{"id":"W2099954138","doi":"10.1016/j.ygyno.2005.07.040","title":"Kappa statistics to measure interrater and intrarater agreement for 1790 cervical biopsy specimens among twelve pathologists: Qualitative histopathologic analysis and methodologic issues","year":2005,"lang":"en","type":"article","venue":"Gynecologic Oncology","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":90,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"National Cancer Institute","keywords":"Medicine; Biopsy; Inter-rater reliability; Cohen's kappa; Cervical cancer; Radiology; Kappa; Family medicine; Cancer; Statistics; Internal medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.02167428,0.0005250087,0.001603962,0.0006906674,0.0003879808,0.0002371023,0.0007766491,0.0005269216,0.002428644],"category_scores_gemma":[0.01218319,0.0003445577,0.0002358359,0.0008973108,0.001106595,0.0002400235,0.0005930126,0.000406082,0.0001980606],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005820693,"about_ca_system_score_gemma":0.00008526498,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005595708,"about_ca_topic_score_gemma":0.001815171,"domain_scores_codex":[0.9901624,0.004570346,0.001741697,0.001755707,0.0009148847,0.0008549701],"domain_scores_gemma":[0.9889414,0.008439044,0.0006521557,0.0007358625,0.0008530112,0.0003784896],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002547797,0.003529766,0.3018108,0.0001602781,0.002038486,0.0004830072,0.08651789,0.001950942,0.0177167,0.01679632,0.08312747,0.4833205],"study_design_scores_gemma":[0.002624947,0.009718316,0.7209008,0.00002290404,0.001303673,0.00005871608,0.03155709,0.001814052,0.001078077,0.1313717,0.09815412,0.00139556],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8078763,0.0006070869,0.1714945,0.01557534,0.0006080382,0.001816253,0.0002511194,0.00006817509,0.001703133],"genre_scores_gemma":[0.7277134,0.00009657118,0.2670175,0.002841398,0.0001637549,0.0004214282,0.00003377517,0.00001292224,0.001699268],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.481925,"threshold_uncertainty_score":0.9999006,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2655803757781627,"score_gpt":0.4873603395796752,"score_spread":0.2217799638015124,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}