Spaces:
Running
Running
Commit History
-
Additive CARE literal-claim and eigengap audit
Verified signature679bbc9 -
Full-scale benchmark reproduction and machine-checked theory verdicts for CARE
Verified signaturedc8ad3c -
Full-scale benchmark reproduction and machine-checked theory verdicts for CARE
Verified signature5599e3f -
Full-scale benchmark reproduction and machine-checked theory verdicts for CARE
Verified signature5e111f1 -
Full-scale benchmark reproduction and machine-checked theory verdicts for CARE
Verified signatureae73dd3 -
Full-scale benchmark reproduction and machine-checked theory verdicts for CARE
Verified signaturea3f1c77 -
Full-scale benchmark reproduction and machine-checked theory verdicts for CARE
Verified signature6c10f40
-
Full-scale benchmark reproduction and machine-checked theory verdicts for CARE
Verified signature13a5fd7 -
Full-scale benchmark reproduction and machine-checked theory verdicts for CARE
Verified signaturea72dcee -
Full-scale benchmark reproduction and machine-checked theory verdicts for CARE
Verified signaturecac559b -
Update logbook: Repro - CARE: Confounder-Aware Aggregation for Reliable LLM Evaluation
Verified signature2a647ca