textmachine/eval/tenant_panel
2026-08-16 22:27:32 +03:00
..
bank.py Scope the bank stem rule, manual lists and display to the pair so short Latin names stop matching unrelated Russian words 2026-08-14 16:00:04 +03:00
checks21.py Freeze the phase 0 and 1 pre-registration of experiment 22 with its harness, ledger and thresholds before any paid call 2026-08-08 15:14:14 +03:00
contam.py Freeze the phase 0 and 1 pre-registration of experiment 22 with its harness, ledger and thresholds before any paid call 2026-08-08 15:14:14 +03:00
editors.py Re-freeze phase 3 for the slow mandatory candidate: hard per-model timeout, no client retries, declared unit subset 2026-08-08 22:26:30 +03:00
itog22.py Fix packs 22/23 rigs and reports per acceptance 16 and three adversarial review lines: exact sign test, word-boundary bank regex, judge attribution, coverage guard 2026-08-10 07:05:55 +03:00
judge.py Fix packs 22/23 rigs and reports per acceptance 16 and three adversarial review lines: exact sign test, word-boundary bank regex, judge attribution, coverage guard 2026-08-10 07:05:55 +03:00
material.py Freeze editor-tier phase A: pack roster with vendor-verified prices, configurable ledger, unit pinning by manifest, and screen reusing exp-22 thresholds 2026-08-09 02:44:28 +03:00
money.py Freeze editor-tier phase A: pack roster with vendor-verified prices, configurable ledger, unit pinning by manifest, and screen reusing exp-22 thresholds 2026-08-09 02:44:28 +03:00
panel.py Re-freeze the phase 2 floor stage so its two end-to-end runs and their units can be split across processes 2026-08-08 20:58:50 +03:00
prompts.py Freeze the phase-D harness before the en-axis purchases: pair provider, wired rig hooks, pinned unit manifests, pair terminologist prompts and the paid contamination path 2026-08-14 14:17:42 +03:00
roster.py Re-pin DeepSeek to the post-cutover peak price after the vendor switched to time-based billing 2026-08-16 22:27:32 +03:00
screen.py Re-freeze phase 1 tail: raise its ceiling to the owner-approved figure and align the markdown gate with the production sanitizer 2026-08-08 17:59:20 +03:00
sol.py Fix packs 22/23 rigs and reports per acceptance 16 and three adversarial review lines: exact sign test, word-boundary bank regex, judge attribution, coverage guard 2026-08-10 07:05:55 +03:00
verify22.py Fix packs 22/23 rigs and reports per acceptance 16 and three adversarial review lines: exact sign test, word-boundary bank regex, judge attribution, coverage guard 2026-08-10 07:05:55 +03:00