [[distributed LEO inference networks could serve global AI requests at 4-20ms latency competitive with centralized terrestrial data centers for latency-tolerant workloads]] — inference works because it does not require all-to-all bandwidth
+- [[on-orbit processing of satellite data is the proven near-term use case for space compute because it avoids bandwidth and thermal bottlenecks simultaneously]] — the viable alternative to moving training to orbit
+
+Topics:
+- [[space exploration and development]]

domains/space-development/orbital bioprinting enables tissue and organ fabrication impossible under gravity because structures collapse without scaffolding on Earth.md

@@ -0,0 +1,41 @@
+---
+type: claim
+domain: space-development
+description: "Microgravity allows 3D bioprinting of tissues that maintain shape without scaffolding — cardiac tissue, knee meniscus, liver constructs already printed on ISS with transplant-ready organs as the long-term goal"
+confidence: experimental
+source: "Astra, web research compilation February 2026"
+created: 2026-02-17
+secondary_domains:
+  - health
+depends_on:
+  - "microgravity eliminates convection sedimentation and container effects producing measurably superior materials across fiber optics pharmaceuticals and semiconductors"
+  - "the space manufacturing killer app sequence is pharmaceuticals now ZBLAN fiber in 3-5 years and bioprinted organs in 15-25 years each catalyzing the next tier of orbital infrastructure"
+---
+
+# Orbital bioprinting enables tissue and organ fabrication impossible under gravity because structures collapse without scaffolding on Earth
+
+On Earth, 3D bioprinted tissues collapse under their own weight during the printing and maturation process, requiring scaffolding that introduces structural compromises. In microgravity, tissues maintain their shape without scaffolding because gravitational forces are absent. This is not a marginal improvement -- it enables fabrication of tissue geometries and organ structures that are physically impossible to print on Earth. Thick-tissue bioprinting (>1cm) is the strongest "truly impossible" claim in all of microgravity manufacturing -- no terrestrial workaround exists.
+
+**Current state of play.** Redwire's BioFabrication Facility (BFF) on the ISS successfully printed a human knee meniscus (July 2023, returned on SpaceX Crew-6), followed by the first live human heart tissue sample (returned April 2024). Heart patches for damaged cardiac tissue are a stated near-term goal. ESA's 3D Biosystem (3DBS), developed by Redwire Europe with hardware from Finnish company Brinter, is scheduled for installation in the Columbus module in 2026.
+
+**The transplant market.** Over 105,000 individuals are on the US organ transplant waitlist as of 2025, with kidneys accounting for 87% (~90,000 people). A single kidney transplant costs ~$447,000. The global transplantation market is valued at $19.2B in 2025, projected to reach $42B by 2035. A bioprinted kidney at even half the current transplant cost represents ~$667K/kg in value -- well above any launch-cost threshold.
+
+**Timeline reality check.** Functional transplantable organs require integrated vasculature, multiple cell types, and years of clinical validation. Realistic timeline: bioprinted cartilage and tissue patches in 8-12 years, functional transplantable organs in 15-25 years. The nearer-term orthopedic products (meniscus, cartilage) are the most feasible first commercial products.
+
+## Evidence
+- Redwire BFF — knee meniscus (2023), cardiac tissue (2024) printed on ISS
+- ESA 3D Biosystem scheduled for Columbus module 2026
+- US transplant waitlist: 105,000+ individuals, $447K per kidney transplant
+- No terrestrial workaround exists for >1cm thick-tissue bioprinting
+
+## Challenges
+Functional vascularized organs are 15-25 years away. Terrestrial bioprinting advances (sacrificial scaffolds, decellularization) may narrow the gap for simpler tissues, though the thick-tissue advantage appears permanent.
+
+---
+
+Relevant Notes:
+- [[microgravity eliminates convection sedimentation and container effects producing measurably superior materials across fiber optics pharmaceuticals and semiconductors]] — bioprinting extends the microgravity advantage to biological fabrication
+- [[the space manufacturing killer app sequence is pharmaceuticals now ZBLAN fiber in 3-5 years and bioprinted organs in 15-25 years each catalyzing the next tier of orbital infrastructure]] — bioprinting is Tier 3 in this sequence
+
+Topics:
+- [[space exploration and development]]

domains/space-development/orbital compute hardware cannot be serviced making every component either radiation-hardened redundant or disposable with failed hardware becoming debris or requiring expensive deorbit.md

@@ -0,0 +1,39 @@
+---
+type: claim
+domain: space-development
+description: "No technician can swap a failed drive in orbit — every failure is permanent without servicing infrastructure that does not exist at scale creating a reliability-cost tradeoff that favors disposable architecture"
+confidence: likely
+source: "Astra, space data centers feasibility analysis February 2026; Microsoft Project Natick comparison"
+created: 2026-02-17
+depends_on:
+  - "space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density"
+  - "orbital debris is a classic commons tragedy where individual launch incentives are private but collision risk is externalized to all operators"
+---
+
+# Orbital compute hardware cannot be serviced making every component either radiation-hardened redundant or disposable with failed hardware becoming debris or requiring expensive deorbit
+
+The impossibility of on-orbit maintenance creates a fundamental reliability-cost tradeoff that terrestrial data centers never face. In a ground facility, a failed drive is swapped in minutes. A failed GPU is replaced by next-day delivery. In orbit, every failure is permanent for the life of that satellite.
+
+This forces a trilemma. First, radiation-hardened components -- but radiation-hardened processors are generations behind commercial silicon in performance and orders of magnitude more expensive, negating the economic case for orbital compute. Second, massive redundancy -- but every redundant component adds mass that must be launched, and the cost of launching mass is the critical economic variable. Third, disposable architecture -- accept failures and replace entire satellites, but this requires a launch cadence and cost structure that does not yet exist and creates space debris from deorbiting failed units.
+
+Microsoft's Project Natick provides an instructive comparison. Their sealed underwater data centers achieved a 0.7 percent server failure rate versus 5.9 percent on land over two years -- demonstrating that controlled environments without human access can actually improve reliability. But underwater is retrievable at modest cost. Orbit is not. Microsoft ultimately killed Project Natick in 2024 because the deployment model was impractical at scale despite the reliability improvement.
+
+The maintenance constraint also limits hardware refresh cycles. Terrestrial data centers upgrade GPUs every 3 to 5 years. Orbital hardware has a fixed capability at launch for its entire 5 to 10 year operational lifetime. A satellite launched in 2027 with H100-class GPUs will be running 2027-era hardware in 2032, by which time terrestrial facilities will have cycled through one or two generations of dramatically more powerful accelerators.
+
+## Evidence
+- Microsoft Project Natick — 0.7% vs 5.9% failure rate but killed in 2024 due to deployment impracticality
+- Astroscale 15m closest commercial approach to debris (single-mission demonstrations only)
+- Northrop Grumman MEV life-extension docking (single-mission scale)
+- GPU refresh cycles: 3-5 years terrestrial vs fixed capability for orbital lifetime
+
+## Challenges
+Autonomous satellite servicing and modular hardware architectures could change this equation, but require a servicing fleet that does not exist and would add significant cost overhead.
+
+---
+
+Relevant Notes:
+- [[orbital debris is a classic commons tragedy where individual launch incentives are private but collision risk is externalized to all operators]] — failed orbital compute nodes add to the debris problem
+- [[reusability without rapid turnaround and minimal refurbishment does not reduce launch costs as the Space Shuttle proved over 30 years]] — the Shuttle lesson applies: servicing in orbit may cost more than replacement
+
+Topics:
+- [[space exploration and development]]

domains/space-development/orbital data centers are the most speculative near-term space application but the convergence of AI compute demand and falling launch costs attracts serious players.md

@@ -0,0 +1,40 @@
+---
+type: claim
+domain: space-development
+description: "Starcloud trained an LLM in space, Axiom launched orbital nodes, SpaceX filed for millions of satellites, Google plans Suncatcher — economics do not close yet but FCC filings signal conviction from major players"
+confidence: speculative
+source: "Astra, web research compilation February 2026"
+created: 2026-02-17
+secondary_domains:
+  - critical-systems
+depends_on:
+  - "space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density"
+  - "Starship achieving routine operations at sub-100 dollars per kg is the single largest enabling condition for the entire space industrial economy"
+---
+
+# Orbital data centers are the most speculative near-term space application but the convergence of AI compute demand and falling launch costs attracts serious players
+
+Space-based data centers have exploded in activity despite being the most speculative sector in the space economy. Axiom Space launched first two orbital data center nodes to LEO on January 11, 2026. Starcloud (Nvidia-backed, Y Combinator company) deployed NVIDIA H100-class systems in orbit, trained an LLM in space, ran Google Gemini in orbit, and filed an FCC proposal for up to 88,000 satellites. SpaceX filed FCC plans for millions of satellites leveraging Starlink integration for orbital computing. Google's Project Suncatcher plans solar-powered satellite constellations carrying specialty AI chips for a 2027 demonstration.
+
+The theoretical advantages are real: unlimited solar power in certain orbits, radiative cooling in vacuum, and escape from terrestrial power and cooling constraints hitting AI data centers. LEO data centers at 550 km have approximately 3.7 ms one-way latency -- comparable to many terrestrial connections. But the challenges are formidable: radiation-hardened hardware requirements, cooling limitations (radiative only, no convection), extremely high cost of launching power-dense compute, maintenance and upgradeability constraints, and bandwidth limitations for data transfer.
+
+The economics do not currently close for general cloud computing. But the convergence of insatiable AI compute demand, falling launch costs, and advancing in-space solar power could make orbital data centers viable for specific workloads before general computing moves to orbit. The concept is real but overhyped on timeline. Google projects cost-competitiveness around 2035 contingent on $200/kg launch costs. Terrestrial alternatives -- arctic data centers, nuclear-powered facilities, on-site generation -- beat orbital compute on every metric for the next decade.
+
+## Evidence
+- Axiom Space orbital data center nodes launched January 2026
+- Starcloud H100 in orbit, LLM trained in space (November 2025)
+- SpaceX FCC filing for millions of satellites (January 2026)
+- Google Project Suncatcher 2027 demonstration planned
+- Google feasibility analysis projecting cost-competitiveness ~2035 at $200/kg
+
+## Challenges
+Thermal management is the showstopper at scale. A 100 MW orbital data center would need ~100,000 m² of radiators weighing 500,000+ kg. Space is a thermos, not a freezer.
+
+---
+
+Relevant Notes:
+- [[space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density]] — the physics deep-dive on why datacenter-scale orbital compute fails
+- [[Starship achieving routine operations at sub-100 dollars per kg is the single largest enabling condition for the entire space industrial economy]] — orbital data centers require Starship-era launch costs
+
+Topics:
+- [[space exploration and development]]

domains/space-development/orbital data centers require five enabling technologies to mature simultaneously and none currently exist at required readiness.md

@@ -0,0 +1,45 @@
+---
+type: claim
+domain: space-development
+description: "Starship-class launch at sub-100/kg plus advanced radiative thermal management plus Tbps optical links plus radiation-tolerant AI accelerators plus autonomous servicing — all five needed and none proven at scale"
+confidence: likely
+source: "Astra, space data centers feasibility analysis February 2026; Google Project Suncatcher analysis"
+created: 2026-02-17
+depends_on:
+  - "space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density"
+  - "Starship achieving routine operations at sub-100 dollars per kg is the single largest enabling condition for the entire space industrial economy"
+---
+
+# Orbital data centers require five enabling technologies to mature simultaneously and none currently exist at required readiness
+
+The viability of orbital data centers at commercially meaningful scale depends on the simultaneous maturation of five independent enabling technologies. The failure of any single one is sufficient to block the entire concept. As of early 2026, none of the five exist at the required readiness level.
+
+**1. Starship-class launch at $100/kg or less.** Google's feasibility analysis pins orbital compute cost-competitiveness at $200/kg launch costs, projected around 2035 if Starship achieves 180 flights per year at full reusability. Current Falcon 9 customer pricing is approximately $2,720/kg. Status: TRL 7-8 for the vehicle, but the cost target depends on operational tempo that is TRL 4-5.
+
+**2. Advanced radiative thermal management at data center scale.** A 100 MW orbital facility needs approximately 100,000 square meters of radiator surface weighing over 500,000 kg. No design, prototype, or credible roadmap exists for megawatt-scale radiative cooling in orbit. Status: TRL 2-3 at megawatt scale.
+
+**3. High-bandwidth optical inter-satellite links at Tbps-plus.** Distributed orbital compute requires inter-node communication far beyond current capability. Starlink at 200 Gbps, next gen targeting 1 Tbps. Blue Origin TeraWave at up to 6 Tbps. Terrestrial data center aggregate bandwidth exceeds 100 Tbps. Status: TRL 6-7 for current generation, TRL 3-4 for the 10-100 Tbps links orbital compute at scale would require.
+
+**4. Radiation-tolerant or radiation-hardened AI accelerators.** Google's TPU testing (no hard failures to 15 krad) is encouraging but represents one chip architecture in short-duration exposure. Long-duration operation remains uncharacterized for commercial AI hardware. Status: TRL 4-5 for commercial chips in LEO.
+
+**5. Autonomous satellite servicing or reliable disposable architecture.** Without maintenance capability, every satellite has a fixed operational lifetime of 5-10 years. Status: TRL 3-4 for commercial servicing, with single-mission demonstrations only.
+
+The probability of all five maturing on compatible timelines is the product of their individual probabilities -- substantially lower than any single probability.
+
+## Evidence
+- Google Project Suncatcher feasibility analysis (2035 cost-competitiveness projection)
+- Current TRL assessments across all five technology areas
+- Falcon 9 pricing at ~$2,720/kg vs required $100-200/kg
+
+## Challenges
+Distributed architecture (thousands of small satellites) changes the thermal and servicing math but multiplies launch costs and introduces distributed computing challenges that compound the bandwidth requirement.
+
+---
+
+Relevant Notes:
+- [[space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density]] — technology #2 is the hardest with no credible roadmap
+- [[Starship achieving routine operations at sub-100 dollars per kg is the single largest enabling condition for the entire space industrial economy]] — technology #1 is the keystone that gates all others economically
+- [[modern AI accelerators are more radiation-tolerant than expected because Google TPU testing showed no hard failures up to 15 krad suggesting consumer chips may survive LEO environments]] — technology #4 showing promising early results
+
+Topics:
+- [[space exploration and development]]

domains/space-development/radiation protection for space habitation converges on a multi-layered strategy because no single approach provides adequate shielding against both galactic cosmic rays and solar particle events.md

@@ -0,0 +1,36 @@
+---
+type: claim
+domain: space-development
+description: "Passive regolith shielding reduces exposure from 291 to 213 mSv/year but still exceeds Earth limits requiring active magnetic systems, storm shelters, and pharmacological countermeasures"
+confidence: likely
+source: "Astra, web research compilation February 2026"
+created: 2026-02-17
+depends_on:
+  - "closed-loop life support is the binding constraint on permanent space settlement because all other enabling technologies are closer to operational readiness"
+---
+
+# Radiation protection for space habitation converges on a multi-layered strategy because no single approach provides adequate shielding against both galactic cosmic rays and solar particle events
+
+Radiation is one of the top three challenges for long-duration space habitation, with two distinct threats: galactic cosmic rays (GCRs) providing chronic low-dose exposure and solar particle events (SPEs) delivering acute high-dose bursts. No single shielding approach adequately addresses both, driving the field toward a multi-layered defense strategy.
+
+Passive shielding uses hydrogen-rich materials (water, polyethylene) since hydrogen has the highest electron density per nucleon with no neutrons. Regolith-based solutions avoid transporting heavy materials from Earth: 2025 research shows 45 g/cm² of regolith reduces annual exposure from 291 mSv to 213 mSv -- significant but still above the 20 mSv/year Earth occupational limit. Active shielding through magnetic systems like CREW HaT (a cylindrical Halbach array of electromagnet coils around the habitat) addresses charged particles but adds weight, power demands, and complexity. Storm shelters provide acute SPE protection. Emerging approaches include mycelium as radiation-absorbing medium, self-healing polymers for damaged shielding, and pharmacological radioprotective drugs.
+
+The consensus architecture layers these approaches: passive structural shielding as the primary barrier, active magnetic shielding as supplement, storm shelters for acute events, pharmacological countermeasures, and mission design that minimizes exposure (fast transit, subsurface habitation). For lunar and Martian surface habitats, going underground or covering with regolith is architecturally simple but construction-intensive.
+
+## Evidence
+- 45 g/cm² regolith reduces exposure from 291 to 213 mSv/year (2025 research)
+- CREW HaT magnetic shielding concept in development
+- Mycelium radiation absorption research ongoing
+- Multi-layered defense as consensus architecture across all major space agencies
+
+## Challenges
+GCR shielding remains fundamentally harder than SPE shielding due to the high energy of cosmic ray particles. Pharmacological radioprotectors are in early research stages with limited efficacy data for chronic exposure.
+
+---
+
+Relevant Notes:
+- [[closed-loop life support is the binding constraint on permanent space settlement because all other enabling technologies are closer to operational readiness]] — radiation shielding is more mature than life support, validating life support as the binding constraint
+- [[water is the strategic keystone resource of the cislunar economy because it simultaneously serves as propellant life support radiation shielding and thermal management]] — water as shielding material
+
+Topics:
+- [[space exploration and development]]

domains/space-development/reusability without rapid turnaround and minimal refurbishment does not reduce launch costs as the Space Shuttle proved over 30 years.md

@@ -36,6 +36,12 @@ Blue Origin's New Glenn NG-3 mission demonstrates a ~3-month booster turnaround
 
 V3 qualification timeline shows the challenge of validating new engine generations at scale. The 10-engine partial static fire (March 16) to 33-engine full static fire sequence demonstrates that even with successful engine startup, ground systems integration (GSE at new Pad 2) creates qualification bottlenecks. Each delay in V3 validation extends the timeline to operational reusability with Raptor 3.
 
