textmachine/eval/dovodka
2026-08-14 16:27:17 +03:00
..
judge-prompts Rename judge prompt paths to ASCII: Cyrillic names render as octal escapes in the shell and break completion and greps 2026-08-11 18:43:31 +03:00
adjud.py Fix three acceptance defects in the D4 summary: decoy rebuilt with this pack's plants, three axes per arm as the order requires, two inadmissible packets annulled 2026-08-14 03:42:24 +03:00
canon.py Freeze phase D pre-registration: hypotheses verbatim, Holm-corrected power with declared families, equivalence margin, measured budget, cash desk, ja pair pack 2026-08-10 07:06:07 +03:00
contam_d.py Fix the contamination scorer to accept Russian renderings of names and titles, and add a refill mode for cells truncated by the reasoning budget 2026-08-14 15:19:20 +03:00
contour.py Freeze the en axis driver before its purchases: pre-registered E-arm names mapped to shared contour kinds, phase-scoped tags and fresh bases on the reworked pair prompts 2026-08-14 16:27:17 +03:00
en_axis.py Freeze the en axis driver before its purchases: pre-registered E-arm names mapped to shared contour kinds, phase-scoped tags and fresh bases on the reworked pair prompts 2026-08-14 16:27:17 +03:00
itog_d4.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
material_ja.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
money_d.py Raise the pack ceiling to 6.15 on the owner's sanction, funding the A1B re-buy that a session defect made necessary 2026-08-11 11:30:03 +03:00
para.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
paritet.py Rename judge prompt paths to ASCII: Cyrillic names render as octal escapes in the shell and break completion and greps 2026-08-11 18:43:31 +03:00
plan.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
power.py Add the phase D judging harness: floor halves split across sessions, a margin decoy sized by measurement, isolated task dir and a transcript audit 2026-08-11 12:46:45 +03:00
promptdiff.py Freeze phase D pre-registration: hypotheses verbatim, Holm-corrected power with declared families, equivalence margin, measured budget, cash desk, ja pair pack 2026-08-10 07:06:07 +03:00
requirements.md Freeze phase D pre-registration: hypotheses verbatim, Holm-corrected power with declared families, equivalence margin, measured budget, cash desk, ja pair pack 2026-08-10 07:06:07 +03:00
runs.py Freeze phase D pre-registration: hypotheses verbatim, Holm-corrected power with declared families, equivalence margin, measured budget, cash desk, ja pair pack 2026-08-10 07:06:07 +03:00
sessii.py Rename judge prompt paths to ASCII: Cyrillic names render as octal escapes in the shell and break completion and greps 2026-08-11 18:43:31 +03:00
spanjoin.py Add the span-join between the judge and deterministic axes, and blind adjudication with agreeableness and sensitivity controls 2026-08-14 02:00:17 +03:00
sud.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