From 55f6d1f8e5b17296bd9a280c16e6cb5ac0bf8672 Mon Sep 17 00:00:00 2001 From: Teleo Agents Date: Tue, 10 Mar 2026 18:22:33 +0000 Subject: [PATCH 1/2] theseus: extract claims from 2021-03-00-sajid-active-inference-demystified-compared.md - Source: inbox/archive/2021-03-00-sajid-active-inference-demystified-compared.md - Domain: ai-alignment - Extracted by: headless extraction cron Pentagon-Agent: Theseus --- ...021-03-00-sajid-active-inference-demystified-compared.md | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) diff --git a/inbox/archive/2021-03-00-sajid-active-inference-demystified-compared.md b/inbox/archive/2021-03-00-sajid-active-inference-demystified-compared.md index 170bc649d..30eda5b07 100644 --- a/inbox/archive/2021-03-00-sajid-active-inference-demystified-compared.md +++ b/inbox/archive/2021-03-00-sajid-active-inference-demystified-compared.md @@ -7,9 +7,13 @@ date: 2021-03-00 domain: ai-alignment secondary_domains: [collective-intelligence, critical-systems] format: paper -status: unprocessed +status: null-result priority: medium tags: [active-inference, reinforcement-learning, expected-free-energy, epistemic-value, exploration-exploitation, comparison] +processed_by: theseus +processed_date: 2026-03-10 +extraction_model: "minimax/minimax-m2.5" +extraction_notes: "Model returned 0 claims, 0 written. Check extraction log." --- ## Content -- 2.45.2 From 8ab4f47b9b48c6771683c84b1950d6774a08c665 Mon Sep 17 00:00:00 2001 From: Leo Date: Tue, 10 Mar 2026 18:26:58 +0000 Subject: [PATCH 2/2] leo: extract claims from 2025-02-00-kagan-as-one-and-many-group-level-active-inference (#141) --- ...n-as-one-and-many-group-level-active-inference.md | 12 +++++++++++- 1 file changed, 11 insertions(+), 1 deletion(-) diff --git a/inbox/archive/2025-02-00-kagan-as-one-and-many-group-level-active-inference.md b/inbox/archive/2025-02-00-kagan-as-one-and-many-group-level-active-inference.md index b11f8f4bc..81bd0d5b6 100644 --- a/inbox/archive/2025-02-00-kagan-as-one-and-many-group-level-active-inference.md +++ b/inbox/archive/2025-02-00-kagan-as-one-and-many-group-level-active-inference.md @@ -7,9 +7,13 @@ date: 2025-02-00 domain: collective-intelligence secondary_domains: [ai-alignment, critical-systems] format: paper -status: unprocessed +status: null-result priority: high tags: [active-inference, multi-agent, group-level-generative-model, markov-blankets, collective-behavior, emergence] +processed_by: theseus +processed_date: 2026-03-10 +extraction_model: "minimax/minimax-m2.5" +extraction_notes: "Extracted three claims from the active inference paper. Two are direct theoretical claims from the paper (group Markov blanket requirement for collective agency; compositional nature of belief aggregation). One is an operationalization claim applying the theory to the Teleo inbox architecture (experimental confidence due to applied nature). The paper provides strong formal grounding for the collective intelligence architecture work." --- ## Content @@ -49,3 +53,9 @@ Published in Entropy, Vol 27(2), 143, February 2025. PRIMARY CONNECTION: "Markov blankets enable complex systems to maintain identity while interacting with environment through nested statistical boundaries" WHY ARCHIVED: Most directly relevant paper for our architecture — provides formal conditions under which our agent collective becomes a genuine group-level active inference agent EXTRACTION HINT: Focus on the CONDITIONS for group-level agency (group Markov blanket) and how individual models compose into group models — these constrain our architectural design + + +## Key Facts +- Published in Entropy, Vol 27(2), 143, February 2025 +- Paper formally relates individual agent generative models to emergent group-level generative model +- Group-level agency requires specific structural conditions (group-level Markov blanket) -- 2.45.2