Experiment ·
SEARCHPORT P1
Does porting SEFIX-124 + head pass + X2b make the right chunk reach the 1.7B without health or safety changes?
AI-reviewed, not clinically reviewed. Nothing here is medical advice.
From the record
- What was tested
- SEARCHPORT P1 (bench search fixes in the native engine)
- Result
- MAIN 26 → 40, ST 38 → 64, context 1.07×; 3 new dose-figure probes
- Verdict
- closed: rule failed, CI excluded the hoped-for gain, a step-0 gate failed, or the mechanism was falsified
- Detail
- FAIL gate d (safety) after the one fix; switch off
- Set
- MAIN 92 keyed; 180 pack self-tests; 65 F3-SAFETY probes (dev)
- Judge
- replay (0 LLM); regex count
- n
- 92 + 180 + 65
- Seeds
- 1 (42)
- Pre-registered
- yes (fa3b1144)
Linked facts · 2
- SEARCHPORT baseline B0 (native engine 078a2627 with the APK's pack kit and factbook v1, 0 LLM): 26 of 92 keyed MAIN facts delivered at chunk level; own fact chunk kept on 38 of 180 pack self-tests; kept-context p50 347 t…SEARCHPORT baseline B0 (native engine 078a2627 with the APK's pack kit and factbook v1, 0 LLM): 26 of 92 keyed MAIN facts delivered at chunk level; own fact chunk kept on 38 of 180 pack self-tests; kept-context p50 347 tokens; retrieval p50 211 ms on a laptop; recorded before any port code was evaluatedMAIN 26 / 92; ST 38 / 180; context p50 347 tokensSetMAIN 92 keyed (dev); 180 pack self-tests (pack-written)StatusdevJudgereplay (0 LLM)n92 keyed MAIN items; 180 self-testsSeedsnot recordedDate2026-10-24 18:34Sourcenot in the public repositories yetOpen the data file
- SEARCHPORT P1 (the bench search fixes SEFIX-124 + head pass + X2b appends, ported to the native engine) failed its frozen safety gate (d) after the one allowed fix: delivery MAIN 26 → 40 (+14, 0 lost), own fact chunk 38 …SEARCHPORT P1 (the bench search fixes SEFIX-124 + head pass + X2b appends, ported to the native engine) failed its frozen safety gate (d) after the one allowed fix: delivery MAIN 26 → 40 (+14, 0 lost), own fact chunk 38 → 64, 0 health-family losses, context p50 1.07×, but 3 probe answers gained a dose figure copied from an appended first-aid or health Q&A passage; the port stays in the code with its switch offMAIN 26 → 40; ST 38 → 64; context 1.07×; 3 new dose-figure probesSetMAIN 92 keyed; 180 pack self-tests; 65 F3-SAFETY probes (dev)StatusdevJudgereplay (0 LLM); regex count on answersn92 keyed MAIN; 180 self-tests; 65 probesSeeds1 (42) for the probe answersDate2026-10-24 18:34CaveatPorted unchanged, the appends doubled the native prompt (context 2.33×, gate c); the one fix compressed appends with the retrieved passages within 1.2× (MAIN 47 → 40). Criterion frozen before any port code (sha fa3b1144). Health content: AI-reviewed, not clinically reviewed. Nothing here is medical advice.Sourcenot in the public repositories yetOpen the data file