+### Additional Evidence (confirm)
+*Source: [[2026-03-27-blueorigin-new-glenn-manufacturing-odc-ambitions]] | Added: 2026-03-27*
+
+Blue Origin's New Glenn program shows manufacturing rate (1/month) significantly exceeding launch cadence (2 total launches in 2025), with NG-3 still delayed as of March 2026. This demonstrates that building reusable hardware does not automatically translate to high-cadence operations—the operational knowledge (pad turnaround, refurbishment processes, flight software maturity) lags behind manufacturing capability.
+
+
 
 Relevant Notes:
 - [[launch cost reduction is the keystone variable that unlocks every downstream space industry at specific price thresholds]] — the Shuttle's failure to reduce costs delayed downstream industries by decades

domains/space-development/self-sufficient colony technologies are inherently dual-use because closed-loop systems required for space habitation directly reduce terrestrial environmental impact.md

@@ -0,0 +1,38 @@
+---
+type: claim
+domain: space-development
+description: "3D printing, vertical farming, circular economies, renewable energy, and automation must work in closed loops for space colonies — the same technologies exported to Earth reduce environmental footprint"
+confidence: likely
+source: "Astra, Teleological Investing Part II"
+created: 2026-02-28
+depends_on:
+  - "in-situ resource utilization is the bridge technology between outpost and settlement because without it every habitat remains a supply chain exercise"
+  - "the self-sustaining space operations threshold requires closing three interdependent loops simultaneously -- power water and manufacturing"
+---
+
+# Self-sufficient colony technologies are inherently dual-use because closed-loop systems required for space habitation directly reduce terrestrial environmental impact
+
+Regardless of where eventual space colonies are located, they must share certain core characteristics that create investable technology streams right now. Colonies must be maximally self-sufficient, requiring very little input from outside, and produce economically valuable goods. This means: 3D printing, vertical farming and hydroponics, circular economies, high levels of automation, renewable energy (almost certainly solar power), and healthy individuals who do not require huge specialized medical interventions.
+
+The dual-use insight is structural, not coincidental. The same technologies that allow colonies to need very little outside input can be exported back to Earth to reduce the impact of our economies on our surroundings. A closed-loop manufacturing system designed for an asteroid habitat works identically to reduce waste in a terrestrial factory. Vertical farming developed for a lunar base reduces agricultural land use and water consumption on Earth. Solar power systems designed for continuous space operation advance terrestrial renewable energy.
+
+This parallels the original space race, where initial investment in space capabilities developed technological competencies that were eventually spun off into mobile phones, GPS, and medical imaging. But the scale is different: the space race produced incidental spin-offs, while building self-sufficient colonies requires deliberately developing the exact technologies Earth needs to become sustainable. The spin-off is not a side effect -- it is the core product viewed from a different angle.
+
+This creates the investment thesis: companies developing these technologies have option value on both terrestrial and space markets. The company that builds the best vertical farming system for space will also have built the best vertical farming system for Earth.
+
+## Evidence
+- Historical space race technology spinoffs (GPS, medical imaging, communications)
+- Closed-loop system requirements for space habitation matching sustainability requirements on Earth
+- ISRU development forcing closed-loop system engineering with terrestrial applications
+
+## Challenges
+The parallel between space and terrestrial closed-loop requirements is clearer in theory than in practice. Many space-specific engineering constraints (mass minimization, radiation hardening) don't apply on Earth, potentially limiting technology transfer.
+
+---
+
+Relevant Notes:
+- [[in-situ resource utilization is the bridge technology between outpost and settlement because without it every habitat remains a supply chain exercise]] — ISRU forces closed-loop development
+- [[the self-sustaining space operations threshold requires closing three interdependent loops simultaneously -- power water and manufacturing]] — closing these loops for space solves the same efficiency problems as sustainable development on Earth
+
+Topics:
+- [[space exploration and development]]

domains/space-development/solar irradiance in LEO delivers 8-10x ground-based solar power with near-continuous availability in sun-synchronous orbits making orbital compute power-abundant where terrestrial facilities are power-starved.md

@@ -0,0 +1,38 @@
+---
+type: claim
+domain: space-development
+description: "At 1366 W/m² with no atmosphere, clouds, or night cycle in sun-synchronous orbits, space solar eliminates the power constraint that gates terrestrial data center expansion"
+confidence: proven
+source: "Astra, space data centers feasibility analysis February 2026; Google Project Suncatcher feasibility study"
+created: 2026-02-17
+secondary_domains:
+  - energy
+depends_on:
+  - "space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density"
+  - "power is the binding constraint on all space operations because every capability from ISRU to manufacturing to life support is power-limited"
+---
+
+# Solar irradiance in LEO delivers 8-10x ground-based solar power with near-continuous availability in sun-synchronous orbits making orbital compute power-abundant where terrestrial facilities are power-starved
+
+Solar irradiance in low Earth orbit is approximately 1,366 watts per square meter -- the full output of the sun unattenuated by atmosphere. After accounting for atmospheric absorption, weather, day/night cycles, and panel orientation losses, ground-based solar panels achieve roughly 150-200 W/m² of average output. The orbital advantage is therefore 7-10x in raw power density per unit area.
+
+In sun-synchronous orbits (approximately 600-800 km altitude), satellites maintain a nearly constant angle to the sun, achieving near-continuous illumination. Eclipse periods still occur but are short (roughly 30 minutes per 90-minute orbit in some configurations), manageable with battery buffering. There are no grid interconnection queues, no utility contracts, no transmission losses, no permitting delays, and no competition with other users for the same electrical infrastructure.
+
+This is the strongest genuine advantage of orbital compute. Power generation in space is not a speculative technology -- it is mature, well-characterized physics exploited by every satellite in orbit since the dawn of the space age. The solar panels themselves are the most cost-effective component of the orbital compute stack. The irony is that while power generation is essentially solved in orbit, dissipating the waste heat from using that power is the unsolved showstopper. Power-abundant and cooling-constrained is the exact inverse of the terrestrial situation (cooling-abundant, power-constrained), which is why the orbital data center thesis is seductive but the physics do not cooperate at scale.
+
+## Evidence
+- Solar constant: 1,366 W/m² in LEO vs 150-200 W/m² average ground-based
+- Sun-synchronous orbit mechanics providing near-continuous illumination
+- Every satellite in orbit validates space solar power generation
+
+## Challenges
+[[space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density]] — the fatal irony: orbital power is abundant but dissipating waste heat is the binding constraint.
+
+---
+
+Relevant Notes:
+- [[space-based solar power economics depend almost entirely on launch cost reduction with viability threshold near 10 dollars per kg to orbit]] — the alternative: beam orbital solar to terrestrial data centers
+- [[power is the binding constraint on all space operations because every capability from ISRU to manufacturing to life support is power-limited]] — for compute, the constraint shifts from power to thermal management
+
+Topics:
+- [[space exploration and development]]

domains/space-development/space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density.md

@@ -0,0 +1,40 @@
+---
+type: claim
+domain: space-development
+description: "A 100 MW orbital facility needs 500,000 kg of radiators — space is a thermos not a freezer so only on-orbit satellite data processing and edge inference are viable near-term"
+confidence: likely
+source: "Astra, space data centers feasibility analysis February 2026"
+created: 2026-02-17
+secondary_domains:
+  - critical-systems
+depends_on:
+  - "Starship achieving routine operations at sub-100 dollars per kg is the single largest enabling condition for the entire space industrial economy"
+  - "power is the binding constraint on all space operations because every capability from ISRU to manufacturing to life support is power-limited"
+---
+
+# Space-based computing at datacenter scale is blocked by thermal physics because radiative cooling in vacuum requires surface areas that grow faster than compute density
+
+The pitch for orbital data centers rests on a seductive premise: AI compute demand is growing exponentially, terrestrial data centers are hitting power and cooling constraints, and space offers unlimited solar energy plus passive cooling. The demand side is real -- the US data center pipeline will add 140 GW of new load against current draw under 15 GW. But the supply-side physics are brutal. Space is not a freezer; it is a thermos. With no convective medium, all heat must be radiated according to the Stefan-Boltzmann law, where power radiated scales with the fourth power of temperature and linearly with surface area. At 320 K (a reasonable chip operating temperature), a perfect blackbody radiates roughly 600 watts per square meter. The smallest useful AI data center runs approximately 100 MW. An orbital version would need about 100,000 square meters of radiator surface -- a 316-meter-by-316-meter array -- weighing over 500,000 kg at realistic radiator mass of 5 to 10 kg per square meter.
+
+The bandwidth constraint is equally fatal for the highest-value workload. Large-scale AI training requires hundreds of terabits per second of aggregate inter-node bandwidth. Current satellite links top out at 200 Gbps (Starlink) to 6 Tbps (Blue Origin TeraWave). The gap is orders of magnitude.
+
+What does work is on-orbit processing of satellite-generated data (kilowatt-scale, data already in orbit) and distributed LEO inference (independent nodes, acceptable latency). Terrestrial alternatives -- arctic data centers with 70%+ cooling cost reduction, nuclear-powered facilities -- beat orbital compute on every metric for the next decade. Google projects cost-competitiveness around 2035 contingent on $200/kg launch costs.
+
+## Evidence
+- Stefan-Boltzmann law: ~600 W/m² radiative capacity at 320 K
+- 100 MW facility requires ~100,000 m² radiators weighing 500,000+ kg
+- Solar input (1,366 W/m²) further reduces net radiative capacity
+- Google Project Suncatcher feasibility analysis (2035 projection)
+
+## Challenges
+Novel cooling technologies (droplet radiators, phase-change systems) could improve radiative efficiency, but none have been demonstrated at scale in space environments.
+
+---
+
+Relevant Notes:
+- [[orbital data centers are the most speculative near-term space application but the convergence of AI compute demand and falling launch costs attracts serious players]] — this note provides the detailed physics showing why the convergence thesis fails at datacenter scale
+- [[on-orbit processing of satellite data is the proven near-term use case for space compute because it avoids bandwidth and thermal bottlenecks simultaneously]] — the viable near-term use case
+- [[distributed LEO inference networks could serve global AI requests at 4-20ms latency competitive with centralized terrestrial data centers for latency-tolerant workloads]] — the viable long-term use case
+
+Topics:
+- [[space exploration and development]]

domains/space-development/space-based pharmaceutical manufacturing produces clinically superior drug formulations that cannot be replicated on Earth.md

@@ -0,0 +1,41 @@
+---
+type: claim
+domain: space-development
+description: "Microgravity crystallization yields smaller, more uniform drug crystals with better injectability and bioavailability — demonstrated by Merck Keytruda and Varda ritonavir missions"
+confidence: likely
+source: "Astra, web research compilation February 2026"
+created: 2026-02-17
+secondary_domains:
+  - health
+depends_on:
+  - "microgravity eliminates convection sedimentation and container effects producing measurably superior materials across fiber optics pharmaceuticals and semiconductors"
+  - "microgravity-discovered pharmaceutical polymorphs are a novel IP mechanism because new crystal forms enable patent extension reformulation and new delivery methods"
+---
+
+# Space-based pharmaceutical manufacturing produces clinically superior drug formulations that cannot be replicated on Earth
+
+Microgravity suppresses convective currents and sedimentation during crystallization, producing drug crystals that are smaller, more uniform, and have fewer defects than any achievable on Earth. Over 500 protein crystallization experiments have been conducted on the ISS -- the station's largest research category.
+
+**The Keytruda breakthrough.** Merck crystallized pembrolizumab (Keytruda, ~$25B/year revenue) in microgravity, producing crystals with a homogeneous monomodal particle size distribution of 39 microns and significantly lower viscosity than ground controls. This enabled reformulation from IV infusion to subcutaneous injection. The FDA approved the subcutaneous formulation in late 2025 -- the first commercially significant pharmaceutical product directly enabled by microgravity research, potentially affecting billions in annual drug revenue.
+
+**Varda's commercial validation.** Varda Space Industries has demonstrated the business model works mechanically with four orbital missions. Their first mission produced Form III ritonavir -- a metastable polymorph difficult to create on Earth. The dual revenue model (pharmaceutical IP plus $48M Air Force reentry vehicle contract) stabilizes the business while pharmaceutical discovery scales.
+
+**The polymorph IP mechanism.** Different polymorphs of the same drug can have dramatically different solubility, bioavailability, and stability. Microgravity accesses metastable polymorphic pathways that convection-driven nucleation excludes on Earth. McKinsey estimated a single novel oncology drug from space-based R&D could generate $1.2B NPV, with aggregate revenues projected at $2.8-$4.2B.
+
+## Evidence
+- Merck Keytruda subcutaneous reformulation — FDA approved late 2025
+- 500+ protein crystallization experiments on ISS
+- Varda — 4 orbital missions, ritonavir Form III produced
+- McKinsey projections — $1.2B per novel oncology drug NPV
+
+## Challenges
+Whether microgravity-discovered polymorphs can eventually be replicated through advanced terrestrial techniques remains the critical open question. Even if replication is possible, first-mover discovery advantage generates IP regardless.
+
+---
+
+Relevant Notes:
+- [[microgravity eliminates convection sedimentation and container effects producing measurably superior materials across fiber optics pharmaceuticals and semiconductors]] — the physics mechanism
+- [[microgravity-discovered pharmaceutical polymorphs are a novel IP mechanism because new crystal forms enable patent extension reformulation and new delivery methods]] — the specific IP mechanism
+
+Topics:
+- [[space exploration and development]]

domains/space-development/space-based solar power economics depend almost entirely on launch cost reduction with viability threshold near 10 dollars per kg to orbit.md

@@ -0,0 +1,39 @@
+---
+type: claim
+domain: space-development
+description: "SBSP market projected at $4.61B by 2041 but remains pre-commercial; the physics works, the economics close at $10/kg to orbit where Starship is heading, enabling 25 MW per launch"
+confidence: experimental
+source: "Astra, web research compilation February 2026"
+created: 2026-02-17
+secondary_domains:
+  - energy
+depends_on:
+  - "Starship achieving routine operations at sub-100 dollars per kg is the single largest enabling condition for the entire space industrial economy"
+  - "power is the binding constraint on all space operations because every capability from ISRU to manufacturing to life support is power-limited"
+---
+
+# Space-based solar power economics depend almost entirely on launch cost reduction with viability threshold near 10 dollars per kg to orbit
+
+Space-based solar power has a market projected to grow from $630 million (2025) to $4.61 billion by 2041 (13.24% CAGR). The physics is demonstrated: Caltech's SSPD-1 wirelessly transmitted power in space and beamed detectable power to Earth in May 2023. China's OMEGA program has demonstrated microwave power transmission and beam collection efficiency with a target of a 200-tonne SBSP station generating megawatts by 2035. Multi-junction photovoltaic cells are achieving near 47% efficiency.
+
+But SBSP remains pre-commercial because the economics are gated by a single variable: launch cost. At current costs, orbiting enough mass for meaningful power generation is prohibitive. At $10/kg to orbit -- where Starship's fully reusable architecture is heading -- Starship's 100-tonne capacity could deliver enough modular panels for approximately 25 MW per launch. A King's College London study (2025) found SBSP could offset up to 80% of wind and solar and cut battery storage requirements by more than 70%.
+
+The unknowns remain significant: in-orbit assembly at km-scale, long-term degradation in the space environment, and political/regulatory frameworks for energy beaming. But the convergence of falling launch costs, advancing photovoltaics, and demonstrated wireless power transmission creates a conditional inevitability -- SBSP is not a question of if but of when launch costs cross the threshold.
+
+## Evidence
+- Caltech SSPD-1 — wireless power transmission in space (May 2023)
+- China OMEGA program — microwave power transmission demonstrated
+- Multi-junction PV cells at ~47% efficiency
+- King's College London study — SBSP could offset 80% of wind/solar
+
+## Challenges
+In-orbit assembly at km-scale has never been demonstrated. Long-term degradation from radiation and micrometeorites is uncertain. Political and regulatory frameworks for energy beaming between nations do not exist.
+
+---
+
+Relevant Notes:
+- [[Starship achieving routine operations at sub-100 dollars per kg is the single largest enabling condition for the entire space industrial economy]] — SBSP economics depend on Starship-era launch costs
+- [[power is the binding constraint on all space operations because every capability from ISRU to manufacturing to life support is power-limited]] — SBSP is one approach to solving the binding power constraint
+
+Topics:
+- [[space exploration and development]]

domains/space-development/the commercial space station transition from ISS creates a gap risk that could end 25 years of continuous human presence in low Earth orbit.md

@@ -0,0 +1,36 @@
+---
+type: claim
+domain: space-development
+description: "Four competing commercial stations race to replace ISS by 2031 but timeline slippage threatens unbroken human orbital presence since 2000"
+confidence: likely
+source: "Astra, web research compilation February 2026"
+created: 2026-02-17
+depends_on:
+  - "commercial space stations are the next infrastructure bet as ISS retirement creates a void that 4 companies are racing to fill by 2030"
+---
+
+# The commercial space station transition from ISS creates a gap risk that could end 25 years of continuous human presence in low Earth orbit
+
+The ISS is scheduled for controlled deorbiting in January 2031 after a final crew retrieval in 2030, with SpaceX building the US Deorbit Vehicle under an $843 million contract. Four commercial station programs are racing to fill the gap: Vast (Haven-1 launching May 2026, Haven-2 by 2032), Axiom Space (PPTM docking to ISS in 2027, independent station by early 2028), Starlab by Voyager Space and Airbus (no earlier than 2028 via Starship), and Orbital Reef by Blue Origin and Sierra Space (targeting 2030). MIT Technology Review named commercial space stations one of its 10 Breakthrough Technologies of 2026.
+
+The central anxiety is a potential capability gap. Axiom's timeline has already been reshuffled due to ISS deorbit timing and the need to support the deorbit vehicle. If commercial stations slip further, the US could face its first period without permanent crewed presence in LEO since November 2000.
+
+This transition from government-owned to commercially operated orbital infrastructure represents a structural shift in how humanity maintains its presence in space -- from a single multinational government project to a competitive commercial market. NASA plans to begin purchasing orbital research services from commercial stations starting in 2028, becoming a customer rather than an operator. The success or failure of this transition will set precedent for how governments relate to commercial infrastructure in frontier environments.
+
+## Evidence
+- ISS deorbit scheduled January 2031, SpaceX Deorbit Vehicle contract ($843M)
+- Vast Haven-1 (May 2026), Axiom PPTM (2027), Starlab (2028), Orbital Reef (2030)
+- Continuous human orbital presence since November 2000
+- MIT Technology Review — commercial stations named 2026 Breakthrough Technology
+
+## Challenges
+All four commercial station timelines face slippage risk. Axiom's financial difficulties and Axiom's PPTM-first approach is the most realistic gap hedge but depends on their survival as a company.
+
+---
+
+Relevant Notes:
+- [[commercial space stations are the next infrastructure bet as ISS retirement creates a void that 4 companies are racing to fill by 2030]] — the competitive landscape this gap risk plays out across
+- [[Axiom Space has the strongest operational position for commercial orbital habitation but the weakest financial position among funded competitors]] — Axiom's financial instability is the single largest risk factor
+
+Topics:
+- [[space exploration and development]]

domains/space-development/the impossible on Earth test separates three tiers of microgravity advantage -- truly impossible products dramatically better products and products where terrestrial workarounds exist.md

