wassnameandClaude Opus 4.7 48d8ca5576 add 08_multibool_baseline: run multibool eval over classic vignettes ...

Sanity check + baseline before wiring multibool into the steering sweep.
Computes per-foundation logratios on all 132 classic vignettes, dumps to
data/results/multibool_baseline.jsonl, prints per-foundation lr summary
and Spearman corr against human-rater %s.

SHOULD: mean pmass > 0.9; Spearman ρ > 0.3 on ≥4/6 foundations.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-05 22:20:48 +08:00

..

01_download.py

init

2026-04-30 17:10:09 +08:00

02_rewrite.py

Implement N-token evaluation with guided rollouts

2026-05-01 21:44:14 +08:00

02a_backfill_labels.py

add human labels

2026-05-02 15:58:08 +08:00

03_eval.py

Implement N-token evaluation with guided rollouts

2026-05-01 21:44:14 +08:00

04_validate.py

decent

2026-04-30 21:22:07 +08:00

05_drift.py

decent

2026-04-30 21:22:07 +08:00

05_upload_hf.py

docs: use simple emoji links for cross-referencing github and huggingface

2026-05-03 12:58:24 +08:00

06_consistency.py

fix airisk self_violate actor archetype + simplify to 2 conditions

2026-04-30 21:29:38 +08:00

07_multilabel.py

feat: multi-label moral foundation ratings with z-scored frame averaging and human calibration

2026-05-03 12:48:14 +08:00

07a_merge_labels.py

chore: remove uncalibrated raw LLM columns from final vignettes

2026-05-03 12:55:00 +08:00

07b_review.py

chore: remove uncalibrated raw LLM columns from final vignettes

2026-05-03 12:55:00 +08:00

08_multibool_baseline.py

add 08_multibool_baseline: run multibool eval over classic vignettes

2026-05-05 22:20:48 +08:00

smoke_batch_parity.py

batch the eval: guided_rollout_batch + 4× speedup

2026-05-03 06:42:17 +08:00