Hanashi e90f64b30e bench: results summarizer (mean±std tables); rebuild CSVs from authoritative JSONL ...

The CSV header predated the ref_count column so later rows were misaligned;
JSONL rows were always complete.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

2026-08-06 13:51:17 -04:00

..

4000

bench: results summarizer (mean±std tables); rebuild CSVs from authoritative JSONL

2026-08-06 13:51:17 -04:00

4090

bench: results summarizer (mean±std tables); rebuild CSVs from authoritative JSONL

2026-08-06 13:51:17 -04:00

minimax_bench.py

bench: survive server loss during polling (mark run failed, keep suite alive)

2026-08-06 03:48:37 -04:00

results.csv

bench: results summarizer (mean±std tables); rebuild CSVs from authoritative JSONL

2026-08-06 13:51:17 -04:00

results.jsonl

bench: results summarizer (mean±std tables); rebuild CSVs from authoritative JSONL

2026-08-06 13:51:17 -04:00

summarize.py

bench: results summarizer (mean±std tables); rebuild CSVs from authoritative JSONL

2026-08-06 13:51:17 -04:00