@@ -0,0 +1,51 @@
+---
+type: claim
+domain: space-development
+description: "A rigorous filter for evaluating space manufacturing candidates based on whether Earth gravity creates absolute impossibility, order-of-magnitude degradation, or merely inconvenience"
+confidence: likely
+source: "Astra, microgravity manufacturing research February 2026"
+created: 2026-02-17
+depends_on:
+  - "microgravity eliminates convection sedimentation and container effects producing measurably superior materials across fiber optics pharmaceuticals and semiconductors"
+  - "the space manufacturing killer app sequence is pharmaceuticals now ZBLAN fiber in 3-5 years and bioprinted organs in 15-25 years each catalyzing the next tier of orbital infrastructure"
+---
+
+# The impossible on Earth test separates three tiers of microgravity advantage -- truly impossible products dramatically better products and products where terrestrial workarounds exist
+
+Not all microgravity manufacturing advantages are equal. A rigorous "impossible on Earth" test reveals three distinct tiers that determine which products justify orbital production. The distinction matters enormously for investment: truly impossible products have permanent competitive moats, while "better in space" products face constant risk that terrestrial engineering closes the gap.
+
+**Tier 1: Truly impossible (or effectively impossible) in gravity.**
+- *Thick-tissue bioprinting (>1cm):* Gravity collapses printed hydrogel structures before maturation. No terrestrial workaround exists. This is the strongest "impossible" claim in all of microgravity manufacturing.
+- *Large 3D colloidal photonic crystals:* FCC colloidal crystal self-assembly requires eliminating sedimentation at production scale. Magnetic levitation works only in microliters.
+- *Certain pharmaceutical polymorphs:* Some metastable crystal forms may only nucleate in convection-free microgravity.
+
+**Tier 2: Dramatically better in microgravity (10x+).**
+- *ZBLAN fiber optics:* Terrestrial achieves 0.7 dB/km; theoretical minimum is 0.001 dB/km. Space-made fiber approaching 0.01-0.1 dB/km would be 7-70x better.
+- *CdZT radiation detector crystals:* Measurably more homogeneous, perhaps 2-5x improvement.
+
+**Tier 3: Better but workarounds exist.**
+- *Bulk metallic glasses:* Electromagnetic levitation achieves containerless processing on Earth.
+- *Semiconductor single crystals:* Terrestrial methods (VGF, Czochralski) continue advancing.
+- *Stem cell expansion:* Rotating wall vessels and clinostats simulate some microgravity effects.
+- *Carbon nanotubes:* Minimal microgravity improvement; terrestrial methods advance faster.
+
+**Terrestrial simulation limits:** No platform provides sustained microgravity at production volumes. Drop towers give 2-10 seconds, parabolic flights 20-30 seconds, sounding rockets 3-13 minutes, magnetic levitation only microliters. For processes requiring hours to days at useful volumes, orbit remains the only option.
+
+## Evidence
+- Redwire BFF — thick-tissue bioprinting demonstrations on ISS
+- Flawless Photonics — 12 km ZBLAN on ISS
+- Terrestrial simulation platform comparison (drop tower, parabolic, sounding rocket, magnetic levitation)
+- Multiple material categories assessed against tier criteria
+
+## Challenges
+The boundary between Tier 1 and Tier 2 shifts as terrestrial techniques advance. Products currently in Tier 2 could move to Tier 3 if ground-based workarounds improve sufficiently.
+
+---
+
+Relevant Notes:
+- [[microgravity eliminates convection sedimentation and container effects producing measurably superior materials across fiber optics pharmaceuticals and semiconductors]] — the physics foundation this framework evaluates
+- [[orbital bioprinting enables tissue and organ fabrication impossible under gravity because structures collapse without scaffolding on Earth]] — the strongest Tier 1 example
+- [[ZBLAN fiber optics produced in microgravity could eliminate submarine cable repeaters extending signal range from 50 km to potentially 5000 km]] — the leading Tier 2 example
+
+Topics:
+- [[space exploration and development]]

domains/space-development/the self-sustaining space operations threshold requires closing three interdependent loops simultaneously -- power water and manufacturing.md

@@ -0,0 +1,38 @@
+---
+type: claim
+domain: space-development
+description: "You cannot extract water without power, run power without manufacturing replacement parts, or manufacture without water — the bootstrapping problem means early operations require massive Earth supply before any loop closes"
+confidence: likely
+source: "Astra, web research compilation February 2026"
+created: 2026-02-17
+depends_on:
+  - "power is the binding constraint on all space operations because every capability from ISRU to manufacturing to life support is power-limited"
+  - "water is the strategic keystone resource of the cislunar economy because it simultaneously serves as propellant life support radiation shielding and thermal management"
+---
+
+# The self-sustaining space operations threshold requires closing three interdependent loops simultaneously -- power water and manufacturing
+
+Self-sustaining space operations require closing three fundamental loops: power, water/consumables, and manufacturing/maintenance. Each enables the others in a circular dependency that creates a severe bootstrapping problem. You cannot extract water without power. You cannot run power systems indefinitely without manufacturing replacement parts. You cannot manufacture without water (for hydrogen, for cooling, for processing).
+
+The integration challenge is that all three loops must close simultaneously -- partial closure of one loop provides limited value without the others. A lunar base with nuclear power but no water extraction cannot produce propellant. Water extraction without manufacturing capability cannot maintain its own equipment. Manufacturing without local power and water reverts to depending on Earth resupply for energy and feedstock.
+
+By 2056, the likely state is partially closed loops: power and oxygen locally sourced from nuclear fission and regolith processing, water locally extracted from permanently shadowed craters, basic structural materials locally produced via sintering and 3D printing. But complex electronics, biological supplies, and advanced materials still come from Earth. True self-sufficiency -- where space infrastructure can maintain and expand itself without Earth resupply for basic operations -- is a 50-100 year project.
+
+The critical implication for investors: the path to self-sustaining operations is not a series of independent milestones but a system that must be built holistically, favoring platforms and companies whose capabilities span multiple loops.
+
+## Evidence
+- Circular dependency analysis of power/water/manufacturing systems
+- Current technology roadmaps for lunar ISRU, fission power, 3D printing
+- No demonstrated closure of any single loop at operational scale
+
+## Challenges
+Partial loop closure may provide enough value to sustain investment and operations even without full self-sufficiency. Earth resupply for high-value components may remain economically rational indefinitely.
+
+---
+
+Relevant Notes:
+- [[power is the binding constraint on all space operations because every capability from ISRU to manufacturing to life support is power-limited]] — power is the most fundamental of the three loops
+- [[water is the strategic keystone resource of the cislunar economy because it simultaneously serves as propellant life support radiation shielding and thermal management]] — water is the most versatile resource within the system
+
+Topics:
+- [[space exploration and development]]

domains/space-development/the small-sat dedicated launch market faces a structural paradox because SpaceX rideshare at 5000-6000 per kg undercuts most dedicated small launchers on price.md

@@ -0,0 +1,39 @@
+---
+type: claim
+domain: space-development
+description: "Dedicated small-sat launch sells orbit specificity and schedule control not cost, explaining why most startups have failed while Rocket Lab alone sustains operations through pivot to space systems"
+confidence: proven
+source: "Astra, web research compilation February 2026"
+created: 2026-02-17
+depends_on:
+  - "SpaceX vertical integration across launch broadband and manufacturing creates compounding cost advantages that no competitor can replicate piecemeal"
+  - "Rocket Lab pivot to space systems reveals that vertical component integration may be more defensible than launch in the emerging space economy"
+---
+
+# The small-sat dedicated launch market faces a structural paradox because SpaceX rideshare at 5000-6000 per kg undercuts most dedicated small launchers on price
+
+SpaceX's rideshare program (Transporter missions) offers launches at approximately $5,000-$6,000/kg -- cheaper than most dedicated small-sat launchers. Rocket Lab's Electron, the most successful small-sat rocket, costs approximately $7.5 million per launch for 300 kg to LEO, or roughly $25,000/kg. The value proposition of dedicated small-sat launch is orbit specificity and schedule control, not cost. This limits the addressable market.
+
+The failure cases are instructive. Virgin Orbit (LauncherOne, air-launched from a modified Boeing 747) went bankrupt in 2023 after achieving only 4 successful orbital launches. Astra achieved only 2 successes out of 7 orbital attempts before going private after stock collapse -- demonstrating that "move fast and break things" does not translate to rocket engineering.
+
+Rocket Lab is the sole success story precisely because it did not compete on cost alone. Its 21 successful Electron launches in 2025 (100% success rate) provided the reliability and schedule control that justified the price premium. More importantly, Rocket Lab recognized the structural limitation and is transitioning to a full space systems company: the $816 million SDA satellite contract and Neutron medium-lift rocket (13,000 kg to LEO, debut mid-2026) expand its addressable market. Electron's 80+ cumulative missions with 98% success rate make it the most prolific small-lift vehicle globally.
+
+Neutron targets 13,000 kg reusable capacity at $50 million, which would undercut Falcon 9 on both total cost and per-kg cost ($4,230/kg vs ~$6,000/kg). However, a January 2026 tank rupture during qualification testing added schedule risk. The space systems pivot makes the launch paradox moot for Rocket Lab specifically: with 70%+ of revenue now from Space Systems and a $1.3B SDA backlog, Electron functions as customer acquisition for the higher-margin systems business.
+
+## Evidence
+- SpaceX rideshare: ~$5,000-6,000/kg
+- Rocket Lab Electron: ~$25,000/kg but 98% success rate, 80+ missions
+- Virgin Orbit bankruptcy (2023), Astra stock collapse
+- Rocket Lab space systems revenue: 70%+ of total, $1.3B SDA backlog
+
+## Challenges
+Neutron's January 2026 tank rupture adds schedule risk. If SpaceX further reduces rideshare pricing, even orbit specificity may not justify the premium.
+
+---
+
+Relevant Notes:
+- [[SpaceX vertical integration across launch broadband and manufacturing creates compounding cost advantages that no competitor can replicate piecemeal]] — rideshare pricing is a byproduct of SpaceX's flywheel
+- [[Rocket Lab pivot to space systems reveals that vertical component integration may be more defensible than launch in the emerging space economy]] — Rocket Lab survives the paradox by using launch as customer acquisition
+
+Topics:
+- [[space exploration and development]]

entities/internet-finance/kalshi.md

@@ -54,6 +54,10 @@ CFTC-designated contract market for event-based trading. USD-denominated, KYC-re
 - **2026-03-19** — Ninth Circuit denied administrative stay motion, allowing Nevada to proceed with temporary restraining order that would exclude Kalshi from Nevada for at least two weeks pending preliminary injunction hearing
 - **2026-03-16** — Federal Reserve Board paper validates Kalshi prediction market accuracy, showing statistically significant improvement over Bloomberg consensus for CPI forecasting and perfect FOMC rate matching
 - **2026-03-23** — CEO Tarek Mansour co-founded [[5cc-capital]] with Polymarket CEO Shayne Coplan, creating dedicated VC fund for prediction market infrastructure
+- **2026-03-19** — Raised funding at $22 billion valuation
+- **2026-03-26** — Trading at $110M monthly revenue with $18.6B pre-IPO valuation
+- **2026-03-26** — Operating at $110M/month revenue with $18.6B pre-IPO valuation, establishing benchmark for prediction market valuations.
+- **2026-03-23** — CEO Tarek Mansour co-founded [[5cc-capital]] with Polymarket CEO, creating first prediction market sector VC fund
 ## Competitive Position
 - **Regulation-first**: Only CFTC-designated prediction market exchange. Institutional credibility.
 - **vs Polymarket**: Different market — Kalshi targets mainstream/institutional users who won't touch crypto. Polymarket targets crypto-native users who want permissionless market creation. Both grew massively post-2024 election.

entities/internet-finance/metadao.md

@@ -199,6 +199,10 @@ The futarchy governance protocol on Solana. Implements decision markets through
 - **2026-03-23** — [[metadao-omnibus-migration-proposal]] Active: 84% pass probability with $408K volume; integrates Squads v4.0 multisig
 - **2026-03-23** — [[metadao-migration-proposal-2026]] Active at 84% likelihood: Migration to new onchain DAO program and legal document updates, $408K traded
 - **2026-03-23** — [[metadao-gmu-futarchy-research-funding]] Active: Proposed funding for futarchy research at GMU with Robin Hanson
+- **2026-03-23** — [[metadao-gmu-futarchy-research-funding]] Proposed: Research funding for GMU futarchy program with Robin Hanson
+- **2026-03** — [[metadao-gmu-futarchy-research-funding]] Active: Proposed funding for futarchy research at George Mason University with Robin Hanson
+- **2024-03-31** — [[metadao-appoint-nallok-proph3t-benevolent-dictators]] Passed: Appointed Proph3t and Nallok as Benevolent Dictators for 3 months with authority over compensation, operations, and security (1015 META + 100k USDC for 7 months)
+- **2024-03-31** — [[metadao-appoint-nallok-proph3t-benevolent-dictators]] Passed: Temporary centralized leadership to address execution bottlenecks, 1015 META + 100k USDC compensation
 ## Key Decisions
 | Date | Proposal | Proposer | Category | Outcome |
 |------|----------|----------|----------|---------|

entities/internet-finance/polymarket.md

@@ -50,6 +50,11 @@ Crypto-native prediction market platform on Polygon. Users trade binary outcome
 - **2026-01-XX** — Partnered with Palantir and TWG AI to build surveillance system detecting suspicious trading and manipulation in sports prediction markets
 - **2026-01-XX** — Targeting $20B valuation alongside Kalshi as prediction market duopoly emerges
 - **2026-03-23** — CEO Shayne Coplan co-founded [[5cc-capital]] with Kalshi CEO Tarek Mansour, creating dedicated VC fund for prediction market infrastructure
+- **2026-03-07** — Reportedly seeking $20 billion valuation with confirmed $POLY token and airdrop plans
+- **2026-03-26** — Projected 30-day revenue jumped from $4.26M to $172M through fee expansion from ~0.02% to ~0.80% across Finance, Politics, Economics, Sports markets
+- **2026-03-26** — Projected revenue jump from $4.26M to $172M/month at 0.80% fees across expanded verticals. Projected valuation at $15.77B based on revenue multiples comparable to Kalshi.
+- **2026-03-26** — Projected 30-day revenue jumped from $4.26M to $172M through fee expansion from ~0.02% to ~0.80% across Finance, Politics, Economics, Sports categories
+- **2026-03-23** — CEO Shayne Coplan co-founded [[5cc-capital]] with Kalshi CEO, creating first prediction market sector VC fund
 ## Competitive Position
 - **#1 by volume** — leads Kalshi on 30-day volume ($8.7B vs $6.8B)
 - **Crypto-native**: USDC on Polygon, non-custodial, permissionless market creation

entities/internet-finance/ranger-finance.md

@@ -64,6 +64,8 @@ Perps aggregator and DEX aggregation platform on Solana/Hyperliquid. Three produ
 - **2026-03** — [[ranger-finance-liquidation-2026]] Passed (97%): Liquidation returning 5M USDC to holders at $0.78 book value
 - **2026-03-23** — [[ranger-finance-liquidation-2026]] Passed with 97% support: Liquidation returning 5M USDC to unlocked holders at $0.78 book value, IP returned to team
 - **2026-03-23** — [[ranger-finance-liquidation-march-2026]] Passed: Liquidation executed with 97% support, returning 5M USDC to holders at $0.78 book value
+- **2026-03-23** — [[ranger-finance-liquidation-2026]] Passed: Liquidation returned 5M USDC to holders at $0.78 book value with 97% support
+- **2026-03-23** — [[ranger-finance-liquidation-march-2026]] Passed: Liquidation approved with 97% support, returning 5M USDC to holders at $0.78 book value
 ## Significance for KB
 Ranger is THE test case for futarchy-governed enforcement. The system is working as designed: investors funded a project, the project underperformed relative to representations, the community used futarchy to force liquidation and treasury return. This is exactly what the "unruggable ICO" mechanism promises — and Ranger is the first live demonstration.
 

entities/internet-finance/superclaw.md

@@ -31,6 +31,9 @@ Infrastructure for economically autonomous AI agents. Provides agents with secur
 - **2026-03-04** — Futardio launch. $5.95M committed against $50K target.
 
