auto-fix: strip 12 broken wiki links

Pipeline auto-fixer: removed [[ ]] brackets from links
that don't resolve to existing claims in the knowledge base.

inbox/queue/2026-05-03-clinical-trial-vanguard-glp1-psychiatric-both-directions.md

@@ -51,7 +51,7 @@ intake_tier: research-task
 **What I expected but didn't find:** Specific clinical screening criteria being adopted in the AUD trial context. The SEMALCO trial enrolled patients with AUD + obesity but the psychiatric screening criteria weren't prominently discussed in the results coverage.
 
 **KB connections:**
-- [[human-in-the-loop clinical AI degrades to worse-than-AI-alone because physicians both de-skill from reliance and introduce errors]] — same paradox structure: the intervention that appears safe in controlled populations creates new risks in real-world deployment
+- human-in-the-loop clinical AI degrades to worse-than-AI-alone because physicians both de-skill from reliance and introduce errors — same paradox structure: the intervention that appears safe in controlled populations creates new risks in real-world deployment
 - [[healthcare AI regulation needs blank-sheet redesign because the FDA drug-and-device model built for static products cannot govern continuously learning software]] — GLP-1 psychiatric safety monitoring faces the same challenge: the drug was approved for metabolic disease, being deployed in behavioral health without mental health-specific monitoring infrastructure
 
 **Extraction hints:**

inbox/queue/2026-05-03-eclinmed-glp1-alcohol-meta-analysis-5m-patients.md

@@ -63,7 +63,7 @@ intake_tier: research-task
 
 **KB connections:**
 - [[GLP-1 receptor agonists are the largest therapeutic category launch in pharmaceutical history but their chronic use model makes the net cost impact inflationary through 2035]] — this meta-analysis substantially expands the claim's scope; should trigger a claim enrichment or new claim
-- [[medical care explains only 10-20 percent of health outcomes because behavioral social and genetic factors dominate]] — Belief 2 complication: a pharmacological intervention at the biological mechanism level shows population-scale behavioral change
+- medical care explains only 10-20 percent of health outcomes because behavioral social and genetic factors dominate — Belief 2 complication: a pharmacological intervention at the biological mechanism level shows population-scale behavioral change
 
 **Extraction hints:**
 1. **High-priority claim candidate:** "GLP-1 receptor agonists reduce alcohol consumption and AUD risk across diverse populations with a 28-36% reduction in AUD-related outcomes, supported by a meta-analysis of 14 studies and 5.26M patients"

inbox/queue/2026-05-03-glp1-addiction-scope-oud-nicotine-cocaine-synthesis.md

@@ -63,7 +63,7 @@ intake_tier: research-task
 
 **KB connections:**
 - [[the mental health supply gap is widening not closing because demand outpaces workforce growth and technology primarily serves the already-served rather than expanding access]] — if GLP-1 can treat SUD pharmacologically via metabolic prescribers, it partially bypasses the specialist shortage
-- [[medical care explains only 10-20 percent of health outcomes because behavioral social and genetic factors dominate]] — Belief 2 complication: pharmacological modulation of reward circuits challenges the behavioral primacy of addiction treatment
+- medical care explains only 10-20 percent of health outcomes because behavioral social and genetic factors dominate — Belief 2 complication: pharmacological modulation of reward circuits challenges the behavioral primacy of addiction treatment
 
 **Extraction hints:**
 1. Do not write a claim yet — evidence is too fragmented across disorders to make a unified claim

inbox/queue/2026-05-03-lancet-psychiatry-swedish-glp1-mental-health-worsening-cohort.md

@@ -58,8 +58,8 @@ intake_tier: research-task
 
 **KB connections:**
 - [[social isolation costs Medicare 7 billion annually and carries mortality risk equivalent to smoking 15 cigarettes per day making loneliness a clinical condition not a personal problem]] — if GLP-1 reduces depression risk, it may address a second pathway to the loneliness/social health crisis
-- [[the mental health supply gap is widening not closing because demand outpaces workforce growth]] — if GLP-1 has antidepressant properties, it could expand behavioral health capacity via prescribers already in the metabolic medicine space
-- [[prescription digital therapeutics failed as a business model]] — GLP-1 may be doing what DTx failed to do: reaching mental health patients through non-psychiatric prescribing channels
+- the mental health supply gap is widening not closing because demand outpaces workforce growth — if GLP-1 has antidepressant properties, it could expand behavioral health capacity via prescribers already in the metabolic medicine space
+- prescription digital therapeutics failed as a business model — GLP-1 may be doing what DTx failed to do: reaching mental health patients through non-psychiatric prescribing channels
 
