{
 "jurors": {
  "claude-sonnet-5": "claude-sonnet-5",
  "deepseek-v3.2": "deepseek-ai/DeepSeek-V3.2",
  "gemini-2.5-pro": "gemini-2.5-pro",
  "llama-4-maverick": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
  "qwen3-235b": "Qwen/Qwen3-235B-A22B-Instruct-2507"
 },
 "n_items": 500,
 "fleiss_kappa_jurors": 0.6862449799196786,
 "pairwise_kappa": {
  "claude-sonnet-5 ~ deepseek-v3.2": 0.6364241659657975,
  "claude-sonnet-5 ~ gemini-2.5-pro": 0.7054798080421336,
  "claude-sonnet-5 ~ llama-4-maverick": 0.6584699453551912,
  "claude-sonnet-5 ~ qwen3-235b": 0.6946709326727905,
  "deepseek-v3.2 ~ gemini-2.5-pro": 0.6957200988228455,
  "deepseek-v3.2 ~ llama-4-maverick": 0.7071714652762034,
  "deepseek-v3.2 ~ qwen3-235b": 0.7575953458306399,
  "gemini-2.5-pro ~ llama-4-maverick": 0.6347732820474886,
  "gemini-2.5-pro ~ qwen3-235b": 0.6858740664708173,
  "llama-4-maverick ~ qwen3-235b": 0.6898036639661339
 },
 "vote_distribution": {
  "0": 94,
  "1": 43,
  "2": 34,
  "3": 30,
  "4": 36,
  "5": 263
 },
 "unanimous_share": 0.714,
 "kappa_llm_vs_jury": 0.7139197267292912,
 "kappa_llm_vs_jury_ci": [
  0.6489726027397259,
  0.7744872141916156
 ],
 "kappa_llm_vs_each_juror": {
  "claude-sonnet-5": 0.6767422334172963,
  "deepseek-v3.2": 0.6891191709844559,
  "gemini-2.5-pro": 0.6706586826347305,
  "llama-4-maverick": 0.5898778359511345,
  "qwen3-235b": 0.6683673469387755
 },
 "weighted": {
  "precision": {
   "est": 0.9366666666666666,
   "ci": [
    0.9066666666666667,
    0.9600000000000001
   ]
  },
  "recall": {
   "est": 0.9530305015577571,
   "ci": [
    0.942439780507583,
    0.964476223971168
   ]
  },
  "specificity": {
   "est": 0.6977163253283433,
   "ci": [
    0.6093801714792522,
    0.7926618287746177
   ]
  },
  "accuracy": {
   "est": 0.9081672942873167,
   "ci": [
    0.8817694896242289,
    0.931770861709799
   ]
  },
  "ref_prevalence": {
   "est": 0.8242823491707396,
   "ci": [
    0.7983139071388511,
    0.8470779584969154
   ]
  }
 },
 "confusion_sample": {
  "llm_inc_jury_inc": 281,
  "llm_inc_jury_exc": 19,
  "llm_exc_jury_inc": 48,
  "llm_exc_jury_exc": 152
 },
 "unanimous_items": {
  "n": 357,
  "agreement_llm": 0.938375350140056,
  "kappa": 0.8453815261044176
 },
 "llm_conf_agree_mean": 0.8690762124711318,
 "llm_conf_disagree_mean": 0.7891044776119404,
 "coding": {
  "tech": {
   "micro_precision": 0.753393665158371,
   "micro_recall": 0.9823008849557522,
   "micro_f1": 0.8527528809218949,
   "mean_jaccard": 0.8299525504151838,
   "n_items": 281
  },
  "domain": {
   "micro_precision": 0.785377358490566,
   "micro_recall": 0.8975741239892183,
   "micro_f1": 0.8377358490566037,
   "mean_jaccard": 0.7870699881376038,
   "n_items": 281
  },
  "method": {
   "accuracy": 0.9039145907473309,
   "n_items": 281
  }
 },
 "retest_same_model": {
  "deepseek-v3.2": {
   "repeated": 340,
   "changed": 34,
   "rate": 0.1
  },
  "gemini-2.5-pro": {
   "repeated": 290,
   "changed": 21,
   "rate": 0.07241379310344828
  },
  "llama-4-maverick": {
   "repeated": 330,
   "changed": 45,
   "rate": 0.13636363636363635
  },
  "qwen3-235b": {
   "repeated": 410,
   "changed": 47,
   "rate": 0.11463414634146342
  }
 }
}