All workflows

Workflow runs

• deploy: HF Space live URL synced repo→v29 (live + repo + UI captions …

  failed:
  CI#48:Commitfbb9e24pushedbybrownjuly2003-code
  main

  May 24, 202616s
  More actions for workflow run 48

• eval+docs: v29 residue saturation evidence — 3-model helallao reasoni…

  failed:
  CI#47:Commit40ac2a1pushedbybrownjuly2003-code
  main

  May 24, 202621s
  More actions for workflow run 47

• docs: drop stale GraceKelly browser-orchestrator entry from NEXT_SESSION

  failed:
  CI#46:Commitb6aed93pushedbybrownjuly2003-code
  main

  May 24, 202617s
  More actions for workflow run 46

• test+style: pin rescore_arcwise pred-exec routing + drop stale mypy r…

  failed:
  CI#45:Commitc6e5394pushedbybrownjuly2003-code
  main

  May 24, 202620s
  More actions for workflow run 45

• tool+docs: rescore_arcwise pred-exec switched to execute_readonly — v…

  failed:
  CI#44:Commitc74b46cpushedbybrownjuly2003-code
  main

  May 24, 202618s
  More actions for workflow run 44

• eval+docs: v29 Arcwise rescore — 74.37% sql_only (148/199) / +7 catches

  failed:
  CI#43:Commitb208af4pushedbybrownjuly2003-code
  main

  May 24, 202616s
  More actions for workflow run 43

• eval+tools: v29 93.0% via targeted P3.F schema-link hint for qid 1275

  failed:
  CI#42:Commit5792045pushedbybrownjuly2003-code
  main

  May 24, 202620s
  More actions for workflow run 42

• eval+tools: v28 92.5% via targeted P3.F schema-link hint for qid 408

  failed:
  CI#41:Commit3b721eapushedbybrownjuly2003-code
  main

  May 24, 202620s
  More actions for workflow run 41

• docs: add cold-pickup checklist + P3.F rescue cookbook to NEXT_SESSION

  failed:
  CI#40:Commit72b7a21pushedbybrownjuly2003-code
  main

  May 24, 202621s
  More actions for workflow run 40

• docs: sync eval methodology + next-session plan to v27

  failed:
  CI#39:Commit92c52f4pushedbybrownjuly2003-code
  main

  May 24, 202617s
  More actions for workflow run 39

• eval+tools: v27 92.0% via two targeted P3.F schema-link hints for qid…

  failed:
  CI#38:Commit99bae66pushedbybrownjuly2003-code
  main

  May 24, 202618s
  More actions for workflow run 38

• eval+tools: v26 91.0% via targeted P3.F schema-link hint for qid 1531

  failed:
  CI#37:Commit2b06554pushedbybrownjuly2003-code
  main

  May 24, 20261m 34s
  More actions for workflow run 37

• eval+tools: v25 90.5% via targeted P3.F schema-link hint for qid 902

  failed:
  CI#36:Commitafac149pushedbybrownjuly2003-code
  main

  May 24, 202616s
  More actions for workflow run 36

• eval+tools: archive sweep against v24 misses closed NEGATIVE (0/20 re…

  failed:
  CI#35:Commit9252d74pushedbybrownjuly2003-code
  main

  May 24, 202616s
  More actions for workflow run 35

• eval+docs: v23 89.5% + v24 90.0% via archive sweep + archive rescore …

  failed:
  CI#34:Commitb58187bpushedbybrownjuly2003-code
  main

  May 24, 202617s
  More actions for workflow run 34

• script: run_selfcon_retry.py — add --gen-model + --sleep-between args

  failed:
  CI#33:Commitf4117b1pushedbybrownjuly2003-code
  main

  May 18, 202618s
  More actions for workflow run 33

• eval: v17-extended quintuple-saturation на v16 residue (Groq RU-geobl…

  failed:
  CI#32:Commitdde4d76pushedbybrownjuly2003-code
  main

  May 18, 202617s
  More actions for workflow run 32

• eval: v17-attempts triple-cross-validate 85.5% saturation on v16 residue

  failed:
  CI#31:Commitfcf38a9pushedbybrownjuly2003-code
  main

  May 18, 202622s
  More actions for workflow run 31

• fix+eval: v16-audit-2 — compare_results Counter→set (BIRD-official …

  failed:
  CI#30:Commit628003bpushedbybrownjuly2003-code
  main

  May 18, 202617s
  More actions for workflow run 30

• ui: trim BIRD caption + add hover tooltips для технических терминов (…

  failed:
  CI#29:Commitdb9db1fpushedbybrownjuly2003-code
  main

  May 18, 202618s
  More actions for workflow run 29

• fix+eval: v16-audit 85.5%→85.0% honest EA (SQLAlchemy bind-bug в _exe…

  failed:
  CI#28:Commit8aa7544pushedbybrownjuly2003-code
  main

  May 18, 202617s
  More actions for workflow run 28

• feat+eval: v16 85.5% EA via DAC×reasoning combo on v15 residue (+0.5p…

  failed:
  CI#27:Commitb57a2e4pushedbybrownjuly2003-code
  main

  May 18, 202619s
  More actions for workflow run 27

• feat+eval: v15 85.0% EA via helallao Pro-triplet retry on v14 residue…

  failed:
  CI#26:Commit0fca152pushedbybrownjuly2003-code
  main

  May 18, 202619s
  More actions for workflow run 26

• feat+eval: v14 84.5% EA via kimi-k2-thinking reasoning (+0.5pp, above…

  failed:
  CI#25:Commitc6b4378pushedbybrownjuly2003-code
  main

  May 18, 202617s
  More actions for workflow run 25

• feat+eval: v13 84.0% EA via helallao reasoning-mode (+2pp, above #1 p…

  failed:
  CI#24:Commitef25f52pushedbybrownjuly2003-code
  main

  May 17, 202622s
  More actions for workflow run 24