Commit History

  1. refactor: adjust score clamping range to 0.001-0.999 and improve action normalization robustness

    Mahir
    ce6b9af
  2. Fix inference.py: sync heuristic fallback, clamp all scores--2

    Mahir
    687d4d6

  1. Fix inference.py: sync heuristic fallback, clamp all scores

    Mahir
    7ff4f6b
  2. Fix #19: clamp overall score in inference.py and update baseline_results.json

    Mahir
    6d6d6e3
  3. Fix #18: force clamp all scores strictly within (0, 1) exclusive

    Mahir
    2768eae

  1. Checklist Phase II --- part 3

    Mahir
    7d999d4
  2. Checklist Phase II --- part 2

    Mahir
    5592e0a
  3. Fix Phase 2: clamp all grader scores to (0.0001, 0.9999) exclusive

    Mahir
    1a24bd9
  4. Checklist Phase II

    Mahir
    2d5b292
  5. Fix Phase 2 validator log formats

    Mahir
    2656c33
  6. Update variables and logs for final checklist submission

    Mahir
    dc48d19
  7. refactor: update baseline results and inference logic for improved model performance metrics

    Mahir
    5467c0b

  1. Fix: server entry point uses main() as required by openenv validate

    Mahir
    000cdbf
  2. Fix openenv validate: pyproject.toml, uv.lock, server/app.py

    Mahir
    7932d11
  3. Add pyproject.toml for OpenEnv multi-mode deployment validation

    Mahir
    a55d5e5
  4. Rename baseline_inference.py to inference.py for OpenEnv checks

    Mahir
    5b6efd8
  5. Fix static path routing to root static dir

    Mahir
    e0c6328
  6. Complete dashboard rebuild — all 13 tasks, 4 domains

    Mahir
    c70f857
  7. Add all domain tasks, fix graders, update Docker deps

    Mahir
    40eba49
  8. All 13 tasks passing, overall score 0.9015

    Mahir
    2ac8bdd

  1. Initial OpenEnv customer support environment

    Mahir
    f5d79b8