core/docs/analysis
Shay c31bc82621 docs: third leg — candidate-graph builds 0 admissible candidates on held-out
All three GSM8K paths exhausted on the held-out 500:
- candidate-graph (sound filter): 0 admissible candidates built (498/500 build nothing)
- composer (open): 87 wrong
- narrow reader (open): 61 wrong
The sound path is wrong=0 only because it constructs no reading to commit. No sound
lift exists in the current substrate; confirmed empirically, three ways.
2026-06-04 02:49:00 -07:00
..
composition-capability-scope.md docs: mark ADR-0174 Phase 5a shipped in composition-capability-scope 2026-06-03 16:23:53 -07:00
composition-wall-execution-plan-2026-06-03.md feat(r4): flip cv-0005 to serving — train_sample 6/44/0 -> 7/43/0 (ADR-0207 §5 step 2) 2026-06-03 22:20:12 -07:00
comprehension-primitive-inventory.md Add canonical composition analysis docs 2026-06-03 15:35:58 -07:00
extraction-richness-audit-2026-06-03.md docs: ratify ADR-0207 — GSM8K comprehension/composition substrate 2026-06-03 19:42:47 -07:00
gsm8k-lift-program-strategy-2026-06-04.md fix(gsm8k): disable unsound serving bridges — restore sealed wrong=0 (0/5 -> 0/0) 2026-06-04 01:55:05 -07:00
question-layer-gap-survey.md Harden no-reference n-times comparative guard 2026-06-03 15:22:42 -07:00
real-gsm8k-capability-measurement-2026-06-04.md docs: third leg — candidate-graph builds 0 admissible candidates on held-out 2026-06-04 02:49:00 -07:00
solver-operation-coverage.md Harden no-reference n-times comparative guard 2026-06-03 15:22:42 -07:00
wiring-promotion-gate-brief-2026-06-03.md docs: composition-wall execution scope (ADR-0207 §5 step 2) 2026-06-03 21:14:02 -07:00