Experiment ·
HEADPASS-X3
Cross-encoder reranker choosing the appended chunks on the HEADPASS path (X3a reranker-only, X3b X1 + reranker; bge-reranker-v2-m3 over BM25 ∪ dense ∪ top-article candidates, under the X2b token budget)
AI-reviewed, not clinically reviewed. Nothing here is medical advice.
From the record
- What was tested
- Cross-encoder reranker choosing the appended chunks on the HEADPASS path
- Result
- reach 111/109 vs 117; 21.4 s/item
- Verdict
- closed: rule failed, CI excluded the hoped-for gain, a step-0 gate failed, or the mechanism was falsified
- Detail
- FAIL at step 0 (reach below the power bar; device cost rules out a default)
- Set
- 180 self-tests replays + v0.1/v0.2 kit no-harm; 0 judge calls; reranker latency timed
- Judge
- none (deterministic gate)
- Pre-registered
- see registry row
- Reopen if
- a reranker ≤ 1 s/item on device with the health-strict rule applied before ranking; M2 (pack-agnostic rerank under many packs: article kept 41 → 64, 3.9 s/item, 9 emptied contexts) parked as a declared variant
Linked facts · 2
- R74 Reranker-chosen append (X3): replayR74 Reranker-chosen append (X3): replayreach 111/109 vs 117; 21.4 s/itemKinda record, not a measurement (set, status, judge, n, seeds, date: not recorded)Caveatwhy closed: step-0 FAILSourceresearch record
reports/CLOSED.md:103Open the data file - HEADPASS-X3: cross-encoder reranker picks appended chunks → 111/109 vs 117; 3.9 s/item (slower and below the bar)HEADPASS-X3: cross-encoder reranker picks appended chunks → 111/109 vs 117; 3.9 s/item (slower and below the bar)Kinda record, not a measurement (set, status, judge, n, seeds, date: not recorded)Sourcenot in the public repositories yetOpen the data file