{"id":"W2018205196","doi":"10.1111/j.0006-341x.2001.00584.x","title":"Inference Procedures for Assessing Interobserver Agreement among Multiple Raters","year":2001,"lang":"en","type":"article","venue":"Biometrics","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Statistics; Goodness of fit; Mathematics; Nominal level; Confidence interval; Binomial distribution; Range (aeronautics); Inference; Sample size determination; Binomial (polynomial); Multiple comparisons problem; Statistical inference; Computer science; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3137946,0.002474973,0.00322756,0.01279146,0.003608268,0.004268166,0.008994936,0.00434158,0.004996895],"category_scores_gemma":[0.6643057,0.002306794,0.003897474,0.007957811,0.006298745,0.007081587,0.006588009,0.00793683,0.00228904],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002728511,"about_ca_system_score_gemma":0.005126656,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002597524,"about_ca_topic_score_gemma":0.002407569,"domain_scores_codex":[0.6355671,0.2772988,0.0219454,0.0198812,0.04322911,0.002078449],"domain_scores_gemma":[0.2639889,0.627777,0.03134468,0.03925431,0.0363327,0.001302217],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0007740678,0.0003516848,0.01766177,0.00167916,0.001559468,0.0004988748,0.006548977,0.02386639,0.003353431,0.2715099,0.0066649,0.6655313],"study_design_scores_gemma":[0.0005868046,0.001157252,0.01979469,0.001494088,0.000978157,0.001497964,0.001314869,0.2538045,0.01357544,0.6868187,0.01830673,0.000670769],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001151112,0.00008218994,0.9976524,0.00007696337,0.00003113794,0.0003532384,0.00004963885,0.0001678314,0.0004355256],"genre_scores_gemma":[0.02372381,0.0001028425,0.9732196,0.0001025781,0.00008544866,0.002381611,0.0001245067,0.00008963341,0.0001700327],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6862054,"threshold_uncertainty_score":0.8462134,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3335008582243348,"score_gpt":0.4305500555919031,"score_spread":0.09704919736756829,"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."}}