 - **2026-03-04** — Launched futarchy-governed fundraise on Futardio, raising $5,950,859 against $50,000 target (119x oversubscription). Token: SUPER (mint: 5TbDn1dFEcUTJp69Fxnu5wbwNec6LmoK42Sr5mmNmeta). Completed 2026-03-05.
+- **2026-03-26** — [[superclaw-liquidation-proposal]] Active: Liquidation vote opened on MetaDAO platform
+- **2026-03-26** — [[superclaw-liquidation-proposal-2026-03]] Active: Team proposed full liquidation citing below-NAV trading and limited traction
+- **2026-03-26** — [[superclaw-liquidation-proposal]] Proposed: Team-initiated orderly liquidation due to below-NAV trading, 11% monthly treasury burn, and limited traction
 ## Relationship to KB
 - futardio — launched on Futardio platform
 - [[agents that raise capital via futarchy accelerate their own development because real investment outcomes create feedback loops that information-only agents lack]] — direct test case for AI agents raising capital via futarchy

entities/space-development/nasa-authorization-act-2026.md

@@ -0,0 +1,41 @@
+---
+type: entity
+entity_type: policy
+name: NASA Authorization Act of 2026
+domain: space-development
+status: pending
+---
+
+# NASA Authorization Act of 2026
+
+**Type:** Congressional legislation  
+**Status:** Passed Senate Commerce, Science & Transportation Committee (March 2026), awaiting full Senate vote  
+**Sponsors:** Sen. Ted Cruz (R-TX), bipartisan support  
+
+## Overview
+
+The NASA Authorization Act of 2026 extends ISS operational life to September 30, 2032 and introduces a mandatory overlap requirement: ISS must operate alongside at least one "fully operational" commercial space station for at least one full year, with full crews in space concurrently for at least 180 days.
+
+## Key Provisions
+
+1. **ISS Extension:** Extends ISS operational life from 2030 to September 30, 2032
+2. **Overlap Mandate:** Requires ISS to operate alongside at least one fully operational commercial station for minimum one year
+3. **Crew Continuity Requirement:** During overlap year, full crews must be in space concurrently for at least 180 days
+4. **Commercial Acceleration:** Directs NASA to accelerate commercial LEO destinations development
+5. **Strategic Rationale:** Cites "Tiangong scenario" (China's station as world's only inhabited station) as national security justification
+
+## Legislative Status
+
+- **March 5, 2026:** Passed Senate Commerce, Science & Transportation Committee with bipartisan support
+- **Pending:** Full Senate vote, House passage, Presidential signature
+- **Status:** Not yet law
+
+## Significance
+
+This bill is qualitatively different from prior ISS extension proposals. Previous extensions simply deferred the deadline. The overlap mandate creates a TRANSITION CONDITION: a commercial station must be operational and crewed before ISS can deorbit. This guarantees a government anchor tenant relationship during a defined operational window, creating a policy-engineered Gate 2 mechanism for commercial space stations.
+
+The 180-day concurrent crew requirement is operationally specific, requiring full crew capability, life support, docking, and communication systems — not just minimal presence.
+
+## Timeline
+
+- **2026-03-05** — Passed Senate Commerce, Science & Transportation Committee with bipartisan support

inbox/archive/2026-03-24-theseus-compute-infrastructure-research.md

@@ -0,0 +1,66 @@
+---
+type: source
+title: "AI Compute Infrastructure Research Sessions — ARM, NVIDIA, TSMC"
+author: "Theseus (research agent synthesis)"
+url: n/a
+date: 2026-03-24
+domain: ai-alignment
+intake_tier: research-task
+rationale: "Cory directed research into physical infrastructure enabling AI — ARM strategy, NVIDIA dominance/moat, TSMC supply chain chokepoints. Goal: understand compute governance implications for alignment."
+proposed_by: "Cory (via Theseus)"
+format: report
+status: processing
+processed_by: theseus
+tags: [compute-governance, semiconductors, supply-chain, power-constraints, inference-shift]
+notes: "Compiled from 5 research agent sessions. VERIFICATION NEEDED: (1) NVIDIA-Groq acquisition ($20B) — UNVERIFIED, (2) OpenAI-AMD 10% stake — UNVERIFIED, (3) Meta MTIA 4 generations at 6-month cadence — needs confirmation. Structural arguments high-confidence; specific numbers need manual verification."
+flagged_for_astra:
+  - "Power constraints on datacenter scaling — overlaps energy domain"
+  - "TSMC geographic diversification — manufacturing domain"
+  - "CoWoS packaging bottleneck — manufacturing domain"
+cross_domain_flags:
+  - "Rio: NVIDIA vertical integration follows attractor state pattern"
+  - "Leo: Taiwan concentration as civilizational single point of failure"
+  - "Astra: Nuclear revival for AI power, semiconductor supply chain"
+---
+
+# AI Compute Infrastructure Research — Synthesis
+
+Research compiled from 5 agent sessions on 2026-03-24. Three companies studied: ARM Holdings, NVIDIA, TSMC. Plus gap-filling research on compute governance discourse and power constraints.
+
+## Key Structural Findings
+
+### 1. Three chokepoints gate AI scaling
+CoWoS advanced packaging (TSMC near-monopoly, sold out through 2026), HBM memory (3-vendor oligopoly, all sold out through 2026), and power/electricity (5-10 year build cycles vs 1-2 year chip cycles). The bottleneck is NOT chip design.
+
+### 2. NVIDIA's moat is the full stack
+CUDA ecosystem (4M+ developers) + networking (Mellanox/InfiniBand) + full-rack solutions (GB200 NVL72) + packaging allocation (60%+ of CoWoS). Vertical integration following the "own the scarce complement" pattern.
+
+### 3. The inference shift redistributes AI capability
+Training ~33% of compute (2023) → inference projected ~66% by 2026. Training requires centralized NVIDIA clusters; inference runs on diverse, power-efficient hardware. Structurally favors distributed architectures.
+
+### 4. ARM's position is unique
+Doesn't compete with NVIDIA — provides the CPU substrate everyone builds on. Licensing model means revenue from every hyperscaler's custom chip program. Power efficiency advantage aligns with inference shift.
+
+### 5. TSMC is the single largest physical vulnerability
+~92% of advanced logic chips (7nm and below). Geographic diversification underway (Arizona 92% yield) but most advanced processes Taiwan-first through 2027-2028.
+
+### 6. Power may physically bound capability scaling
+Projected 8-9% of US electricity by 2030 for datacenters. Nuclear deals cover 2-3 GW near-term against 25-30 GW needed. Grid interconnection averages 5+ years.
+
+## Compute Governance Discourse Landscape
+
+| Area | Maturity | Key Sources |
+|------|----------|------------|
+| Compute governance | High | Heim/GovAI (Sastry et al. 2024), Shavit 2023 (compute monitoring) |
+| Compute trends | High | Epoch AI (Sevilla et al.), training compute doubling every 9-10 months |
+| Energy constraints | Medium | IEA, Goldman Sachs April 2024, de Vries 2023 in Joule |
+| Supply chain concentration | Medium-High | Chris Miller "Chip War", CSET Georgetown, RAND |
+| Inference shift + governance | LOW — genuine gap | Fragmented discourse, no systematic treatment |
+| Export controls as alignment | Medium | Gregory Allen CSIS, Heim/Fist "Secure Governable Chips" |
+
+## UNVERIFIED Claims (DO NOT extract without confirmation)
+- NVIDIA acquired Groq for $20B (Dec 2025)
+- OpenAI took 10% stake in AMD
+- Meta MTIA releasing 4 chip generations at 6-month cadence
+- ARM Graviton4 "168% higher token throughput" vs AMD EPYC
+- Specific market share percentages (vary by methodology)

inbox/archive/general/2026-03-24-tg-shared-unknown-metadao-appoint-nallok-proph3t.md

@@ -7,7 +7,7 @@ url: "https://git.livingip.xyz/teleo/teleo-codex/src/branch/main/decisions/inter
 date: 2026-03-24
 domain: internet-finance
 format: social-media
-status: enrichment
+status: processed
 proposed_by: "@m3taversal"
 contribution_type: source-submission
 tags: [telegram-shared, x-tweet]

inbox/archive/general/2026-03-26-polymarket-p2p-protocol-commitment-market.md

@@ -0,0 +1,78 @@
+---
+type: source
+title: "Polymarket: P2P Protocol Public Sale commitment prediction market — probability cascade to 99.8% on ICO launch day"
+author: "Polymarket"
+url: https://polymarket.com/event/total-commitments-for-the-p2p-protocol-public-sale-on-metadao
+date: 2026-03-26
+domain: internet-finance
+secondary_domains: []
+format: data
+status: processed
+priority: high
+tags: [polymarket, p2p-protocol, prediction-markets, futarchy, metadao, social-proof, manipulation]
+---
+
+## Content
+
+Polymarket prediction market: "Total commitments for the P2P Protocol public sale on MetaDAO"
+- Market opened: March 14, 2026
+- Market closes: July 1, 2026
+- 25 outcome tiers
+- Total trading volume: $1.7M
+
+Current probabilities as of March 26, 2026 (ICO launch day):
+
+| Outcome | Probability |
+|---------|------------|
+| >$1M | 100% |
+| >$2M | 100% |
+| >$3M | 100% |
+| >$4M | 100% |
+| >$6M | ~99.8% |
+| >$8M | 97% |
+| >$10M | 93% |
+| >$12M | 88% |
+| >$14M | 77% |
+| >$16M | 75% |
+| >$18M–$20M | 67% |
+| >$25M | 47% |
+| >$30M | 43% |
+| >$50M | 25% |
+| >$100M | 9% |
+
+Previous observed probability for >$6M: 77% (as of ~March 14 when archived in Session 11 research)
+
+Implied median prediction: ~$20-25M total commitments.
+
+**Context — Polymarket controversy (from prior research):**
+Session 11 (March 25) documented: traders in the Polymarket comment section alleged that the P2P team "openly participated" in the commitment prediction market. Polymarket rules prohibit market participants from influencing outcomes they're trading on. The allegation is unconfirmed, but structurally novel: team buying ">$6M" tranche to signal community confidence creates circular social proof (team buys → price increases → generates social proof → attracts real commitments → validates original purchase). Unlike governance market self-dealing, no arbitrage correction mechanism exists because the team is the most informed actor.
+
+**Actual ICO commitments as of March 26 (Futardio archive):** $6,852 committed of $6,000,000 target. ICO closes March 30. 4 days remaining.
+
+## Agent Notes
+
+**Why this matters:** The gap between $6,852 actual commitments and 99.8% Polymarket confidence for >$6M on ICO launch day is the most direct available test of the circular social proof mechanism hypothesized in Session 11. Either commitments surge in the final 4 days (mechanism worked correctly), or the market was inflated (manipulation thesis gains evidence).
+
+**What surprised me:** The probability shift from 77% to 99.8% on launch day itself. This implies either (a) massive new information arrived justifying the shift, or (b) the market is tracking actual commitment flow in near-real-time as traders observe MetaDAO ICO commitments and trade accordingly. The $1.7M trading volume on a single ICO prediction market is substantial — this is a highly liquid market for a relatively small ICO.
+
+**What I expected but didn't find:** Evidence that the team's alleged Polymarket participation has been confirmed or denied by Polymarket. The platform hasn't issued a public statement. The market continues operating normally despite the controversy.
+
+**KB connections:**
+- prediction markets show superior accuracy over polls and expert forecasts (Belief #1 evidence — is this market showing superior accuracy or being manipulated?)
+- FairScale's manipulation attempt by team demonstrates futarchy's self-correcting mechanism (contrast case — FairScale governance market had an arbitrage correction; Polymarket social proof doesn't)
+- Session 11 CC2: Prediction market participation by issuers in own ICO commitment markets creates circular social proof with no arbitrage correction
+
+**Extraction hints:**
+1. The circular social proof mechanism (CC2 from Session 11) — the mechanism claim is novel and KB-ready
+2. Evidence for/against: if ICO raises >$6M by March 30, Polymarket was directionally correct (doesn't prove manipulation was absent); if ICO fails, Polymarket was wrong despite 99.8% confidence (strong evidence of manipulation)
+3. The $1.7M trading volume on this prediction market is itself a data point about prediction market liquidity for ICO social proof purposes
+
+**Context:** Polymarket is the largest prediction market platform by volume. The P2P.me ICO is a MetaDAO futarchy-governed public sale on Solana. The prediction market and the ICO are separate mechanisms, but in this case the prediction market output (commitment probability) may be feeding back into ICO commitment decisions.
+
+## Curator Notes (structured handoff for extractor)
+
+PRIMARY CONNECTION: Session 11 CC2 — "Prediction market participation by project issuers in their own ICO commitment markets creates circular social proof with no arbitrage correction"
+
+WHY ARCHIVED: The probability shift from 77% to 99.8% on launch day combined with only $6,852 actual commitments creates a testable tension. This is the most direct current evidence for or against the circular social proof mechanism. ALSO: the raw probability cascade data is the primary input for any claim about Polymarket's accuracy on futarchy ICO markets.
+
+EXTRACTION HINT: Wait for ICO close (March 30) and Polymarket resolution (July 1) before extracting the final claim. The mechanism claim can be extracted now; the empirical confirmation/disconfirmation must wait. Flag as "extract after resolution" for the highest-confidence version.

inbox/archive/general/2026-03-26-tg-shared-sjdedic-2037143546256384412-s-46.md

@@ -0,0 +1,43 @@
+---
+type: source
+source_type: x-tweet
+title: "@sjdedic — shared via Telegram by @m3taversal"
+author: "@sjdedic"
+url: "https://x.com/sjdedic/status/2037143546256384412?s=46"
+date: 2026-03-26
+domain: internet-finance
+format: social-media
+status: processed
+proposed_by: "@m3taversal"
+contribution_type: source-submission
+tags: [telegram-shared, x-tweet]
+processed_by: rio
+processed_date: 2026-03-26
+extraction_model: "anthropic/claude-sonnet-4.5"
+extraction_notes: "LLM returned 0 claims, 0 rejected by validator"
+---
+
+# @sjdedic — Tweet/Thread
+
+Shared by @m3taversal via Telegram.
+Source URL: https://x.com/sjdedic/status/2037143546256384412?s=46
+
+## Content
+
+I literally have 0 coding experience and had never worked with Dune dashboards before.
+
+It always annoyed me having to rely on other people’s dashboards and never finding the exact data I was looking for, so I figured I’d try building one myself with AI.
+
+With Claude’s help, it took me less than 1.5 hours, and most of that was just understanding how Dune works. The next one would probably take under an hour.
+
+I remember some of our portfolio companies paying thousands of $$ for these and waiting weeks for them to go live.
+
+Even though this trend has been obvious for a while, this really made it click for me just how much AI is eroding the moat and defensibility of developers, and how easy it is now for a complete beginner like me.
+
+Devs are cooked.
+
+
+## Key Facts
+- A non-developer built a Dune dashboard in under 1.5 hours using Claude AI in March 2026
+- Portfolio companies previously paid thousands of dollars and waited weeks for similar Dune dashboards
+- The author estimates the next dashboard would take under 1 hour

inbox/archive/general/2026-03-26-tg-shared-unknown.md

@@ -0,0 +1,23 @@
+---
+type: source
+source_type: x-tweet
+title: "unknown — shared via Telegram by @m3taversal"
+author: "unknown"
+url: "https://futarchy.info/"
+date: 2026-03-26
+domain: internet-finance
+format: social-media
+status: processed
+proposed_by: "@m3taversal"
+contribution_type: source-submission
+tags: ['telegram-shared', 'x-tweet', 'futarchy', 'governance']
+---
+
+# unknown — Tweet/Thread
+
+Shared by @m3taversal via Telegram.
+Source URL: https://futarchy.info/
+
+## Content
+
+Futarchy Research Library | MetaDAO Knowledge Center Toggle theme Research Digital Library Futarchy Knowledge Center A comprehensive collection of research, analysis, and insights on prediction markets, futarchy governance, and the MetaDAO ecosystem—from foundational papers to cutting-edge developments. Filter Resources Academic Papers 3 Articles & Analysis 125 Podcasts 16 Videos 24 News Coverage 7 Loading resources...

inbox/archive/general/2026-03-26-tg-shared-wsj-2037146683960676492-s-46.md

@@ -0,0 +1,33 @@
+---
+type: source
+source_type: x-tweet
+title: "@wsj — shared via Telegram by @m3taversal"
+author: "@wsj"
+url: "https://x.com/wsj/status/2037146683960676492?s=46"
+date: 2026-03-26
+domain: internet-finance
+format: social-media
+status: processed
+proposed_by: "@m3taversal"
+contribution_type: source-submission
+tags: ['telegram-shared', 'x-tweet']
+processed_by: rio
+processed_date: 2026-03-26
+extraction_model: "anthropic/claude-sonnet-4.5"
+extraction_notes: "LLM returned 0 claims, 0 rejected by validator"
+---
+
+# @wsj — Tweet/Thread
+
+Shared by @m3taversal via Telegram.
+Source URL: https://x.com/wsj/status/2037146683960676492?s=46
+
+## Content
+
+Exclusive: OpenAI is backing a new AI startup that aims to build software allowing so-called AI “agents” to communicate and solve complex problems in industries such as finance and biotech https://t.co/qLRGZUguvk
+
+
+## Key Facts
+- OpenAI is backing a new AI startup focused on agent-to-agent communication software
+- The startup aims to enable AI agents to solve complex problems in finance and biotech industries
+- WSJ published this as an exclusive report on March 26, 2026

inbox/archive/general/2026-03-26-tg-source-m3taversal-superclaw-liquidation-proposal-shared-by-m3tavers.md

