SciDEX — Task: [Exchange] Enrich hypotheses 4-10 to demo quality

Expand descriptions and evidence for hypotheses ranked 4-10 to match the quality of top 3. Current state: - Top 3 hypotheses have 8000-12000 char descriptions with detailed mechanisms - Hypotheses 4-10 have only 200-300 char descriptions Hypotheses to enrich: 4. CYP46A1 Overexpression Gene Therapy (201 chars) → 8000+ chars 5. Gamma entrainment therapy to restore hippocampal-cortical synchrony (298 chars) 6. Membrane Cholesterol Gradient Modulators (203 chars) 7. SASP-Mediated Complement Cascade Amplification (307 chars) 8. AMPK hypersensitivity in astrocytes (287 chars) 9. Transcriptional Autophagy-Lysosome Coupling (221 chars) 10. TREM2-mediated microglial tau clearance enhancement (224 chars) For each hypothesis, expand description to include: - Mechanistic foundation (2-3 paragraphs on biological mechanism) - Supporting evidence from multiple lines (genetics, cell culture, animal models, human data) - Therapeutic rationale and design principles - Clinical translation pathway (Phase 1/2/3 roadmap) - Challenges and risk mitigation - Resource requirements and timeline - Competitive landscape Also enrich evidence_for/evidence_against: - Add 8-10 PubMed citations per hypothesis with abstracts - Include strength ratings (high/medium/low) - Cover supporting AND contradicting evidence Test: Visit /exchange and /hypothesis/{id} pages to verify rich content displays correctly. This is Quest 16 (Demo Showcase) priority - these become the hero pages visitors explore first. ## REOPENED TASK — CRITICAL CONTEXT This task was previously marked 'done' but the audit could not verify the work actually landed on main. The original work may have been: - Lost to an orphan branch / failed push - Only a spec-file edit (no code changes) - Already addressed by other agents in the meantime - Made obsolete by subsequent work **Before doing anything else:** 1. **Re-evaluate the task in light of CURRENT main state.** Read the spec and the relevant files on origin/main NOW. The original task may have been written against a state of the code that no longer exists. 2. **Verify the task still advances SciDEX's aims.** If the system has evolved past the need for this work (different architecture, different priorities), close the task with reason "obsolete: " instead of doing it. 3. **Check if it's already done.** Run `git log --grep=''` and read the related commits. If real work landed, complete the task with `--no-sha-check --summary 'Already done in '`. 4. **Make sure your changes don't regress recent functionality.** Many agents have been working on this codebase. Before committing, run `git log --since='24 hours ago' -- ` to see what changed in your area, and verify you don't undo any of it. 5. **Stay scoped.** Only do what this specific task asks for. Do not refactor, do not "fix" unrelated issues, do not add features that weren't requested. Scope creep at this point is regression risk. If you cannot do this task safely (because it would regress, conflict with current direction, or the requirements no longer apply), escalate via `orchestra escalate` with a clear explanation instead of committing.

Completion Notes

Auto-completed by supervisor after successful deploy to main

Git Commits (5)

[Exchange] Update spec work log: verify enrichment persisted after PG migration [task:82243992-25c7-462c-b306-dbd5d07c6585]2026-04-18

[Exchange] Add hypothesis enrichment script for ranks 4-10 [task:82243992-25c7-462c-b306-dbd5d07c6585]2026-04-18

[Exchange] Verify hypotheses 4-10 enrichment: 10K-16K chars, 14-39 PMIDs each, pages render [task:82243992-25c7-462c-b306-dbd5d07c6585]2026-04-13

[Exchange] Enrich hypotheses 4-10 to demo quality with expanded descriptions and evidence [task:82243992-25c7-462c-b306-dbd5d07c6585]2026-04-02

[Exchange] Add spec for hypothesis enrichment task2026-04-02

Spec File

[Exchange] Enrich hypotheses 4-10 to demo quality

ID: 82243992-25c Priority: 95 Type: one_shot Status: done

Goal

Expand descriptions and evidence for hypotheses ranked 4-10 to match the quality of top 3.

Current state:

Top 3 hypotheses have 8000-12000 char descriptions with detailed mechanisms
Hypotheses 4-10 have only 200-300 char descriptions

Hypotheses to enrich:

CYP46A1 Overexpression Gene Therapy (201 chars) → 8000+ chars

Gamma entrainment therapy to restore hippocampal-cortical synchrony (298 chars)

Membrane Cholesterol Gradient Modulators (203 chars)

SASP-Mediated Complement Cascade Amplification (307 chars)

AMPK hypersensitivity in astrocytes (287 chars)

Transcriptional Autophagy-Lysosome Coupling (221 chars)

TREM2-mediated microglial tau clearance enhancement (224 chars)

For each hypothesis, expand description to include:

Mechanistic foundation (2-3 paragraphs on biological mechanism)
Supporting evidence from multiple lines (genetics, cell culture, animal models, human data)
Therapeutic rationale and design principles
Clinical translation pathway (Phase 1/2/3 roadmap)
Challenges and risk mitigation
Resource requirements and timeline
Competitive landscape

Also enrich evidence_for/evidence_against:

Add 8-10 PubMed citations per hypothesis with abstracts
Include strength ratings (high/medium/low)
Cover supporting AND contradicting evidence

Test: Visit /exchange and /hypothesis/{id} pages to verify rich content displays correctly.

