Drew T 1eadbc73e9 docs(phase-23): 8-hour autonomous run — corpus-v3 + v3 + local serving; fleet 63.67->63.82% ...

The run (Drew away): built tools/serve_local.py (Unsloth GPU serving, replaces ejected LM
Studio); the prompt fix (translate-every-instruction, 0/3->2/3 on the empty-leaf class);
corpus-v3 (mine the 1623 engine_core.h DEFINE_func macros + struct types: 1312->2891 pairs,
2534+291 trainable); v3 trained (loss 1.275->0.085) eval 23/40 (57.5%); v3 production batch
banked ~352 fns + 45 new shared groups -> fleet 63.67->63.82% (+502 byte-identical), 136/136
byte-clean, 25 auto-commits, $0. v3 banks the empty-leaf/setter class v2 couldn't.

- docs/gen2-mips-matching-model.md: corpus-v3 + serving + prompt-fix + v3 eval + harvest
- docs/SETUP.md: LLM matching tier added to the Tooling inventory (R21)
- phase-ends/CURRENT_PHASE.md: run progress + next levers (reach>=2 targeting, dedup-collapse)

2026-06-30 07:36:33 -06:00

..

history

feat(phase-22): cheap-tier A/B experiment harness + findings

2026-06-29 12:52:39 -06:00

actor-struct.md

feat(phase-17): T4+T5 — actor struct recovered (comprehension) but byte-neutral for matching

2026-06-19 13:03:14 -06:00

automation-runbook.md

feat(phase-21): reach-1 harvest pivot — fuel built + handoff (×134 walls exhausted at 61.16%)

2026-06-22 21:22:35 -06:00

backlog.md

docs(phase-23): 8-hour autonomous run — corpus-v3 + v3 + local serving; fleet 63.67->63.82%

2026-06-30 07:36:33 -06:00

difficulty.md

feat(phase-11): T3 — intra-binary collapse PROOF (one body, two addresses, byte-identical)

2026-06-16 00:56:35 -06:00

difficulty.ov_SC01_005.md

docs(phase-13): T6 docs — cookbook §13 overlay runbook + SETUP/gen2-roadmap + digests

2026-06-16 17:56:38 -06:00

difficulty.ov_SC01_006.md

docs(phase-13): T6 docs — cookbook §13 overlay runbook + SETUP/gen2-roadmap + digests

2026-06-16 17:56:38 -06:00

difficulty.ov_SC01_077.md

feat(phase-19): T2 recovery tooling — canon_resident_calls + no-proto caller fix (3 matches)

2026-06-20 17:12:00 -06:00

difficulty.ov_SC03_001.md

docs(phase-13): T6 docs — cookbook §13 overlay runbook + SETUP/gen2-roadmap + digests

2026-06-16 17:56:38 -06:00

difficulty.resident.md

feat(phase-12): T3a — extern-conflict recovery, +20 (REAL 102->123, 85.6%)

2026-06-16 14:05:20 -06:00

duplicates.cross.md

feat(phase-15): T4 — fleet progress roll-up + fix cross-report double-count

2026-06-16 20:00:19 -06:00

duplicates.md

feat(phase-7): matching reports + 24 matches (38 real) — session A checkpoint

2026-06-14 17:36:12 -06:00

duplicates.ov_SC01_077.md

feat(phase-19): T2 recovery tooling — canon_resident_calls + no-proto caller fix (3 matches)

2026-06-20 17:12:00 -06:00

duplicates.resident.md

feat(phase-10): T4 — resident Ghidra program (2nd binary) + symbol seed + sig

2026-06-15 23:25:00 -06:00

effort-map.md

feat(phase-13): T7 — effort experiment (Max vs Ultracode yield = noise) + bank 14

2026-06-16 17:50:31 -06:00

exemplar_curriculum.md

feat(phase-20): T2 — exemplar_miner routes 835 residuals (WAVE 472 / PINS 45 reach-134 / STUB 90)

2026-06-20 23:55:51 -06:00

formats.md

docs(phase-12): T5 — save trace findings (memcard path + directory confirmed; deep data deferred)

2026-06-16 14:33:54 -06:00

gen2-mips-matching-model.md

docs(phase-23): 8-hour autonomous run — corpus-v3 + v3 + local serving; fleet 63.67->63.82%

2026-06-30 07:36:33 -06:00

gen2-roadmap.md

docs(phase-15): close — PhaseEnd v1.14.0 (fleet 54.48%), continuation backlog -> Phase 16

2026-06-18 21:01:38 -06:00

hand-matching-process.md

docs(phase-18): correct §17/§8e — register-order class is STEERABLE via pins (not unsteerable)

2026-06-20 12:33:08 -06:00

matching-cookbook.md

docs(phase-22): correct cookbook §28b-6 — the dedup_propagate registry-skip is independent of concurrent make (R14, per §28c)

2026-06-26 22:25:17 -06:00

memory-map.md

docs(phase-12): T4 — script/event system + SQV driver determinations (byte-backed)

2026-06-16 14:14:57 -06:00

progress.fleet.md

docs(phase-23): 8-hour autonomous run — corpus-v3 + v3 + local serving; fleet 63.67->63.82%

2026-06-30 07:36:33 -06:00

progress.md

feat(phase-15): T4 — fleet progress roll-up + fix cross-report double-count

2026-06-16 20:00:19 -06:00

progress.ov_SC01_005.md

docs(phase-13): T6 docs — cookbook §13 overlay runbook + SETUP/gen2-roadmap + digests

2026-06-16 17:56:38 -06:00

progress.ov_SC01_006.md

docs(phase-13): T6 docs — cookbook §13 overlay runbook + SETUP/gen2-roadmap + digests

2026-06-16 17:56:38 -06:00

progress.ov_SC01_077.md

feat(phase-19): T2 recovery tooling — canon_resident_calls + no-proto caller fix (3 matches)

2026-06-20 17:12:00 -06:00

progress.ov_SC03_001.md

docs(phase-13): T6 docs — cookbook §13 overlay runbook + SETUP/gen2-roadmap + digests

2026-06-16 17:56:38 -06:00

progress.resident.md

docs(phase-13): T6 docs — cookbook §13 overlay runbook + SETUP/gen2-roadmap + digests

2026-06-16 17:56:38 -06:00

proto-correspondence.md

feat(phase-3.5): prototype research spike — go/no-go (protos don't accelerate Gen1 matching)

2026-06-14 03:19:23 -06:00

psyq-worklist.md

feat(phase-12): T1 — resident PsyQ footprint survey = NIL (resident is custom engine code)

2026-06-16 11:05:22 -06:00

SETUP.md

docs(phase-23): 8-hour autonomous run — corpus-v3 + v3 + local serving; fleet 63.67->63.82%

2026-06-30 07:36:33 -06:00

struct-core-pivot.md

feat(phase-17): T4+T5 — actor struct recovered (comprehension) but byte-neutral for matching

2026-06-19 13:03:14 -06:00

wall-taxonomy.md

feat(phase-17): T3 — bank 42 sig_unify matches + propagate x134 (fleet 54.48%->55.00%); fix taxonomy classifier

2026-06-19 12:13:38 -06:00

worklist.md

chore(phase-22): refresh worklist after close=0 batch (441 live stubs, fleet 63.66%)

2026-06-26 04:15:54 -06:00