Commit Graph

258 Commits

Author SHA1 Message Date
1f32ae217e Harden strong fidelity pilot validation 2026-07-14 13:39:38 +08:00
4ad699ef97 Report fidelity pilot covariate shift 2026-07-14 13:38:32 +08:00
12d1d4ad02 Make fidelity simulator tools self-contained 2026-07-14 13:29:38 +08:00
a3b25f4a92 Add simulator-aware fidelity pilot audit 2026-07-14 13:28:16 +08:00
23142aa359 Strengthen fidelity calibration baseline 2026-07-14 13:08:45 +08:00
93daf291f6 Fix prefix pilot warmup validation 2026-07-14 12:58:01 +08:00
8eeba597b3 Fix pilot burn-in selection manifest 2026-07-14 12:52:00 +08:00
16239bef00 Add fidelity-aware verification pilot 2026-07-14 12:49:53 +08:00
57dd6a9fac Record static-policy oracle gap refutation 2026-07-14 02:18:44 +08:00
16177b0045 Close shifted oracle frontier boundaries 2026-07-14 00:32:09 +08:00
0f891d99c9 Generalize oracle transport retry rule 2026-07-14 00:00:24 +08:00
d3bc63a972 Quarantine transport-invalid oracle trial 2026-07-13 23:16:04 +08:00
a9e7e9991e Extend oracle gap P06 bracket 2026-07-13 22:21:17 +08:00
34e1f4c144 Add static-policy oracle gap experiment 2026-07-13 20:25:44 +08:00
a730b368d6 Document CollectiveSpec P2 no-go gate 2026-07-13 18:47:31 +08:00
5359463652 Record CollectiveSpec P0 no-go evidence 2026-07-13 18:11:32 +08:00
bb698b5de1 Avoid duplicate TP accounting in P0 padding summary 2026-07-13 18:09:54 +08:00
08de0695e0 Correct CollectiveSpec P0 phase accounting 2026-07-13 18:08:52 +08:00
7f4ae1708b Trace P0 batch-level DP coordination 2026-07-13 17:45:08 +08:00
f1cd859eea Add CollectiveSpec P0 phase trace harness 2026-07-13 17:33:01 +08:00
e6246a4c19 Flag invalid grid records in sanity checks 2026-07-13 17:22:32 +08:00
f56ecad64d Harden trace replay measurement integrity 2026-07-13 17:17:30 +08:00
5ae0525611 Add window-scoped session closure fallback 2026-07-13 16:23:38 +08:00
eb67212b17 Tighten CollectiveSpec system research gates 2026-07-13 16:05:43 +08:00
8d9a1d2b57 Verify session closure in controlled trace materialization 2026-07-13 15:50:51 +08:00
9b3a2eab80 Add reproducible CollectiveSpec opportunity screen 2026-07-13 15:09:01 +08:00
6db7308558 Add SimFid+OpProf campaign overview
Entry-point summary of both closed campaigns: verdicts, corrected
readings (P5 supersedes P3's P10-vs-P04 magnitude), methodological
findings (co-location SLO validity, arrival uniformization, compile-
factor env poisoning), artifact map, and GPU accounting.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-13 11:06:12 +08:00
46d15f0e13 Add simulator fidelity review of Frontier baseline
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-13 11:06:11 +08:00
d5b276180d Add OpProf campaign: protocols, results, patches, run evidence (P0-P6)
Workload-conditioned operator profiling on patched vLLM 0.24.0 +
Qwen3-30B-A3B/H20. H1b PASS (irregular patterns carry +23-45pp R64
raggedness, 8-45% token-efficiency loss vs rectangular controls);
mechanism decomposition kills the padding narrative and finds the
arrival-uniformization artifact (-12.9%); cross-version churn surface
shows TP2/MNS64 -29.4% across vLLM 0.20->0.24 while the argmax held.
Raw Layer-1 JSONL streams (507 MB) stay on disk, git-ignored; footer
sidecars and metrics are tracked.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-13 11:06:10 +08:00
607e88da3c Ignore raw run telemetry, ruff cache, and recovered stores
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-13 11:05:35 +08:00
7ba98b6087 Add knob conditional effect figures 2026-07-06 13:19:09 +08:00
cb89549334 Add MaaS collaboration overview 2026-07-06 13:19:00 +08:00
d8899c50ce Add interaction screening matrix generator 2026-07-01 14:43:29 +08:00
46b477f48e Add initial config preflight review 2026-07-01 11:12:58 +08:00
1b8f5a3af1 Integrate descriptor runtime candidates into harness 2026-06-30 14:10:19 +08:00
adb5356c4b Add advisory harness attribution and descriptor planner MVP 2026-06-30 12:05:03 +08:00
08429e5da8 Refine harness design flow overview 2026-06-29 20:41:54 +08:00
00ba573631 Document harness design contract 2026-06-29 20:26:58 +08:00
6ea259a0a3 Keep target topology explicit in delta projections 2026-06-29 19:56:50 +08:00
6b4efdad82 Relax lower-frontier delta projection gate 2026-06-29 17:57:29 +08:00
9ef9550214 Use full state for frontier projection 2026-06-29 16:22:09 +08:00
8dd9ada194 Add frontier delta projection harness candidates 2026-06-29 16:15:06 +08:00
6c84dc91d7 Document hardened topology feedback 2026-06-29 02:34:12 +08:00
1c4ed4cab3 Document hardened harness feedback 2026-06-29 02:28:30 +08:00
6b25d56c1f Gate GMU climb on measured improvement 2026-06-29 02:00:41 +08:00
ee101a7c24 Harden prefill scheduler harness 2026-06-29 01:54:02 +08:00
bfd85793f3 Prioritize uncovered prefill scheduler candidates 2026-06-29 01:30:34 +08:00
36c301c128 Add normalized prefill scheduler harness 2026-06-29 01:12:19 +08:00
7ad439730e Add llm-first tuning proposal policy 2026-06-27 12:21:51 +08:00
9accf2575e Require harness proposals from candidate sets 2026-06-27 01:03:30 +08:00