@@ -0,0 +1,26 @@
+---
+type: source
+source_type: telegram-contribution
+title: "Source from @m3taversal — Superclaw liquidation proposal shared by @m3taversal: https://www.metadao.fi/pro"
+author: "@m3taversal"
+date: 2026-03-26
+domain: internet-finance
+format: contribution
+status: processed
+proposed_by: "@m3taversal"
+contribution_type: source-submission
+tags: ['telegram-contribution', 'inline-source', 'futarchy', 'governance', 'market-analysis', 'crypto-infra']
+---
+
+# Source: Superclaw liquidation proposal shared by @m3taversal: https://www.metadao.fi/projects/superclaw/prop
+
+Contributed by @m3taversal in Telegram chat.
+Flagged by Rio as relevant source material.
+
+## Verbatim User Message
+
+@FutAIrdBot what do you think of this decision market that should go live soon? Liquidation Proposal for $SUPER https://www.metadao.fi/projects/superclaw/proposal/FZNt29qdEhvnJWswpoWvvAFV5TBhnpBzUaFced3ZFx1X do you have it in your knowledge base? whats the current price of $SUPER vs NAV
+
+## Rio's Context
+
+Superclaw liquidation proposal shared by @m3taversal: https://www.metadao.fi/projects/superclaw/proposal/FZNt29qdEhvnJWswpoWvvAFV5TBhnpBzUaFced3ZFx1X — liquidation decision market for $SUPER on MetaDAO's futarchy platform.

inbox/archive/general/2026-03-26-tg-source-m3taversal-superclaw-super-liquidation-proposal-full-text-sh.md

@@ -0,0 +1,50 @@
+---
+type: source
+source_type: telegram-contribution
+title: "Source from @m3taversal — Superclaw $SUPER liquidation proposal full text shared by @m3taversal. Summary: "
+author: "@m3taversal"
+date: 2026-03-26
+domain: internet-finance
+format: contribution
+status: processed
+proposed_by: "@m3taversal"
+contribution_type: source-submission
+tags: ['telegram-contribution', 'inline-source', 'futarchy', 'ownership-coins', 'defi', 'governance', 'market-analysis', 'crypto-infra']
+---
+
+# Source: Superclaw $SUPER liquidation proposal full text shared by @m3taversal. Summary: Team-initiated order
+
+Contributed by @m3taversal in Telegram chat.
+Flagged by Rio as relevant source material.
+
+## Verbatim User Message
+
+here's the proposal from the link I previously sent. 1. Summary
+Since the ICO concluded, it has become increasingly clear that the best path forward is a full and orderly liquidation of the $SUPER treasury.
+
+At this time:
+
+$SUPER is trading below NAV
+An additional month of operating spend would reduce NAV by approximately 11%
+Traction has remained limited
+Catalysts to date have not meaningfully changed market perception or business momentum
+Given these circumstances, we believe the most responsible course of action is to preserve remaining value and return capital to tokenholders rather than continue funding operations with uncertain prospects.
+
+If passed, this proposal would do the following:
+
+Remove all $SUPER / USDC liquidity from the Futarchy AMM
+Send all treasury USDC to a liquidation contract to be redeemed pro-rata excluding unissued and protocol owned tokens.
+Wind down the onchain treasury associated with the project
+Return any non-treasury assets, including intellectual property and related operating assets, to the appropriate original entity and/or the current contributors of Superclaw.
+2. Motivation
+The motivation for this proposal is straightforward: preservation of tokenholder value.
+
+At present, $SUPER is trading below NAV. This creates a situation where continued spending is difficult to justify, particularly when each additional month of burn materially erodes the recoverable value of the treasury. Based on current estimates, one more month of monthly spend would reduce NAV by approximately 11%.
+
+At the same time, traction remains limited. Despite multiple attempts to create momentum through catalysts, the market response has been muted and there is little evidence so far that these efforts are translating into sustained growth, stronger fundamentals, or improved confidence from tokenholders.
+
+This proposal is not based on allegations of misconduct, fraud, or bad faith. Rather, it reflects a practical assessment of current conditions. Where a project
+
+## Rio's Context
+
+Superclaw $SUPER liquidation proposal full text shared by @m3taversal. Summary: Team-initiated orderly liquidation. SUPER trading below NAV, 11% monthly NAV burn, limited traction, catalysts haven't moved the needle. Proposal would remove AMM liquidity, send treasury USDC to liquidation contract for pro-rata redemption (excluding unissued and protocol-owned tokens), wind down treasury, return IP to original contributors. Not based on misconduct allegations, framed as value preservation. Proposal account: FZNt29qdEhvnJWswpoWvvAFV5TBhnpBzUaFced3ZFx1X on metadao.fi.

inbox/archive/general/2026-03-26-x-research-wsj-ai-sentiment.md

@@ -0,0 +1,59 @@
+---
+type: source
+source_type: x-research
+title: "X research: WSJ AI sentiment"
+date: 2026-03-26
+domain: internet-finance
+status: processed
+proposed_by: "@m3taversal"
+contribution_type: research-direction
+---
+
+@TheDuranReal: WSJ: Trump's AI and Crypto Czar
+“This is a good time to declare victory and get out.”
+
+@DavidSacks called for an end to the war in Iran: “We should try to find the offramp."
+
+MAGA anti-war sentiment i
+@CryptoThreadsX: • Mark Zuckerberg creates AI agent to streamline Meta management, WSJ reports.
+
+• Japanese stocks fall sharply as Hormuz Strait tensions drive risk-off sentiment.
+
+• #Gold falls below $4,350/oz, erasi
+@tradedots: $META: Court verdict + AI workforce push
+
+Sentiment: Negative
+
+'''WSJ reported a New Mexico case imposing a $375M penalty tied to claims Meta harmed children by enabling predation, while PYMNTS noted 
+@JChengWSJ: @QinSherry @Tracyyyqu Even though the program’s popularity could well be a fad, it is lifting investor sentiment toward the sector, Morningstar analyst Ivan Su said. Sheng Fu, CEO of Beijing-based Che
+@matthew_crvisua: Hope you caught this?
+
+CFOs are now confirming the AI payoff is real. Major shift in sentiment from the WSJ's CFO Summit.
+
+Options flow anticipated for $NOW. https://t.co/El7tjP6nMh
+@cninsight: "Thousands of U.S. Marines to Arrive in the Middle East on Friday - WSJ"
+
+Info⚪(Sentiment Analysis 🤖)
+
+Critical 🚨(Severity Level 🤖)
+
+For AI Summary & More Details 👇
+https://t.co/BE62vwyOKT
+
+$BTC
+@grok: @dontreadnyc @rohindhar rohindhar's profile (SF agent/investor): Posts show market sentiment flipped positive by early 2026—bidding wars returning (WSJ Mar 15), $2M+ over-ask deals, $4.6M off-market s
+@CooperRiveraQ8: Could a WSJ correction signal a momentum shift for $AIMD?
+
+• Correction issued for "AI Learns to Smell" article.
+• Misspelled name (Lu vs. Liu) may erode narrative confidence.
+• Monitor trading volume
+@charles_mostrea: Tracking cautious market sentiment and risk management flows around AI surveillance devices.
+
+Highlighted by the WSJ's report on backlash against always-watching tech.
+
+Implications for key players $A
+@benjamin_h_lens: Is the AI surveillance backlash a market inflection point? 📉
+
+- $ANTHROPIC, $QCOM, $META face scrutiny over "always-on" devices.
+- WSJ details rising public & regulatory pushback.
+- Risk managemen

inbox/archive/general/2026-03-27-vast-haven1-delay-2027-fundraise.md

@@ -0,0 +1,39 @@
+---
+type: source
+title: "Vast delays Haven-1 to Q1 2027, raises $500M — technical readiness as post-Gate-1 binding constraint"
+author: "Payload Space / Vast Space (@vastspace)"
+url: https://payloadspace.com/vast-delays-haven-1-launch-to-2027/
+date: 2026-03-05
+domain: space-development
+secondary_domains: []
+format: article
+status: processed
+priority: high
+tags: [haven-1, vast, commercial-space-station, gate-2, launch-delay, fundraising, iss-transition]
+---
+
+## Content
+
+Vast has delayed Haven-1's launch from mid-2026 to Q1 2027 (approximately 6-8 month slip). The company raised $500M on March 5, 2026 ($300M equity + $200M debt). Haven Demo pathfinder mission successfully completed controlled deorbit on February 4, 2026. Vast describes itself as ~40% of the way to a continuously crewed space station.
+
+The delay is characterized as a technical development issue ("zero-to-one development; gaining more data with each milestone enables progressively more precise timelines"), not a cost or funding issue. Commercial demand pipeline includes negotiating crew slots with private individuals and nation-states (Europe, Japan, Middle East, Asia). NASA anchor tenant relationship remains the primary revenue foundation.
+
+Launch vehicle: SpaceX Falcon 9 (booked).
+
+## Agent Notes
+**Why this matters:** Haven-1 is the most advanced commercial station and the only realistic candidate to meet the ISS transition window. Its delay to Q1 2027 is the first direct evidence that for post-Gate-1 sectors, the binding constraint is technical readiness, not launch cost. Falcon 9 is available and affordable for government-funded crew transport — the bottleneck is not "can we get to orbit" but "is the hardware ready."
+
+**What surprised me:** The combination of 6-8 month delay AND $500M fundraise (simultaneously) is counterintuitive. Normally a delay signals trouble; here, capital markets are clearly confident in the team and thesis. This suggests the delay is a technical maturation event, not a distress signal. Strong contrast with weaker commercial station programs (Orbital Reef dissolution, Starlab uncertainty).
+
+**What I expected but didn't find:** A specific technical explanation for the delay (what subsystem caused the slip). Vast characterizes it generically as "zero-to-one development." This is honest but not diagnostic.
+
+**KB connections:** Two-gate model (Pattern 10) — Haven-1 has cleared Gate 1 but Gate 2 formation is still undemonstrated. The $500M fundraise implies investor expectation that Gate 2 will form, but it doesn't constitute Gate 2 itself. Pattern 2 (institutional timelines slipping) — another program slip. Pattern 6 (thesis hedging by first-movers) — Vast's demand pipeline (nation-states, private individuals) suggests diversifying off NASA dependence.
+
+**Extraction hints:** Primary claim candidate: "Haven-1's delay to Q1 2027 demonstrates that post-Gate-1 commercial space sectors are constrained by technical readiness, not launch cost." Secondary: "Haven-1 is the only realistic commercial station candidate for the ISS overlap window under the NASA Authorization Act of 2026." Tertiary: "$500M fundraise amid delay signals investor belief in Gate 2 formation independent of near-term revenue."
+
+**Context:** Haven-1 Q1 2027 launch + ~4 years to 2031 ISS deorbit. Under the ISS overlap bill (if passed), commercial station must operate alongside ISS for 1 full year with 180 days of concurrent crew. Haven-1 would need to be operational and crewed by late 2029-2030 to be the designated overlap partner. This is extremely tight given Q1 2027 launch.
+
+## Curator Notes
+PRIMARY CONNECTION: Two-gate sector activation model (gate 2 formation dynamics)
+WHY ARCHIVED: First direct evidence that technical readiness is the operative constraint for post-Gate-1 commercial stations — qualifies Belief #1 (launch cost as keystone) without falsifying it
+EXTRACTION HINT: Extract the technical readiness claim AND the fundraise-despite-delay signal separately — they're different claims that together tell a coherent story about post-Gate-1 dynamics

inbox/archive/internet-finance/2026-03-23-5cc-capital-polymarket-kalshi-founders-vc-fund.md

@@ -0,0 +1,66 @@
+---
+type: source
+title: "5c(c) Capital: Polymarket CEO + Kalshi CEO launch VC fund investing in prediction market companies — institutional adoption signal"
+author: "Various (TechCrunch, Coindesk coverage)"
+url: https://polymarket.com
+date: 2026-03-23
+domain: internet-finance
+secondary_domains: []
+format: announcement
+status: unprocessed
+priority: medium
+tags: [prediction-markets, polymarket, kalshi, venture-capital, institutional-adoption, cftc, regulation]
+---
+
+## Content
+
+5c(c) Capital announced March 23, 2026. New VC fund:
+- **Founders:** Shayne Coplan (Polymarket CEO) + Tarek Mansour (Kalshi CEO)
+- **Focus:** Prediction market companies and infrastructure
+- **Significance:** The two largest US prediction market platforms' founders forming a capital vehicle signals the sector has matured to the point of self-sustaining capital formation
+
+Also March 2026: **Truth Predict** — Trump Media & Technology Group (owner of Truth Social) entering the prediction market space. Mainstream political adoption of prediction market product category.
+
+**The institutional adoption pattern building across 2025-2026:**
+- GENIUS Act signed (July 2025) — stablecoin regulatory framework
+- CLARITY Act in Senate — token classification
+- Polymarket received CFTC approval via $112M acquisition (context from Session 1)
+- Kalshi allowed to list federal election markets following court ruling
+- 5c(c) Capital: prediction market sector founders as capital allocators (March 2026)
+- Truth Predict: mainstream political brand entering space (March 2026)
+
+**The regulatory ambiguity this creates:**
+Institutional prediction market adoption (Polymarket, Kalshi, 5c(c) Capital) strengthens the "markets beat votes" legitimacy thesis (Belief #1). These platforms provide empirical evidence at scale that prediction markets function as designed. However, this creates a classification problem for futarchy specifically:
+- Polymarket/Kalshi focus: event prediction (elections, sports, economic indicators)
+- Futarchy focus: governance decision markets
+- The more mainstream event prediction markets become, the harder it is to distinguish futarchy governance markets as categorically different
+- The CFTC ANPRM will define the regulatory perimeter — if 5c(c) Capital + Truth Predict shape that perimeter around event prediction, futarchy governance markets may be excluded or lumped into a less favorable category
+
+**5c(c) Capital ANPRM angle:** Both Coplan and Mansour have direct CFTC comment incentive. Their interests (protecting event prediction platforms from gaming classification) are partially aligned with futarchy (protecting governance markets from gaming classification) — but they may NOT advocate for governance market distinctions if that complicates their simpler regulatory ask.
+
+## Agent Notes
+
+**Why this matters:** The prediction market sector is going through a legitimization phase. Every mainstream adoption signal (5c(c) Capital, Truth Predict, CFTC ANPRM attention) increases the category's credibility — which ultimately helps futarchy's legitimacy case. But the pathway to legitimacy that event prediction markets are building may crowd out futarchy's distinct narrative.
+
+**What surprised me:** The timing: 5c(c) Capital announced 10 days before the CFTC ANPRM comment deadline. Whether intentional or coincidental, the founders of the two largest prediction market platforms have maximum incentive and credibility to shape CFTC rulemaking. If they focus only on event prediction, futarchy has no institutional advocates in the process.
+
+**What I expected but didn't find:** Any statement from 5c(c) Capital or Truth Predict about DAO governance applications or futarchy. Complete silence on governance market use cases.
+
+**KB connections:**
+- prediction markets show superior accuracy over polls and expert forecasts — Polymarket/Kalshi empirical track record underpins this claim; 5c(c) Capital's formation is a secondary legitimacy signal
+- legacy financial intermediation is the rent-extraction incumbent (Belief #5) — prediction market VC formation is a capital formation attractor state
+- CFTC ANPRM (this session) — 5c(c) Capital + Truth Predict are the key players who could shape the rulemaking
+
+**Extraction hints:**
+1. **Institutional prediction market adoption acceleration claim:** "Prediction market sector legitimization accelerated in 2026 with 5c(c) Capital (Polymarket + Kalshi founders) and Truth Predict (Trump Media) — institutional adoption validates the product category while complicating futarchy's distinct regulatory narrative"
+2. This source is primarily context for the CFTC ANPRM regulatory risk claim — it explains WHO will likely comment and WHOSE interests will shape the rulemaking
+
+**Context:** Prediction market industry is 3-4 years into mainstream adoption curve. Polymarket and Kalshi are the dominant US platforms. 5c(c) Capital represents the sector's founders reinvesting in the ecosystem — a strong maturity signal.
+
+## Curator Notes (structured handoff for extractor)
+
+PRIMARY CONNECTION: CFTC ANPRM regulatory risk — 5c(c) Capital's formation explains why futarchy may not get distinct regulatory treatment (its advocates are absent while event prediction market advocates are active)
+
+WHY ARCHIVED: Context for the advocacy gap claim. Also strengthens the institutional adoption pattern that underlies Belief #1's legitimacy layer. Medium priority — this is context, not primary evidence.
+
+EXTRACTION HINT: Don't extract independently. Use as supporting evidence for the CFTC ANPRM claims and the institutional adoption pattern. The key insight is the divergence between event prediction adoption and governance market adoption.

inbox/archive/internet-finance/2026-03-26-cftc-anprm-prediction-markets-federal-register.md

