textmachine/eval/dovodka
2026-08-11 18:43:31 +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
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 Freeze judge wrappers built from one shared core with a mechanical parity gate, plus reproducible session layout keeping floor halves in different sessions 2026-08-11 14:53:34 +03:00
contour.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
material_ja.py Freeze phase D pre-reg erratum and harness repair: A2 arm built, battery wired with violation whitelist, per-contrast power with Student quantile, guard is a real stop 2026-08-11 03:18:37 +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
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 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
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
sud.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