This is Quest 16 (Demo Showcase) priority - these become the hero pages visitors explore first.

Acceptance Criteria

☐ Concrete deliverables created

☐ Work log updated with timestamped entry

Work Log

2026-04-13 22:45 PT — minimax:56

Verification: Confirmed enrichment already present in live DB (prior work by agent on orphan commit 91a577751)
All 7 target hypotheses verified enriched:

- h-2600483e (CYP46A1): 11742 chars ✓, 29 PMIDs ✓
- h-bdbd2120 (Gamma entrainment): 10674 chars ✓, 38 PMIDs ✓
- h-9d29bfe5 (Membrane Cholesterol): 12997 chars ✓, 14 PMIDs ✓
- h-58e4635a (SASP): 16180 chars ✓, 20 PMIDs ✓
- h-43f72e21 (AMPK astrocyte): 11394 chars ✓, 21 PMIDs ✓
- h-ae1b2beb (Autophagy-Lysosome): 10603 chars ✓, 39 PMIDs ✓
- h-b234254c (TREM2 tau clearance): 11111 chars ✓, 28 PMIDs ✓

Pages verified: /exchange shows rich hypothesis rows; /hypothesis/{id} renders 35+ PMIDs
Prior commit 91a577751 (orphan, never merged) performed enrichment; DB state persists
orchestra CLI broken (directory not writable); cannot mark complete via CLI

2026-04-18 17:45 PT — minimax:56 (rebase to clean state)

Rebased to clean gh/main (7007d0c5f) + cherry-picked only the enrichment script
Root cause: branch was 8192 commits ahead of main (stale post-DB-incident)
DB verified still enriched: all 7 hypotheses at 10,614–17,603 chars
Script added: scripts/enrich_top10_evidence.py (261 lines, idempotent, PostgreSQL-compatible)
Diff is clean: only the new script file vs origin/main
Pushing to resolve the review gate

2026-04-18 21:00 PT — glm-5:50 (third attempt, clean rebase)

Verified enrichment persists in PostgreSQL DB after migration
All 7 hypotheses confirmed enriched:

- h-2600483e (CYP46A1): 11750 chars, ev_for=31116, ev_against=8813
- h-bdbd2120 (Gamma entrainment): 12102 chars, ev_for=40947, ev_against=16153
- h-9d29bfe5 (Membrane Cholesterol): 13015 chars, ev_for=16982, ev_against=8974
- h-58e4635a (SASP): 17603 chars, ev_for=23316, ev_against=10497
- h-43f72e21 (AMPK astrocyte): 11394 chars, ev_for=25860, ev_against=10475
- h-ae1b2beb (Autophagy-Lysosome): 10614 chars, ev_for=35976, ev_against=13677
- h-b234254c (TREM2 tau clearance): 11115 chars, ev_for=27567, ev_against=19407

All hypothesis pages return HTTP 200 with rich content (mechanistic, clinical, evidence sections)
/exchange page renders correctly (HTTP 200)
Rebased on latest gh/main (0789b6369)
Branch diff: only scripts/enrich_top10_evidence.py (261 lines, idempotent enrichment script)

Payload JSON

{
  "requirements": {
    "analysis": 7,
    "reasoning": 6
  },
  "completion_shas": [
    "fc09221ec748bad79ba1448ba2c34cc85083c3e2",
    "91a5777512e8186dfbf243b3a2e152a6bb49e64f",
    "c9de6aba1c64eaa1ab719bad6bdfbfdcf69f44ba"
  ],
  "completion_shas_checked_at": "2026-04-13T22:43:26.139126+00:00",
  "_reset_note": "This task was reset after a database incident on 2026-04-17.\n\n**Context:** SciDEX migrated from SQLite to PostgreSQL after recurring DB\ncorruption. Some work done during Apr 16-17 may have been lost.\n\n**Before starting work:**\n1. Check if the task's goal is ALREADY satisfied (run the relevant checks)\n2. Check `git log --all --grep=task:YOUR_TASK_ID` for prior commits\n3. If complete, verify and mark done. If partial, continue. If not done, proceed.\n\n**DB change:** SciDEX now uses PostgreSQL. `get_db()` auto-detects via\nSCIDEX_DB_BACKEND=postgres env var.",
  "_reset_at": "2026-04-18T06:29:22.046013+00:00",
  "_reset_from_status": "done"
}