BSD Testbench

{
  "name": "test new value+policy together  (fix)",
  "description": "Fast (current value+policy) vs Large (old value+old policy)",
  "system_a": {
    "name": "new-policy",
    "repo_url": "https://github.com/XInTheDark/brawlstarsdraft_0827.git",
    "commit_or_ref": "20251020_base",
    "subdir": null,
    "config_path": "webapp/config.yaml",
    "model": "Large",
    "models_dir": null,
    "download_link": null,
    "fm_device": null,
    "env_overrides": {},
    "request_timeout_seconds": null,
    "port_hint": null
  },
  "system_b": {
    "name": "new-policy",
    "repo_url": "https://github.com/XInTheDark/brawlstarsdraft_0827.git",
    "commit_or_ref": "20251020_base",
    "subdir": null,
    "config_path": "webapp/config.yaml",
    "model": "Large",
    "models_dir": null,
    "download_link": null,
    "fm_device": null,
    "env_overrides": {},
    "request_timeout_seconds": null,
    "port_hint": null
  },
  "judges": [
    {
      "name": "website-judge",
      "weight": 1.0,
      "epsilon": null,
      "evaluate_both_sides": true,
      "system": {
        "name": "website-judge",
        "repo_url": "https://github.com/XInTheDark/brawlstarsdraft_0827.git",
        "commit_or_ref": "website",
        "subdir": null,
        "config_path": "webapp/config.yaml",
        "model": "Large",
        "models_dir": null,
        "download_link": null,
        "fm_device": null,
        "env_overrides": {},
        "request_timeout_seconds": null,
        "port_hint": null
      }
    },
    {
      "name": "old-judge",
      "weight": 1.0,
      "epsilon": null,
      "evaluate_both_sides": true,
      "system": {
        "name": "website-judge",
        "repo_url": "https://github.com/XInTheDark/brawlstarsdraft_0827.git",
        "commit_or_ref": "website",
        "subdir": null,
        "config_path": "webapp/config.yaml",
        "model": "Large",
        "models_dir": null,
        "download_link": null,
        "fm_device": null,
        "env_overrides": {},
        "request_timeout_seconds": null,
        "port_hint": null
      }
    }
  ],
  "judge_policy": "average",
  "time_control": {
    "seconds": 6.0,
    "rollout": "pad",
    "policy_temperature": 0.8,
    "seed_mode": "deterministic",
    "extra_flags": null,
    "normalize_sides": true
  },
  "draft": {
    "bans_per_side": 3,
    "epsilon_draw": 0.05,
    "book_path": "books/ranked.yaml",
    "map_mode_weights": {}
  },
  "sprt": {
    "elo0": 0.0,
    "elo1": 2.0,
    "alpha": 0.05,
    "beta": 0.05
  },
  "fixed_n": null,
  "parallelism_hint": 4,
  "max_trials": null,
  "id": "fdd7feef-ee4b-4ddd-9844-e5cb6408b8b0",
  "status": "cancelled",
  "created_at": "2025-10-20T12:11:46"
}