Commit History

  1. Remove evaluation review markdown

    3311798
  2. Update evaluation predictions and figures

    193007d
  3. Clean custom evaluation dataset metadata

    adc58cf
  4. Add evaluation scripts and result artifacts

    72b0375
  5. Add custom argument evaluation dataset

    028ed9a

  1. Initial project scaffold⁠

    nicopbeard +1: Claude Sonnet 4.6
    3e68fce