wassname 8353897780 scenarios: register BullshitBench for credulity screening

2026-07-26 10:23:55 +08:00

..

corpus

scenarios: register BullshitBench for credulity screening

2026-07-26 10:23:55 +08:00

report

refactor: sort scripts/ by who runs it

2026-07-25 10:23:22 +08:00

bounded_thinking_judge_liveproof.py

Run persona validation through Inspect AI

2026-07-18 19:09:02 +08:00

bounded_thinking_judge.py

Run persona validation through Inspect AI

2026-07-18 19:09:02 +08:00

export_selections.py

Simplify persona scenario and template selection

2026-07-18 10:48:35 +08:00

export_steering_selection.py

refactor: drop orphaned prepare_authority script, rename export to be axis-neutral

2026-07-25 10:11:53 +08:00

parse_stage_a.py

Baseline-anchor axis judging: gate on min side delta (neg < baseline < pos)

2026-07-17 14:01:28 +08:00

run_axis.py

refactor: replace 4 per-axis shell scripts with run_axis.py + data/axes/<id>/config.yaml

2026-07-25 10:12:01 +08:00

template_catalog.py

organize persona and scenario data paths

2026-06-29 19:16:41 +08:00

validate_persona_axes.py

Run persona validation through Inspect AI

2026-07-18 19:09:02 +08:00