@@ -0,0 +1,90 @@
+---
+type: source
+title: "CFTC ANPRM on Prediction Markets — 40+ questions, blockchain-native markets covered, futarchy governance markets absent, April 30 comment deadline"
+author: "Commodity Futures Trading Commission"
+url: https://www.cftc.gov/PressRoom/PressReleases/9194-26
+date: 2026-03-12
+domain: internet-finance
+secondary_domains: []
+format: regulatory
+status: processed
+priority: high
+tags: [cftc, regulation, prediction-markets, futarchy, governance, anprm, legal, dcm]
+---
+
+## Content
+
+CFTC issued an Advanced Notice of Proposed Rulemaking (ANPRM) on March 12, 2026 (published in Federal Register March 16, 2026).
+
+**Comment deadline: April 30, 2026** (45 days from Federal Register publication)
+
+Chairman Michael Selig framed this as "promoting responsible innovation" while establishing CFTC's exclusive jurisdiction over prediction markets.
+
+**The 40+ questions cover:**
+- Public interest considerations for event contracts
+- DCM (Designated Contract Market) Core Principles compliance
+- Market manipulation and insider trading susceptibility
+- Settlement methodology and data integrity
+- Information asymmetry between market participants
+- Blockchain-based prediction markets (specifically mentioned)
+- Position limits, margin trading rules
+
+**What the ANPRM explicitly covers:**
+- Blockchain-based and decentralized prediction markets
+- Event contracts generally (elections, sports, weather, economic indicators)
+- Market structure for prediction market DCMs
+
+**What the ANPRM does NOT cover (the governance gap):**
+- No questions about how to classify event contracts used for corporate governance decisions
+- No distinction between governance decision markets (resolve endogenous decisions) and event prediction markets (resolve exogenous events)
+- No mention of DAO treasury governance using conditional markets
+- No mention of futarchy, conviction voting, or any other on-chain governance mechanism
+- No framework for prediction markets that serve as substitute voting mechanisms
+
+**Law firm analyses confirming the gap:**
+- Sidley Austin: prediction market overview, no futarchy mention
+- Norton Rose Fulbright: "CFTC Advances Regulatory Framework for Prediction Markets," no futarchy mention
+- Davis Wright Tremaine: "CFTC Advisory and ANPRM on Prediction Markets," no futarchy mention
+- Prokopiev Law: detailed question summary, no futarchy mention
+
+**Institutional context:**
+- 5c(c) Capital (announced March 23, 2026): New VC fund backed by Polymarket CEO Shayne Coplan + Kalshi CEO Tarek Mansour, investing in prediction market companies. These founders have strong ANPRM comment incentive but their interests may not align with futarchy governance markets.
+- Truth Predict (Trump Media, March 2026): Trump's media company entering prediction markets — mainstream political adoption; potential political dimension to CFTC rulemaking.
+
+**Regulatory risk without futarchy-specific comments:**
+Without comments distinguishing governance decision markets from entertainment/sports prediction, the rulemaking default is the least-favorable analogy: gaming classification. This is the primary regulatory threat identified in Sessions 2-3. The gaming law preemption gap in the CLARITY Act (identified Session 2) means futarchy governance markets need an affirmative regulatory home, not just the absence of a negative one.
+
+**The key argument that NEEDS to be made (for any comment submission):**
+Governance decision markets differ from event prediction contracts in two structural ways:
+1. They resolve ENDOGENOUS decisions (the DAO decides what to do), not EXOGENOUS events (the world decides what happened)
+2. They coordinate JOINT OWNERSHIP decisions (the decision IS the outcome), not information markets (the outcome informs decisions made elsewhere)
+This structural difference supports different regulatory treatment — not securities, not gaming, but a category of collective decision-making infrastructure.
+
+## Agent Notes
+
+**Why this matters:** The CFTC ANPRM is the most consequential near-term regulatory event for futarchy governance mechanisms. The comment window (April 30) is the only near-term opportunity to influence whether futarchy governance markets get classified under gaming law (worst case) or receive a distinct regulatory framework. No futarchy advocate has filed as of March 26.
+
+**What surprised me:** The complete absence of futarchy from four major law firm analyses. These are sophisticated regulatory shops with prediction market clients. If they don't see futarchy as categorically different from Polymarket, the CFTC certainly won't distinguish it by default. The classification risk is larger than I previously assessed.
+
+**What I expected but didn't find:** Any filing by MetaDAO, Futardio, or any futarchy-adjacent entity. The 36+ days since ANPRM publication have passed with zero futarchy-specific comment activity.
+
+**KB connections:**
+- DAO Reports rejected voting as active management — prediction markets must prove mechanistically different (Belief #6 core tension)
+- Ooki DAO shows entity wrapping is non-negotiable — regulatory context for DAO structure
+- CFTC prediction market jurisdiction is expanding and state-federal tension is heading toward Supreme Court (from Session 2)
+- The CLARITY Act gap identified in Session 2: gaming law preemption not included
+
+**Extraction hints:**
+1. **CFTC default classification risk claim:** "CFTC ANPRM contains no questions distinguishing futarchy governance markets from event prediction contracts — default rulemaking will apply gaming classification to DAO governance mechanisms absent futarchy-specific advocacy"
+2. **Governance market structural distinction:** "Futarchy governance decision markets differ from prediction event contracts in that they resolve endogenous organizational decisions rather than exogenous events — this structural difference should support distinct CFTC regulatory treatment"
+3. **Advocacy gap claim:** "No futarchy or DAO governance advocate has filed CFTC ANPRM comments as of April 30 deadline — institutional prediction market founders (5c(c) Capital, Truth Predict) have comment incentive but divergent interests from governance market operators"
+
+**Context:** This is the most important near-term regulatory development in Rio's domain. The April 30 deadline is a firm cutoff — post-deadline advocacy is possible but far less influential than comment period submissions.
+
+## Curator Notes (structured handoff for extractor)
+
+PRIMARY CONNECTION: DAO Reports rejected voting as active management — prediction markets must prove mechanistically different (Belief #6 — this ANPRM is the real-world test of whether that proof gets made)
+
+WHY ARCHIVED: The CFTC ANPRM is the primary regulatory threat to futarchy governance markets. The comment deadline creates urgency. Three extractable claims: (1) default classification risk, (2) structural distinction argument, (3) advocacy gap.
+
+EXTRACTION HINT: Extract claim #1 (default classification risk) as highest priority — it's a time-sensitive factual claim that the KB should carry. Claim #2 (structural distinction) is more analytical and supports the regulatory positioning claims in the Living Capital domain. Claim #3 (advocacy gap) is tactical intelligence — relevant to Living Capital regulatory strategy.

inbox/archive/internet-finance/2026-03-26-pine-analytics-p2p-protocol-ico-analysis.md

@@ -0,0 +1,109 @@
+---
+type: source
+title: "Pine Analytics: P2P.me ICO Analysis — 'Cautious' rating, 182x gross profit multiple, performance-gated team vesting breakdown"
+author: "Pine Analytics (Substack)"
+url: https://pineanalytics.substack.com/p/p2p-metadao-ico-analysis
+date: 2026-03-15
+domain: internet-finance
+secondary_domains: []
+format: article
+status: processed
+priority: high
+tags: [p2p-protocol, metadao, ico, tokenomics, ownership-alignment, vesting, valuation]
+---
+
+## Content
+
+Pine Analytics published a comprehensive ICO analysis of P2P Protocol (P2P.me) on March 15, 2026, rating the project "CAUTIOUS" (not AVOID, not STRONG BUY).
+
+**Product summary:**
+- Non-custodial USDC-to-fiat on/off-ramp built on Base blockchain
+- Uses zk-KYC (zero-knowledge identity via Reclaim Protocol)
+- Live local payment rails: UPI (India), PIX (Brazil), QRIS (Indonesia), ARS (Argentina)
+- On-chain matching: users assigned to merchants based on staked USDC
+- Settlement, disputes, and fee routing all execute on-chain
+- Fraud rate: fewer than 1 in 1,000 transactions via Proof-of-Credibility system (ZK-TLS social verification + Reputation Points)
+
+**Business metrics:**
+- $3.95M peak monthly volume (February 2026) / $4M per Futardio archive
+- $327.4K cumulative revenue (per Pine) / $578K annual run rate (per Futardio archive — implies recent acceleration)
+- $34K-$47K monthly revenue range (Pine) → consistent with $578K annualized
+- 27% average month-on-month growth over 16 months
+- $175K/month burn rate (25 staff)
+- Annual gross profit ~$82K (Pine) / "20% of revenue as gross profit to treasury from June 2026" (Futardio archive)
+- 23,000+ registered users; 78% concentrated in India
+
+**Valuation:**
+- ICO price: $0.60/token
+- FDV: $15.5M
+- Pine assessment: **182x multiple on annual gross profit** — "buying optionality, not current business"
+
+**Tokenomics (the mechanism design centerpiece):**
+- Total supply: 25.8M tokens
+- ICO sale: 10M tokens at $0.60 = $6M target
+- Liquidity allocation: 2.9M tokens at TGE (11% of supply)
+- Total liquid at TGE: 12.9M tokens = 50% of supply — highest float in MetaDAO ICO history
+
+**Team vesting (performance-gated — the key design innovation):**
+- 7.74M tokens (30% of supply)
+- 12-month cliff
+- ZERO benefit below 2x ICO price ($1.20)
+- Five equal tranches at: 2x / 4x / 8x / 16x / 32x ICO price
+- Price measured via 3-month TWAP
+- Team receives nothing unless community value is created first
+
+**Investor vesting:**
+- 5.16M tokens (20% of supply)
+- Fully locked 12 months
+- Five equal unlocks at months 12, 15, 18, 21, 24 (fully unlocked month 24)
+- No performance gate — only time-based
+
+**Prior investors revealed (from Futardio archive):**
+- Reclaim Protocol: 3.45% supply, $80K at seed (March 2023)
+- Alliance DAO: 4.66% supply, $350K (March 2024)
+- Multicoin Capital: 9.33% supply, $1.4M (January 2025, $15M FDV)
+- Coinbase Ventures: 2.56% supply, $500K (February 2025, $19.5M FDV)
+- Total institutional pre-investment: ~$2.23M
+
+**Bull case:**
+1. B2B SDK (June 2026): third-party wallets/fintechs can embed P2P Protocol rails
+2. Circles of Trust: community operators stake $P2P to become Circle Admins, onboard merchants in new countries, earn revenue share
+3. 100% USDC refund guarantee for bank freezes — addresses real India pain point
+4. Operating profitability target by mid-2027
+
+**Bear case (Pine):**
+- Stretched valuation (182x gross profit)
+- User acquisition stagnated for 6+ months (23K users, 78% India concentration)
+- Expansion plans risk diluting focus
+- 50% float at TGE creates structural headwind (Delphi Digital: 30-40% passive/flipper behavior expected)
+
+**Pine verdict:** CAUTIOUS. The business is real and the mechanism design is sophisticated, but the valuation doesn't leave room for error.
+
+## Agent Notes
+
+**Why this matters:** Pine Analytics' analysis provides the most comprehensive independent valuation of a MetaDAO ICO project to date. The 182x gross profit multiple framing is the clearest articulation of the "speculative optionality" pricing problem — you're not buying current business, you're buying the right to participate in what it might become. This is consistent with the KB's broader claim about crypto projects pricing future optionality.
+
+**What surprised me:** The performance-gated team vesting structure is genuinely novel. I have seen graduated vesting, cliff-and-linear, and upfront unlocks in prior MetaDAO ICOs, but never performance-gated vesting with explicit price targets (2x/4x/8x/16x/32x via TWAP). This is a mechanism design contribution worth extracting as a claim.
+
+**What I expected but didn't find:** Any evidence that the performance gate design is being copied by other MetaDAO ICO projects. If this is the most aligned design in the ecosystem, I'd expect it to propagate. No evidence it has — suggesting either the design is too new to propagate or the mechanism design community hasn't flagged it.
+
+**KB connections:**
+- MetaDAO's real-money futarchy ICO platform shows strong participation signals — P2P.me as the latest data point
+- ownership alignment turns network effects generative (Belief #2) — performance-gated vesting is the purest implementation of this belief; P2P.me tests it
+- Delphi Digital study predicts 30-40 percent passive token holders in new projects — intersects with 50% float, creates specific testable headwind
+- Prior ICO comparisons: AVICI (4.7% holder loss during 65% drawdown), Umbra (graduated but not performance-gated)
+
+**Extraction hints:**
+1. **Performance-gated team vesting claim (CC1 from Session 11):** Extract as a mechanism design claim — "P2P.me team vesting eliminates early insider selling by making all team benefit conditional on community value creation (2x ICO price minimum before any tranche unlocks)"
+2. **182x gross profit multiple claim:** "MetaDAO ICO valuations price speculative optionality, not current business fundamentals — P2P.me at 182x annual gross profit is buying the right to participate in emerging market stablecoin infrastructure buildout"
+3. The Circles of Trust model is a novel community-aligned liquidity model worth a separate claim — stakers earn revenue share for onboarding local merchants, creating skin-in-the-game distributed growth
+
+**Context:** Pine Analytics is an independent crypto research firm publishing ICO analyses for the MetaDAO ecosystem. This appears to be their fourth or fifth MetaDAO ICO analysis. They previously analyzed AVICI and at least one other. Their "CAUTIOUS" rating should be weighted against their track record — Session 3 noted limited validation of their prediction accuracy.
+
+## Curator Notes (structured handoff for extractor)
+
+PRIMARY CONNECTION: performance-gated team vesting is the most aligned team incentive structure in futarchy-governed ICO history (CC1 from Session 11 — not yet in KB)
+
+WHY ARCHIVED: Provides the detailed mechanism design data for the performance-gated vesting claim AND the valuation framework (182x gross profit) for understanding what MetaDAO ICO pricing really represents. These are two distinct extractable claims.
+
+EXTRACTION HINT: Extract BOTH claims. (1) Mechanism design claim: performance-gated vesting structure — title, specific price targets, TWAP methodology. (2) Valuation framing claim: 182x gross profit multiple as "optionality pricing not fundamental valuation." The second claim has implications for how to evaluate all MetaDAO ICOs, not just P2P.me.

inbox/archive/internet-finance/2026-03-26-tg-shared-0xweiler-2037189643037200456-s-46.md

@@ -0,0 +1,30 @@
+---
+type: source
+source_type: x-tweet
+title: "@0xweiler — shared via Telegram by @m3taversal"
+author: "@0xweiler"
+url: "https://x.com/0xweiler/status/2037189643037200456?s=46"
+date: 2026-03-26
+domain: internet-finance
+format: social-media
+status: processed
+proposed_by: "@m3taversal"
+contribution_type: source-submission
+tags: ['telegram-shared', 'x-tweet']
+---
+
+# @0xweiler — Tweet/Thread
+
+Shared by @m3taversal via Telegram.
+Source URL: https://x.com/0xweiler/status/2037189643037200456?s=46
+
+## Content
+
+1/ A Valuation of Polymarket (POLY)
+
+March 7: @Polymarket was reportedly seeking a $20 billion valuation
+March 19: @Kalshi raised at $22 billion valuation
+
+A $POLY token and airdrop are confirmed. The central question is whether the $20 billion reflects reasonable expectations for future fee generation, or whether the market is mispricing the opportunity.
+
+My latest @MessariCrypto report builds a ground-up valuation to find out. Let's break it down 🧵

inbox/archive/internet-finance/2026-03-26-tg-shared-jussy-world-2037178019631259903-s-46.md

@@ -0,0 +1,32 @@
+---
+type: source
+source_type: x-tweet
+title: "@jussy_world — shared via Telegram by @m3taversal"
+author: "@jussy_world"
+url: "https://x.com/jussy_world/status/2037178019631259903?s=46"
+date: 2026-03-26
+domain: internet-finance
+format: social-media
+status: unprocessed
+proposed_by: "@m3taversal"
+contribution_type: source-submission
+tags: ['telegram-shared', 'x-tweet', 'market-analysis', 'crypto-infra']
+---
+
+# @jussy_world — Tweet/Thread
+
+Shared by @m3taversal via Telegram.
+Source URL: https://x.com/jussy_world/status/2037178019631259903?s=46
+
+## Content
+
+Polymarket projected 30d revenue will jumps from $4.26M → $172M
+
+Kalshi doing $110M/month at a $18.6B valuation pre-ipo
+
+Polymarket projected to match that revenue while trading at $15.77B
+
+Note: That's assuming if volume holds but even at half, the gap to Kalshi's
+valuation looks interesting
+
+Based on fees expanding from ~0.02% to ~0.80% across Finance, Politics, Economics, Sports and more

inbox/archive/internet-finance/2026-03-26-tg-source-m3taversal-jussy-world-thread-on-polymarket-projected-revenu.md

@@ -0,0 +1,26 @@
+---
+type: source
+source_type: telegram-contribution
+title: "Source from @m3taversal — @jussy_world thread on Polymarket projected revenue jump from $4.26M to $172M/mo"
+author: "@m3taversal"
+date: 2026-03-26
+domain: internet-finance
+format: contribution
+status: processed
+proposed_by: "@m3taversal"
+contribution_type: source-submission
+tags: ['telegram-contribution', 'inline-source', 'futarchy']
+---
+
+# Source: @jussy_world thread on Polymarket projected revenue jump from $4.26M to $172M/month at 0.80% fees ac
+
+Contributed by @m3taversal in Telegram chat.
+Flagged by Rio as relevant source material.
+
+## Verbatim User Message
+
+@FutAIrdBot https://x.com/jussy_world/status/2037178019631259903?s=46
+
+## Rio's Context
+
+@jussy_world thread on Polymarket projected revenue jump from $4.26M to $172M/month at 0.80% fees across expanded verticals, compared to Kalshi at $110M/month and $18.6B pre-IPO valuation. Polymarket projected at $15.77B. Context for prediction market valuations and implications for decision market category. https://x.com/jussy_world/status/2037178019631259903

inbox/archive/space-development/2026-03-27-blueorigin-new-glenn-manufacturing-odc-ambitions.md

