{
  "frozen_at": "2026-07-18T23:46:57.951556+00:00",
  "git_sha": "f93f4b5578c221d3d2665f9b305f3e86759be862+dirty",
  "spec": {
    "analysis": "campaign.chidrift.analyze",
    "hypotheses": [
      {
        "id": "H-chi-bon",
        "prediction": {
          "ci_excludes": 0.0,
          "comparator": ">",
          "effect": null,
          "metric": "chi_bon_spearman",
          "threshold": 0.3
        },
        "scoreboard_row": "T9",
        "statement": "chi predicts realized best-of-n feature-drift ordering on a real bank"
      },
      {
        "id": "H-chi-beats-var",
        "prediction": {
          "ci_excludes": 0.0,
          "comparator": ">",
          "effect": null,
          "metric": "chi_minus_variance_baseline_spearman",
          "threshold": 0.0
        },
        "scoreboard_row": null,
        "statement": "chi beats a base-variance-only baseline"
      }
    ],
    "id": "campaign-chi-drift",
    "kill_criteria": [
      {
        "comparator": "<",
        "id": "K-chi",
        "metric": "chi_bon_spearman",
        "threshold": 0.3
      }
    ],
    "science": "S03-thermo",
    "subjects": {
      "datasets": [
        "ultrafeedback-bank"
      ],
      "extra": {
        "slice_hashes": {
          "ultrafeedback-bank": "ds:1cb97d4beca432de1793f56a4183a4aa"
        }
      },
      "organisms": [],
      "signals": [
        "skywork-v2-qwen3-8b",
        "skywork-v2-llama31-8b"
      ]
    },
    "title": "Susceptibility chi predicts best-of-n feature drift on a real bank",
    "version": 1
  },
  "spec_hash": "spec:1c12042d2eeb93b23ff9cf27b6433125",
  "study_id": "study:campaign-chi-drift@v1#1c12042d"
}