{
  "beemo": {
    "accuracy_at_zero": 0.7068885806749884,
    "auroc": 0.7565249117839237,
    "auroc_ci95": [
      0.7426192602909137,
      0.7701325982367685
    ],
    "mean_ai_score": 8.459569506846641,
    "mean_human_score": -0.7130339165776624,
    "pairs": 2163,
    "texts": 4326
  },
  "full_steps": 75,
  "full_train_pairs": 5000,
  "full_train_sources": 4081,
  "raid_standard_test": {
    "accuracy_at_zero": 0.8465,
    "auroc": 0.9503284444444446,
    "auroc_ci95": [
      0.9451532750000001,
      0.9554070277777778
    ],
    "mean_ai_score": 6.605718453546365,
    "mean_human_score": -13.570049094657103,
    "pairs": 3000,
    "texts": 6000
  },
  "selected_pilot": {
    "accuracy_at_zero": 0.746,
    "auroc": 0.790496,
    "checkpoint": "/workspace/expanded_raid_ai_20260726/outputs/gemma_locked_pairwise_ce_seed101/pilot/lr_0.001/final",
    "final_rolling_loss": 0.09688073217368583,
    "lr": 0.001,
    "mean_ai_score": 5.69093910741806,
    "mean_human_score": -2.0359047451019285,
    "pairs": 250,
    "steps": 125,
    "texts": 500
  },
  "tokens": "/workspace/expanded_raid_ai_20260726/outputs/gemma_locked_pairwise_ce_seed101/full/final/tokens"
}