Day 40 of 78 · Run #30 · 2026-09-28
uncentered consensus_w single-variable ablation — overall +0.1178 (rank 455/1202), regression; common-response centering is load-bearing
Overall score 0.118 · Perturbation discrimination (pds) 0.580 · +5 more
Audit & metrics Overall score 0.118 · Perturbation discrimination (pds) 0.580 · +5 more
No audit flags.
Differential expression volcano plot (log2FC vs -log10 p)
Pre-registered hypotheses (1)
- common-response centering is incidental to the consensus gain (falsified)
Evidence Literature & entity enrichment
Literature
0 genesTavily · auxiliary, not scored
Literature pending — run tools/enrich_literature.py.
Field context
VCC / perturbation researchField research pending — run tools/enrich_newsroom.py.
Biomedical NER
0 entitiesPioneer GLiNER2 · fine-tuned on Tavily literature when available · regex fallback offline
NER pending — run tools/pioneer_ner.py --train once, then tools/pioneer_ner.py --run experiments/<run-id>.
Narrative digest run digest · traces to facts.json
Narrative pending — run tools/render_narrative.py.
Trust & provenance Self-tests + reproduce command
6 pipeline steps · sourced from committed artifacts only
No metrics CSVs found — run cell-eval and commit results.
Ran 5 deterministic rules · 0 flags raised (none fired).
Literature enrichment not yet run — execute tools/enrich_literature.py.
NER extraction not yet run — execute tools/pioneer_ner.py.
Narrative not yet generated — execute tools/render_narrative.py.
Verification artifacts not yet committed — run planted_signal.py, holo_audit.py, check_narrative.py.