purpose-agent / benchmarks

Commit History

  1. clean: remove temp scripts, patches, and dev artifacts before public release

    Verified signature
    e4105d6
  2. v3.0.0 Production Release: Hardened framework, strict tool validation, test suite robustification

    36d2671

  1. fix: real-model robustness — benchmarks/validate_real.py

    Verified signature
    d7dc6c8
  2. Track 2: validation suite with improvement curves, cold/warm, transfer, adversarial

    Verified signature
    ec1ea80
  3. Track 2: validation suite with improvement curves, cold/warm, transfer, adversarial

    Verified signature
    d9f6778
  4. Track 2: validation suite with improvement curves, cold/warm, transfer, adversarial

    Verified signature
    ab5adb4