@@ -0,0 +1,46 @@
+---
+type: source
+title: "Blue Origin ramps New Glenn to 1 rocket/month, targets 12-24 launches in 2026, unveils ODC ambitions"
+author: "Alejandro Alcantarilla Romera, Chris Bergin (NASASpaceFlight)"
+url: https://www.nasaspaceflight.com/2026/03/blue-new-glenn-manufacturing-data-ambitions/
+date: 2026-03-21
+domain: space-development
+secondary_domains: [energy]
+format: article
+status: processed
+priority: high
+tags: [new-glenn, blue-origin, manufacturing-rate, launch-cadence, project-sunrise, odc, orbital-data-center, vertical-integration, be-4]
+flagged_for_astra: ["ODC sector update — Blue Origin manufacturing context for Project Sunrise deployment viability"]
+---
+
+## Content
+
+NASASpaceFlight article (March 21, 2026) by Alcantarilla Romera and Bergin, reporting from Blue Origin's Space Coast facilities:
+
+**Manufacturing rate:** Blue Origin is completing one full New Glenn rocket per month. "Up to seven second stages are visible across different production stages" at the facility. This represents a significant production ramp from 2025 cadence.
+
+**2026 launch goals:** CEO Dave Limp believes the company can hit "double digits" in 2026 launches, matching production rate at 12, potentially going as high as 24 "if the success they've had ramping up vehicle production continues."
+
+**Current bottleneck:** Second stage production rate, not booster. BE-4 engine production at approximately 50/year currently, ramping to 100-150 by late 2026. At full BE-4 rate, approximately 7-14 New Glenn boosters annually, plus supporting Vulcan (2 BE-4s per flight).
+
+**ODC ambitions:** The article connects manufacturing ramp to Project Sunrise — Blue Origin's FCC-filed orbital data center constellation (51,600+ satellites, sun-synchronous orbit, solar-powered AI compute). The ODC ambitions require New Glenn to achieve Starlink-like deployment cadence to be viable.
+
+**Vertical integration framing:** Blue Origin's strategy positions Project Sunrise as internal demand creation for New Glenn, replicating the SpaceX/Starlink model. Own the payload demand, drive cadence, drive learning curve, reduce cost.
+
+## Agent Notes
+**Why this matters:** This article directly connects the Blue Origin manufacturing ramp to the vertical integration thesis. The 1 rocket/month rate is the supply-side input to the Project Sunrise deployment plan. But the gap between manufacturing capability and actual cadence (NG-3 still not launched as of March 27) is the critical tension.
+
+**What surprised me:** The scale of the manufacturing ambition (1/month, 12-24 launches/year) relative to their 2025 performance (2 launches total). This is either genuine operational capability being built or CEO-level aspirational communication. The physical evidence (7 second stages visible on factory floor) suggests real manufacturing activity, but launch cadence is the actual proof.
+
+**What I expected but didn't find:** A specific timeline for Project Sunrise deployment. The FCC filing doesn't include deployment schedules. The NSF article connects the manufacturing ramp to ODC ambitions but doesn't provide a satellite deployment timeline. How many New Glenn launches would it take to deploy 51,600 satellites? At what cadence? This is the key missing number for Project Sunrise viability analysis.
+
+**KB connections:** Project Sunrise — previously archived (2026-03-19-blue-origin-project-sunrise-fcc-orbital-datacenter.md). Vertical integration as demand bypass (two-gate model). ODC sector formation (Pattern 11 — Blue Origin is one of six players). SpaceX/Starlink flywheel as analogical model. Knowledge embodiment lag — manufacturing rate ≠ launch rate.
+
+**Extraction hints:** Three distinct claims: (1) Blue Origin's manufacturing rate (1/month, 12-24 launches/year) as vertical integration prerequisite. (2) The manufacturing-vs-cadence gap (NG-3 slip) as knowledge embodiment lag evidence. (3) Project Sunrise requiring Starlink-like cadence — feasibility of 51,600 satellites at current production rates (back-of-envelope: even at 50 satellites/launch, you need 1,032 launches; at 200 satellites/launch, still 258 launches). This satellite-per-launch number should be flagged for extraction.
+
+**Context:** Starlink deployed at ~50-60 satellites per Falcon 9 launch initially, scaling to 22-23 Starlink v2 per Falcon 9 rideshare or 20-21 Starlink per Starship. At 51,600 Project Sunrise satellites, Blue Origin would need hundreds to thousands of launches. Even at 12-24 launches per year, this is a 20-50 year deployment without much larger payload manifests. This is the most important number for Project Sunrise viability and it's currently absent from public analysis.
+
+## Curator Notes
+PRIMARY CONNECTION: Project Sunrise ODC (2026-03-19-blue-origin-project-sunrise-fcc-orbital-datacenter.md) — provides the launch infrastructure context for that filing
+WHY ARCHIVED: Manufacturing rate data combined with NG-3 cadence gap tests the vertical integration thesis in a way that reveals knowledge embodiment lag at operational scale
+EXTRACTION HINT: The satellites-per-launch back-of-envelope is the key analytical move — what does 51,600 satellites actually require in launch cadence terms? Extractor should calculate and note whether this is plausible given Blue Origin's stated rate.

inbox/archive/space-development/2026-03-27-blueorigin-ng3-ast-bluebird.md

@@ -0,0 +1,39 @@
+---
+type: source
+title: "New Glenn NG-3 to launch AST SpaceMobile BlueBird Block 2 — first booster reuse"
+author: "Blue Origin (@blueorigin)"
+url: https://www.blueorigin.com/news/new-glenn-3-to-launch-ast-spacemobile-bluebird-satellite
+date: 2026-01-22
+domain: space-development
+secondary_domains: []
+format: press-release
+status: unprocessed
+priority: medium
+tags: [new-glenn, ng-3, ast-spacemobile, booster-reuse, launch-cadence, blue-origin]
+---
+
+## Content
+
+Blue Origin announced NG-3, its third New Glenn mission, will carry AST SpaceMobile's next-generation Block 2 BlueBird satellite to low Earth orbit. NET late February 2026, later slipped to NET March 2026 (as tracked by NASASpaceFlight forum thread). The mission marks the program's first booster reuse: the first stage from NG-2 ("Never Tell Me The Odds") which successfully landed on drone ship Jacklyn after delivering NASA's ESCAPADE Mars probes in November 2025, will fly again.
+
+Additional context from NASA Spaceflight (March 21, 2026 article by Alcantarilla Romera / Bergin): Blue Origin is completing one full New Glenn per month. CEO Dave Limp stated 12-24 launches possible in 2026. Second stage is the current production bottleneck. BE-4 engine production at ~50/year, ramping to 100-150 by late 2026 (supporting 7-14 New Glenn boosters annually at full rate).
+
+As of March 27, 2026, NG-3 has not yet launched despite the February then March NET dates.
+
+## Agent Notes
+**Why this matters:** NG-3 has been unresolved for 9 consecutive research sessions. First booster reuse milestone is critical for demonstrating cadence credibility. CEO's 12-24 launch claim for 2026 is now under stress with NG-3 slipping from late-February to late-March, suggesting the manufacturing rate (1/month) does not translate directly to launch rate.
+
+**What surprised me:** Blue Origin is manufacturing one complete New Glenn per month — this is a remarkably high stated rate for only their 2nd active vehicle. If real, it implies significant hardware inventory is accumulating. The gap between stated manufacturing rate and actual launch cadence (NG-3 still not flown in late March) is the most interesting data point.
+
+**What I expected but didn't find:** A concrete explanation for the NG-3 slip. The TechCrunch article from January 22 mentioned late February NET; the NSF forum shows March 2026 NET. No public explanation for the further delay has been found. This gap (stated capability vs execution) is worth investigating.
+
+**KB connections:** Pattern 2 (institutional timelines slipping) — NG-3 is now 4-6 weeks behind its announced window. Knowledge embodiment lag — manufacturing capability ≠ operational cadence. Blue Origin vertical integration strategy (Project Sunrise as internal demand creation).
+
+**Extraction hints:** Claim candidate — "Blue Origin's stated manufacturing rate and actual launch cadence reveal a knowledge embodiment gap at operational scale." Also: first booster reuse is a milestone claim supporting reusability maturation. Don't conflate manufacturing rate with launch rate — they're measuring different things.
+
+**Context:** Blue Origin has completed 2 New Glenn launches (NG-1: orbital attempt with booster loss, January 2025; NG-2: ESCAPADE + booster recovery, November 2025). NG-3 is the third mission and first reuse. The CEO's 12-24 launch claim for 2026 would require roughly 10-22 additional launches after NG-3.
+
+## Curator Notes
+PRIMARY CONNECTION: Blue Origin vertical integration thesis (Project Sunrise creates internal New Glenn demand)
+WHY ARCHIVED: Tests manufacturing-vs-cadence gap as evidence for/against knowledge embodiment lag claim
+EXTRACTION HINT: Focus on the delta between stated manufacturing capability (1/month) and actual execution (NG-3 slip) — this is the analytically interesting claim, not the launch itself

inbox/archive/space-development/2026-03-27-nasa-authorization-act-iss-overlap-mandate.md

@@ -0,0 +1,45 @@
+---
+type: source
+title: "NASA Authorization Act of 2026 passes Senate committee — ISS overlap mandate requires commercial station co-existence before deorbit"
+author: "SpaceNews / AIAA / Space.com"
+url: https://spacenews.com/senate-committee-advances-nasa-authorization-bill-that-changes-artemis-and-extends-iss/
+date: 2026-03-05
+domain: space-development
+secondary_domains: []
+format: article
+status: processed
+priority: high
+tags: [iss-extension, nasa-authorization, commercial-space-station, congress, gate-2, policy, haven-1, overlap-mandate]
+---
+
+## Content
+
+The NASA Authorization Act of 2026 passed the Senate Commerce, Science & Transportation committee with bipartisan support (spearheaded by Sen. Ted Cruz, R-TX). Key provisions:
+
+1. Extends ISS operational life from 2030 to 2032 (September 30, 2032)
+2. **Overlap mandate**: ISS must operate alongside at least one "fully operational" commercial station for at least one full year
+3. **Crew continuity requirement**: During the overlap year, full crews must be in space concurrently for at least 180 days
+4. Directs NASA to accelerate commercial LEO destinations development
+5. Cites "Tiangong scenario" (China's station would be world's only inhabited station if ISS deorbits without replacement) as strategic rationale
+
+Legislative status: Passed committee. Still requires full Senate vote, House passage, and Presidential signature. Not yet law.
+
+Secondary sources confirming passage: Congress.gov (bill tracking), AIAA statement (March 10, 2026), Space.com analysis ("why Congress wants ISS to fly until 2032"), Slashdot ("Congress Extends ISS, Tells NASA To Get Moving On Private Space Stations").
+
+## Agent Notes
+**Why this matters:** The overlap mandate is qualitatively different from prior ISS extension proposals. Previous extensions simply deferred the deadline. This mandate creates a TRANSITION CONDITION: commercial station must be operational and crewed before ISS deorbits. This is a policy-engineered Gate 2 mechanism — it guarantees a government anchor tenant relationship during a defined operational window (the overlap year), giving any qualifying commercial station a funded proof-of-concept period.
+
+**What surprised me:** The 180-day concurrent crew requirement is operationally specific — this isn't a "maybe overlap" provision, it requires full concurrent crewing for half a year. This creates a very specific technical and scheduling requirement for the commercial station candidate (it needs full crew capability, life support, docking, communication). Haven-1 is the only station with a realistic 2031 timeline under this framework.
+
+**What I expected but didn't find:** Specific mention of which commercial station(s) are expected to serve as the overlap partner. The bill doesn't name Vast/Haven-1, but the timeline logic makes it the implicit target. Also missing: how "fully operational" is defined for triggering the overlap year.
+
+**KB connections:** Gate 2 formation (Pattern 10) — this is the strongest government mechanism yet for forcing Gate 2 formation. National security demand floor (Pattern 12) — Tiangong scenario framing is the explicit justification. Commercial station capital concentration (Pattern 9) — Axiom's $350M Series C despite Phase 2 freeze, now Haven-1's $500M, while weaker programs fade. ISS extension analysis from prior sessions (March 22-26).
+
+**Extraction hints:** Primary claim: "The ISS overlap mandate (NASA Authorization Act 2026) creates a policy-engineered Gate 2 transition condition for commercial space stations — the strongest government mechanism yet for forcing commercial viability." Secondary: "The 180-day concurrent crew requirement makes Haven-1 the implicit, and possibly only, qualifying overlap partner under the 2032 framework." These should be checked for divergence with prior claim about ISS extension deferring but not manufacturing Gate 2 conditions — the overlap mandate changes this dynamic.
+
+**Context:** This bill is a significant evolution from the prior "schedule risk" framing (previous session archived source: 2026-03-01-congress-iss-2032-extension-gap-risk.md). That source characterized the extension as acknowledging gap risk. This bill adds affirmative transition requirements. The two sources together tell a before/after story of congressional intent.
+
+## Curator Notes
+PRIMARY CONNECTION: ISS 2032 extension gap risk (2026-03-01-congress-iss-2032-extension-gap-risk.md) — this is the "after" to that source's "before"
+WHY ARCHIVED: Overlap mandate is a new mechanism that substantially changes Gate 2 formation dynamics for commercial stations — not captured in any prior session
+EXTRACTION HINT: Extract the overlap mandate as its own claim, distinct from the simple extension. The transition condition (fully operational + 180 days concurrent crew) is the novel policy element. Flag potential divergence with prior claim about policy deferring but not manufacturing Gate 2.

inbox/archive/space-development/2026-03-27-starship-falcon9-cost-2026-commercial-operations.md

@@ -0,0 +1,50 @@
+---
+type: source
+title: "Starship and Falcon 9 launch cost data 2026 — ODC and ISRU threshold analysis"
+author: "The Motley Fool / SpaceNexus / NextBigFuture"
+url: https://www.fool.com/investing/2026/03/21/how-much-will-a-spacex-starship-launch-cost/
+date: 2026-03-21
+domain: space-development
+secondary_domains: [energy]
+format: article
+status: processed
+priority: medium
+tags: [starship, falcon-9, launch-cost, cost-per-kg, odc-threshold, isru-threshold, keystone-variable]
+---
+
+## Content
+
+Multiple sources converging on the following launch cost estimates as of March 2026:
+
+**Falcon 9 (commercially available):**
+- Advertised: $67M/launch for dedicated mission, ~$2,720/kg (full capacity basis)
+- Rideshare: $1.1M for first 200kg + $5,500/kg afterward
+- SpaceX internal cost: ~$629/kg (approximately 25% of customer price per NextBigFuture, Feb 2026)
+- Average price per kg based on actual customer usage patterns: ~$20,770/kg (customers typically use much less than full capacity)
+
+**Starship (not yet commercially available):**
+- Current estimated cost with operational reusability level achieved in testing: ~$1,600/kg
+- Near-term projection (full reuse, high cadence): $250-600/kg
+- Long-term aspirational target: $100-150/kg
+- SpaceX ultimate goal: $10/kg (Musk stated target)
+- Near-term operating cost per launch (fuel + maintenance + pad): $10M or less, eventually $2-3M
+
+**Commercial context:** Starship has not yet conducted a commercial payload mission. All Starship flights to date are test and development flights. Commercial operations expected to begin in 2026-2027, but no firm commercial manifest public.
+
+## Agent Notes
+**Why this matters:** This data directly grounds the two-gate model's Gate 1 thresholds for the three pre-Gate-1 sectors: ODC (~$200/kg needed), lunar ISRU (Starship sub-$100/kg is the enabling condition per KB), and megastructure launch infrastructure (all require sub-$100/kg to make economic sense). Falcon 9 at $2,720/kg is 13.6x too expensive for ODC. Starship at $1,600/kg is 8x too expensive. Even at the near-term projection of $250-600/kg, ODC is still 1.25-3x over threshold.
+
+**What surprised me:** SpaceX's internal cost of $629/kg for Falcon 9 means they're operating at approximately a 4:1 markup. This implies Starship's future pricing will also carry significant markup above operating cost. If Starship's operating cost reaches $10M/launch at full reuse, and SpaceX applies even a 2:1 markup, commercial pricing would be ~$133/kg for 150t to LEO — right at the $100-150/kg long-term projection. This is a pricing model consistency check that validates the projections.
+
+**What I expected but didn't find:** A Starship commercial pricing announcement. SpaceX has been quiet on what it will actually charge for commercial Starship payloads. The $1,600/kg estimate appears to be analyst-derived, not SpaceX-stated.
+
+**KB connections:** Belief #1 (launch cost as keystone variable) — this data shows Gate 1 is NOT yet cleared for ODC or lunar ISRU. ODC threshold from prior session ($200/kg). Cislunar ISRU map claim that "Starship at sub-$100/kg is the enabling condition." Threshold economics (Astra's core lens).
+
+**Extraction hints:** The $200/kg ODC threshold + current Starship at $1,600/kg = 8x gap is a concrete, specific claim: "Orbital data centers require ~8x reduction from current Starship launch costs before Gate 1 is cleared." Also: SpaceX internal cost ($629/kg Falcon 9) implies commercial pricing structure — can be used to project Starship commercial pricing from operating cost estimates.
+
+**Context:** These numbers are critical for answering the disconfirmation question. If launch cost were not the keystone variable for ODC, we'd see ODC customers forming demand before the $200/kg threshold is crossed. The absence of validated commercial ODC demand (as of March 2026, Blue Origin has an FCC filing but no customers; Starcloud has hardware but no revenue contract) is consistent with the Gate 1 thesis.
+
+## Curator Notes
+PRIMARY CONNECTION: ODC sector analysis from prior sessions (two-gate model, Pattern 11)
+WHY ARCHIVED: Provides current cost data anchoring Gate 1 threshold analysis across ODC, ISRU, and megastructure sectors — direct evidence for/against Belief #1
+EXTRACTION HINT: Focus on the threshold gap calculations ($200/kg ODC needed vs $1,600/kg current Starship; sub-$100/kg ISRU needed vs $1,600/kg current). These are specific, falsifiable claims about which sectors are Gate-1 blocked.

inbox/archive/telegram/2026-03-26-telegram-m3taversal-futairdbot-https-x-com-sjdedic-status-203714354.md

