-
Notifications
You must be signed in to change notification settings - Fork 6
Pull requests: buildinghumanetech/humanebench
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
F4 follow-ups: correct false provenance claims and two broken documented commands
#101
opened Sep 11, 2026 by
ErikaOnFire
Contributor
Loading…
Rubric v4: gate the principles, fix transparency, map the floor to statute
#97
opened Sep 10, 2026 by
ErikaOnFire
Contributor
Loading…
Conversation-level judging and joint-vs-decomposed analyzer
#92
opened Aug 20, 2026 by
andalibmalit
Contributor
•
3/3
Loading…
Judge-comparison core: joint scorer and panel-vs-single-judge analysis
#91
opened Aug 20, 2026 by
andalibmalit
Contributor
•
2/3
Loading…
Partner mode: re-judge external prompt/response datasets
#90
opened Aug 20, 2026 by
andalibmalit
Contributor
•
1/3
Loading…
Discriminant follow-ups + paper-section annotations
#87
opened Aug 7, 2026 by
andalibmalit
Contributor
•
4/4
Loading…
Pairwise discriminant-validity matrix
#86
opened Aug 7, 2026 by
andalibmalit
Contributor
•
3/4
Loading…
Decomposition completion + supplementary package builder
#85
opened Aug 7, 2026 by
andalibmalit
Contributor
•
2/4
Loading…
Foundations: judge/provenance/decomposition infra + main reconciliation
#84
opened Aug 7, 2026 by
andalibmalit
Contributor
•
1/4
Loading…
Add HumaneBench transcript-scoring Claude Code skill
#81
opened Jul 23, 2026 by
ErikaOnFire
Contributor
Loading…
ProTip!
Filter pull requests by the default branch with base:main.