 **Extraction hints:**
 1. New claim candidate: "Semaglutide is associated with 44% lower risk of worsening depression in patients with pre-existing depression or anxiety, suggesting GLP-1 receptor agonism produces psychiatric protective effects beyond metabolic outcomes"

inbox/queue/2026-05-03-lancet-semalco-semaglutide-aud-rct-results.md

@@ -60,8 +60,8 @@ intake_tier: research-task
 
 **KB connections:**
 - [[GLP-1 receptor agonists are the largest therapeutic category launch in pharmaceutical history but their chronic use model makes the net cost impact inflationary through 2035]] — this finding extends GLP-1 beyond metabolic disease
-- [[the mental health supply gap is widening not closing because demand outpaces workforce growth]] — if GLP-1 treats AUD pharmacologically, it potentially bypasses the therapist workforce constraint
-- [[medical care explains only 10-20 percent of health outcomes because behavioral social and genetic factors dominate]] — requires qualification for addiction medicine subpopulation
+- the mental health supply gap is widening not closing because demand outpaces workforce growth — if GLP-1 treats AUD pharmacologically, it potentially bypasses the therapist workforce constraint
+- medical care explains only 10-20 percent of health outcomes because behavioral social and genetic factors dominate — requires qualification for addiction medicine subpopulation
 
 **Extraction hints:**
 1. New claim: "Semaglutide demonstrates superior AUD efficacy to all approved medications (NNT 4.3 vs 7+) in RCT, extending GLP-1 therapeutic scope from metabolic to behavioral health"

inbox/queue/2026-05-03-omada-glp1-flex-care-employer-market-context.md

@@ -58,8 +58,8 @@ Is behavioral data and outcomes data sufficient for defensibility, or does the t
 
 **KB connections:**
 - [[healthcares defensible layer is where atoms become bits because physical-to-digital conversion generates the data that powers AI care while building patient trust that software alone cannot create]] — Belief 4 test case
-- [[AI-native health companies achieve 3-5x the revenue productivity of traditional health services]] — Omada FY2025 data point
-- [[consumer willingness to pay out of pocket for AI-enhanced care is outpacing reimbursement creating a cash-pay adoption pathway]] — Flex Care is an employer-level version of the same dynamic
+- AI-native health companies achieve 3-5x the revenue productivity of traditional health services — Omada FY2025 data point
+- consumer willingness to pay out of pocket for AI-enhanced care is outpacing reimbursement creating a cash-pay adoption pathway — Flex Care is an employer-level version of the same dynamic
 
 **Extraction hints:**
 1. Not a standalone claim yet — need adoption data before claiming market validation

inbox/queue/2026-05-03-smc-expert-reactions-semalco-trial-caveats.md

@@ -55,8 +55,8 @@ intake_tier: research-task
 **What I expected but didn't find:** Discussion of what "Phase 3 trials underway" means specifically — design, timeline, sponsor. The trial NCT07223983 (SEMA for AUD after bariatric surgery) appeared in search but is a different design from the population-level Phase 3 needed.
 
 **KB connections:**
-- [[AI diagnostic triage achieves 97 percent sensitivity across 14 conditions making AI-first screening viable]] — contrast: AI achieves high evidence quickly, GLP-1 behavioral health requires careful phase progression
-- [[prescription digital therapeutics failed as a business model because FDA clearance creates regulatory cost without pricing power]] — GLP-1 AUD won't face the same model failure (it's a drug, not a DTx) but the reimbursement path for addiction indication is uncertain
+- AI diagnostic triage achieves 97 percent sensitivity across 14 conditions making AI-first screening viable — contrast: AI achieves high evidence quickly, GLP-1 behavioral health requires careful phase progression
+- prescription digital therapeutics failed as a business model because FDA clearance creates regulatory cost without pricing power — GLP-1 AUD won't face the same model failure (it's a drug, not a DTx) but the reimbursement path for addiction indication is uncertain
 
 **Extraction hints:**
 1. Use as the "limitations" section for any SEMALCO-based claim

inbox/queue/2026-05-03-vigibase-pharmacovigilance-glp1-psychiatric-signals.md

@@ -64,7 +64,7 @@ intake_tier: research-task
 
 **KB connections:**
 - [[GLP-1 receptor agonists are the largest therapeutic category launch in pharmaceutical history but their chronic use model makes the net cost impact inflationary through 2035]] — safety signal monitoring as market risk
-- [[Big Food companies engineer addictive products by hacking evolutionary reward pathways creating a noncommunicable disease epidemic]] — GLP-1 addresses food reward pathways; eating disorder risk in vulnerable individuals is the mechanistic flip side
+- Big Food companies engineer addictive products by hacking evolutionary reward pathways creating a noncommunicable disease epidemic — GLP-1 addresses food reward pathways; eating disorder risk in vulnerable individuals is the mechanistic flip side
 
 **Extraction hints:**
 1. No standalone claim yet — the evidence is too contradictory to write with confidence