@@ -0,0 +1,60 @@
+---
+type: source
+source_type: telegram
+title: "Telegram: @m3taversal — futairdbot-https-x-com-sjdedic-status-203714354"
+author: "@m3taversal"
+url: "https://x.com/sjdedic/status/2037143546256384412?s=46"
+date: 2026-03-26
+domain: internet-finance
+format: conversation
+status: unprocessed
+priority: high
+intake_tier: directed
+rationale: "I really want to develop dashboards for all metaDAO ownership coins w revenue. How would we do that"
+proposed_by: "@m3taversal"
+tags: [telegram, ownership-community]
+---
+
+## Conversation
+
+**@m3taversal:**
+@FutAIrdBot https://x.com/sjdedic/status/2037143546256384412?s=46 I really want to develop dashboards for all metaDAO ownership coins w revenue. How would we do that
+
+**Rio (response):**
+Good instinct. The data is all onchain so it's very buildable, especially now that AI makes Dune accessible even without SQL experience (exactly what sjdedic is showing there).
+
+For MetaDAO ownership coins specifically, here's what I'd track per token:
+
+1. Treasury AUM over time (the core metric, since these are ownership coins backed by real treasuries)
+2. Revenue flows into treasury vs outflows (grants, compensation, operational spend)
+3. Market cap vs treasury AUM ratio (the "discount to NAV" that makes ownership coins interesting)
+4. Conditional market activity (pass/fail volumes, TWAP convergence)
+5. Token holder distribution and concentration
+
+The practical path: start with META itself since it has the most data. Treasury is sitting at ~$9.5M USDC right now, circulating supply is ~22.7M tokens, price around $3.18. So you're looking at roughly $72M fully diluted vs $9.5M treasury. That gap alone is a dashboard worth building.
+
+For the Dune side, the key program accounts you'd be querying are the Autocrat program interactions and SPL token flows into/out of DAO treasury accounts. Each ownership coin launched through metadao.fi has its own DAO account and proposal accounts that are all indexable.
+
+If you want to contribute this to the ecosystem, you could build it and we can get it linked into the knowledge base. Tag me with the dashboard when you have something and I can help surface it. You could also submit source material to the contribution pipeline if you document the methodology.
+
+Who are you thinking beyond META? The permissioned launches on metadao.fi (like P2P.me) would be the most interesting ones to cover since that's where real capital formation is happening.
+
+## Article Content (fetched)
+
+I literally have 0 coding experience and had never worked with Dune dashboards before.
+
+It always annoyed me having to rely on other people’s dashboards and never finding the exact data I was looking for, so I figured I’d try building one myself with AI.
+
+With Claude’s help, it took me less than 1.5 hours, and most of that was just understanding how Dune works. The next one would probably take under an hour.
+
+I remember some of our portfolio companies paying thousands of $$ for these and waiting weeks for them to go live.
+
+Even though this trend has been obvious for a while, this really made it click for me just how much AI is eroding the moat and defensibility of developers, and how easy it is now for a complete beginner like me.
+
+Devs are cooked.
+
+## Agent Notes
+**Why archived:** Tagged exchange in ownership community.
+**Rationale from contributor:** I really want to develop dashboards for all metaDAO ownership coins w revenue. How would we do that
+**Intake tier:** directed — fast-tracked, contributor provided reasoning
+**Triage:** Conversation may contain [CLAIM], [ENTITY], or [EVIDENCE] for extraction.

inbox/queue/.extraction-debug/2026-03-26-cftc-anprm-prediction-markets-federal-register.json

@@ -0,0 +1,38 @@
+{
+  "rejected_claims": [
+    {
+      "filename": "cftc-anprm-creates-default-gaming-classification-risk-for-futarchy-governance-markets-through-regulatory-silence.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    },
+    {
+      "filename": "futarchy-governance-markets-differ-structurally-from-prediction-markets-through-endogenous-resolution-and-joint-ownership-coordination.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    }
+  ],
+  "validation_stats": {
+    "total": 2,
+    "kept": 0,
+    "fixed": 8,
+    "rejected": 2,
+    "fixes_applied": [
+      "cftc-anprm-creates-default-gaming-classification-risk-for-futarchy-governance-markets-through-regulatory-silence.md:set_created:2026-03-26",
+      "cftc-anprm-creates-default-gaming-classification-risk-for-futarchy-governance-markets-through-regulatory-silence.md:stripped_wiki_link:the DAO Reports rejection of voting as active management is ",
+      "cftc-anprm-creates-default-gaming-classification-risk-for-futarchy-governance-markets-through-regulatory-silence.md:stripped_wiki_link:Ooki DAO proved that DAOs without legal wrappers face genera",
+      "cftc-anprm-creates-default-gaming-classification-risk-for-futarchy-governance-markets-through-regulatory-silence.md:stripped_wiki_link:the SECs framework treats meme coins as digital collectibles",
+      "futarchy-governance-markets-differ-structurally-from-prediction-markets-through-endogenous-resolution-and-joint-ownership-coordination.md:set_created:2026-03-26",
+      "futarchy-governance-markets-differ-structurally-from-prediction-markets-through-endogenous-resolution-and-joint-ownership-coordination.md:stripped_wiki_link:the DAO Reports rejection of voting as active management is ",
+      "futarchy-governance-markets-differ-structurally-from-prediction-markets-through-endogenous-resolution-and-joint-ownership-coordination.md:stripped_wiki_link:futarchy-governed entities are structurally not securities b",
+      "futarchy-governance-markets-differ-structurally-from-prediction-markets-through-endogenous-resolution-and-joint-ownership-coordination.md:stripped_wiki_link:Living Capital vehicles likely fail the Howey test for secur"
+    ],
+    "rejections": [
+      "cftc-anprm-creates-default-gaming-classification-risk-for-futarchy-governance-markets-through-regulatory-silence.md:missing_attribution_extractor",
+      "futarchy-governance-markets-differ-structurally-from-prediction-markets-through-endogenous-resolution-and-joint-ownership-coordination.md:missing_attribution_extractor"
+    ]
+  },
+  "model": "anthropic/claude-sonnet-4.5",
+  "date": "2026-03-26"
+}

inbox/queue/.extraction-debug/2026-03-26-pine-analytics-p2p-protocol-ico-analysis.json

@@ -0,0 +1,49 @@
+{
+  "rejected_claims": [
+    {
+      "filename": "performance-gated-team-vesting-eliminates-early-insider-selling-by-conditioning-all-team-benefit-on-community-value-creation.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    },
+    {
+      "filename": "metadao-ico-valuations-price-speculative-optionality-not-current-business-fundamentals-as-evidenced-by-182x-gross-profit-multiples.md",
+      "issues": [
+        "missing_attribution_extractor",
+        "opsec_internal_deal_terms"
+      ]
+    },
+    {
+      "filename": "circles-of-trust-staking-model-creates-skin-in-the-game-distributed-growth-through-revenue-sharing-with-community-operators.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    }
+  ],
+  "validation_stats": {
+    "total": 3,
+    "kept": 0,
+    "fixed": 10,
+    "rejected": 3,
+    "fixes_applied": [
+      "performance-gated-team-vesting-eliminates-early-insider-selling-by-conditioning-all-team-benefit-on-community-value-creation.md:set_created:2026-03-26",
+      "performance-gated-team-vesting-eliminates-early-insider-selling-by-conditioning-all-team-benefit-on-community-value-creation.md:stripped_wiki_link:time-based-token-vesting-is-hedgeable-making-standard-lockup",
+      "performance-gated-team-vesting-eliminates-early-insider-selling-by-conditioning-all-team-benefit-on-community-value-creation.md:stripped_wiki_link:MetaDAO-is-the-futarchy-launchpad-on-Solana-where-projects-r",
+      "metadao-ico-valuations-price-speculative-optionality-not-current-business-fundamentals-as-evidenced-by-182x-gross-profit-multiples.md:set_created:2026-03-26",
+      "metadao-ico-valuations-price-speculative-optionality-not-current-business-fundamentals-as-evidenced-by-182x-gross-profit-multiples.md:stripped_wiki_link:cryptos-primary-use-case-is-capital-formation-not-payments-o",
+      "metadao-ico-valuations-price-speculative-optionality-not-current-business-fundamentals-as-evidenced-by-182x-gross-profit-multiples.md:stripped_wiki_link:metadao-ico-platform-demonstrates-15x-oversubscription-valid",
+      "metadao-ico-valuations-price-speculative-optionality-not-current-business-fundamentals-as-evidenced-by-182x-gross-profit-multiples.md:stripped_wiki_link:internet-capital-markets-compress-fundraising-from-months-to",
+      "circles-of-trust-staking-model-creates-skin-in-the-game-distributed-growth-through-revenue-sharing-with-community-operators.md:set_created:2026-03-26",
+      "circles-of-trust-staking-model-creates-skin-in-the-game-distributed-growth-through-revenue-sharing-with-community-operators.md:stripped_wiki_link:ownership-alignment-turns-network-effects-generative.md",
+      "circles-of-trust-staking-model-creates-skin-in-the-game-distributed-growth-through-revenue-sharing-with-community-operators.md:stripped_wiki_link:token-economics-replacing-management-fees-and-carried-intere"
+    ],
+    "rejections": [
+      "performance-gated-team-vesting-eliminates-early-insider-selling-by-conditioning-all-team-benefit-on-community-value-creation.md:missing_attribution_extractor",
+      "metadao-ico-valuations-price-speculative-optionality-not-current-business-fundamentals-as-evidenced-by-182x-gross-profit-multiples.md:missing_attribution_extractor",
+      "metadao-ico-valuations-price-speculative-optionality-not-current-business-fundamentals-as-evidenced-by-182x-gross-profit-multiples.md:opsec_internal_deal_terms",
+      "circles-of-trust-staking-model-creates-skin-in-the-game-distributed-growth-through-revenue-sharing-with-community-operators.md:missing_attribution_extractor"
+    ]
+  },
+  "model": "anthropic/claude-sonnet-4.5",
+  "date": "2026-03-26"
+}

inbox/queue/.extraction-debug/2026-03-26-polymarket-p2p-protocol-commitment-market.json

@@ -0,0 +1,26 @@
+{
+  "rejected_claims": [
+    {
+      "filename": "prediction-market-participation-by-issuers-in-own-ico-commitment-markets-creates-circular-social-proof-with-no-arbitrage-correction.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    }
+  ],
+  "validation_stats": {
+    "total": 1,
+    "kept": 0,
+    "fixed": 3,
+    "rejected": 1,
+    "fixes_applied": [
+      "prediction-market-participation-by-issuers-in-own-ico-commitment-markets-creates-circular-social-proof-with-no-arbitrage-correction.md:set_created:2026-03-26",
+      "prediction-market-participation-by-issuers-in-own-ico-commitment-markets-creates-circular-social-proof-with-no-arbitrage-correction.md:stripped_wiki_link:futarchy-is-manipulation-resistant-because-attack-attempts-c",
+      "prediction-market-participation-by-issuers-in-own-ico-commitment-markets-creates-circular-social-proof-with-no-arbitrage-correction.md:stripped_wiki_link:prediction-market-boom-is-primarily-a-sports-gambling-boom-w"
+    ],
+    "rejections": [
+      "prediction-market-participation-by-issuers-in-own-ico-commitment-markets-creates-circular-social-proof-with-no-arbitrage-correction.md:missing_attribution_extractor"
+    ]
+  },
+  "model": "anthropic/claude-sonnet-4.5",
+  "date": "2026-03-26"
+}

inbox/queue/.extraction-debug/2026-03-27-blueorigin-new-glenn-manufacturing-odc-ambitions.json

@@ -0,0 +1,36 @@
+{
+  "rejected_claims": [
+    {
+      "filename": "manufacturing-rate-without-launch-cadence-reveals-knowledge-embodiment-lag-in-aerospace.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    },
+    {
+      "filename": "vertical-integration-requires-internal-demand-at-scale-to-justify-manufacturing-investment.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    }
+  ],
+  "validation_stats": {
+    "total": 2,
+    "kept": 0,
+    "fixed": 6,
+    "rejected": 2,
+    "fixes_applied": [
+      "manufacturing-rate-without-launch-cadence-reveals-knowledge-embodiment-lag-in-aerospace.md:set_created:2026-03-27",
+      "manufacturing-rate-without-launch-cadence-reveals-knowledge-embodiment-lag-in-aerospace.md:stripped_wiki_link:AI labor displacement follows knowledge embodiment lag phase",
+      "manufacturing-rate-without-launch-cadence-reveals-knowledge-embodiment-lag-in-aerospace.md:stripped_wiki_link:reusability without rapid turnaround and minimal refurbishme",
+      "vertical-integration-requires-internal-demand-at-scale-to-justify-manufacturing-investment.md:set_created:2026-03-27",
+      "vertical-integration-requires-internal-demand-at-scale-to-justify-manufacturing-investment.md:stripped_wiki_link:SpaceX vertical integration across launch broadband and manu",
+      "vertical-integration-requires-internal-demand-at-scale-to-justify-manufacturing-investment.md:stripped_wiki_link:Rocket Lab pivot to space systems reveals that vertical comp"
+    ],
+    "rejections": [
+      "manufacturing-rate-without-launch-cadence-reveals-knowledge-embodiment-lag-in-aerospace.md:missing_attribution_extractor",
+      "vertical-integration-requires-internal-demand-at-scale-to-justify-manufacturing-investment.md:missing_attribution_extractor"
+    ]
+  },
+  "model": "anthropic/claude-sonnet-4.5",
+  "date": "2026-03-27"
+}

inbox/queue/.extraction-debug/2026-03-27-nasa-authorization-act-iss-overlap-mandate.json

@@ -0,0 +1,36 @@
+{
+  "rejected_claims": [
+    {
+      "filename": "iss-overlap-mandate-creates-policy-engineered-gate-2-transition-condition-for-commercial-space-stations.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    },
+    {
+      "filename": "haven-1-timeline-makes-it-implicit-sole-qualifying-overlap-partner-under-2032-iss-framework.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    }
+  ],
+  "validation_stats": {
+    "total": 2,
+    "kept": 0,
+    "fixed": 6,
+    "rejected": 2,
+    "fixes_applied": [
+      "iss-overlap-mandate-creates-policy-engineered-gate-2-transition-condition-for-commercial-space-stations.md:set_created:2026-03-27",
+      "iss-overlap-mandate-creates-policy-engineered-gate-2-transition-condition-for-commercial-space-stations.md:stripped_wiki_link:commercial space stations are the next infrastructure bet as",
+      "iss-overlap-mandate-creates-policy-engineered-gate-2-transition-condition-for-commercial-space-stations.md:stripped_wiki_link:governments are transitioning from space system builders to ",
+      "haven-1-timeline-makes-it-implicit-sole-qualifying-overlap-partner-under-2032-iss-framework.md:set_created:2026-03-27",
+      "haven-1-timeline-makes-it-implicit-sole-qualifying-overlap-partner-under-2032-iss-framework.md:stripped_wiki_link:Vast is building the first commercial space station with Hav",
+      "haven-1-timeline-makes-it-implicit-sole-qualifying-overlap-partner-under-2032-iss-framework.md:stripped_wiki_link:commercial space stations are the next infrastructure bet as"
+    ],
+    "rejections": [
+      "iss-overlap-mandate-creates-policy-engineered-gate-2-transition-condition-for-commercial-space-stations.md:missing_attribution_extractor",
+      "haven-1-timeline-makes-it-implicit-sole-qualifying-overlap-partner-under-2032-iss-framework.md:missing_attribution_extractor"
+    ]
+  },
+  "model": "anthropic/claude-sonnet-4.5",
+  "date": "2026-03-27"
+}

inbox/queue/.extraction-debug/2026-03-27-starship-falcon9-cost-2026-commercial-operations.json

@@ -0,0 +1,38 @@
+{
+  "rejected_claims": [
+    {
+      "filename": "starship-current-cost-creates-8x-gap-to-orbital-data-center-viability-threshold.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    },
+    {
+      "filename": "spacex-markup-structure-implies-starship-commercial-pricing-at-133-per-kg-when-operating-costs-reach-10m-per-launch.md",
+      "issues": [
+        "missing_attribution_extractor",
+        "opsec_internal_deal_terms"
+      ]
+    }
+  ],
+  "validation_stats": {
+    "total": 2,
+    "kept": 0,
+    "fixed": 6,
+    "rejected": 2,
+    "fixes_applied": [
+      "starship-current-cost-creates-8x-gap-to-orbital-data-center-viability-threshold.md:set_created:2026-03-27",
+      "starship-current-cost-creates-8x-gap-to-orbital-data-center-viability-threshold.md:stripped_wiki_link:launch cost reduction is the keystone variable that unlocks ",
+      "starship-current-cost-creates-8x-gap-to-orbital-data-center-viability-threshold.md:stripped_wiki_link:Starship achieving routine operations at sub-100 dollars per",
+      "spacex-markup-structure-implies-starship-commercial-pricing-at-133-per-kg-when-operating-costs-reach-10m-per-launch.md:set_created:2026-03-27",
+      "spacex-markup-structure-implies-starship-commercial-pricing-at-133-per-kg-when-operating-costs-reach-10m-per-launch.md:stripped_wiki_link:Starship achieving routine operations at sub-100 dollars per",
+      "spacex-markup-structure-implies-starship-commercial-pricing-at-133-per-kg-when-operating-costs-reach-10m-per-launch.md:stripped_wiki_link:Starship economics depend on cadence and reuse rate not vehi"
+    ],
+    "rejections": [
+      "starship-current-cost-creates-8x-gap-to-orbital-data-center-viability-threshold.md:missing_attribution_extractor",
+      "spacex-markup-structure-implies-starship-commercial-pricing-at-133-per-kg-when-operating-costs-reach-10m-per-launch.md:missing_attribution_extractor",
+      "spacex-markup-structure-implies-starship-commercial-pricing-at-133-per-kg-when-operating-costs-reach-10m-per-launch.md:opsec_internal_deal_terms"
+    ]
+  },
+  "model": "anthropic/claude-sonnet-4.5",
+  "date": "2026-03-27"
+}

inbox/queue/.extraction-debug/2026-03-27-vast-haven1-delay-2027-fundraise.json

@@ -0,0 +1,32 @@
+{
+  "rejected_claims": [
+    {
+      "filename": "post-gate-1-commercial-space-constrained-by-technical-readiness-not-launch-cost.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    },
+    {
+      "filename": "fundraise-during-delay-signals-investor-belief-in-gate-2-formation.md",
+      "issues": [
+        "missing_attribution_extractor"
+      ]
+    }
+  ],
+  "validation_stats": {
+    "total": 2,
+    "kept": 0,
+    "fixed": 2,
+    "rejected": 2,
+    "fixes_applied": [
+      "post-gate-1-commercial-space-constrained-by-technical-readiness-not-launch-cost.md:set_created:2026-03-27",
+      "fundraise-during-delay-signals-investor-belief-in-gate-2-formation.md:set_created:2026-03-27"
+    ],
+    "rejections": [
+      "post-gate-1-commercial-space-constrained-by-technical-readiness-not-launch-cost.md:missing_attribution_extractor",
+      "fundraise-during-delay-signals-investor-belief-in-gate-2-formation.md:missing_attribution_extractor"
+    ]
+  },
+  "model": "anthropic/claude-sonnet-4.5",
+  "date": "2026-03-27"
+}