{"id":"W4393231936","doi":"10.5489/cuaj.8747","title":"Hawks and doves, differing content, scoring systems, and delivery platforms: No wonder there’s variability in grades","year":2024,"lang":"en","type":"article","venue":"Canadian Urological Association Journal","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of British Columbia","funders":"","keywords":"Wonder; Content (measure theory); Scoring system; Psychology; Social psychology; Mathematics; Medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"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":[],"category_scores_codex":[0.019159,0.0003090653,0.0005358303,0.002789138,0.003854187,0.007504225,0.00148768,0.002145618,0.006910092],"category_scores_gemma":[0.2100624,0.0005460544,0.0007762046,0.00255296,0.005189641,0.008696873,0.001999187,0.003788289,0.001329604],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004017308,"about_ca_system_score_gemma":0.006470843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.08311243,"about_ca_topic_score_gemma":0.1253906,"domain_scores_codex":[0.9899291,0.00271439,0.00101906,0.001844179,0.004088191,0.0004051135],"domain_scores_gemma":[0.8539099,0.07507041,0.009281819,0.006992276,0.04931207,0.005433475],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.001223756,0.0004795128,0.2473829,0.0005435022,0.0007583554,0.0002177413,0.03444323,0.000805929,0.001244183,0.05624652,0.2920767,0.3645777],"study_design_scores_gemma":[0.0005171495,0.000564875,0.6101577,0.002581451,0.001072014,0.0003718868,0.06312851,0.002709113,0.00317022,0.1103394,0.2047163,0.0006714707],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.4072733,0.03318078,0.0225604,0.4358653,0.008883531,0.0003818109,0.003210992,0.0005510912,0.08809289],"genre_scores_gemma":[0.9146402,0.008444686,0.01187474,0.04096315,0.001701378,0.0002387175,0.0006654456,0.0005236905,0.02094803],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.980841,"threshold_uncertainty_score":0.1652573,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02334110560034305,"score_gpt":0.2197017111283282,"score_spread":0.1963606055279852,"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."}}