{"id":"W2984476219","doi":"10.3102/1076998619885636","title":"Full Information Optimal Scoring","year":2019,"lang":"en","type":"article","venue":"Journal of Educational and Behavioral Statistics","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Ottawa Hospital; McGill University","funders":"","keywords":"Statistics; Binary number; Scoring rule; Mathematics; Binary data; Scoring system; Computer science; Point (geometry); Test (biology); Mean squared error; Arithmetic; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01710184,0.001685117,0.002813077,0.003399915,0.000677508,0.003039986,0.00262526,0.001928827,0.007401206],"category_scores_gemma":[0.08574058,0.001257737,0.00171007,0.00326302,0.002125884,0.004608592,0.005312946,0.002528484,0.002642864],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001186081,"about_ca_system_score_gemma":0.001994303,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001229944,"about_ca_topic_score_gemma":0.001223344,"domain_scores_codex":[0.9652968,0.02029377,0.00246086,0.003439441,0.007267433,0.001241786],"domain_scores_gemma":[0.9579268,0.02064258,0.001773369,0.01251678,0.006582701,0.0005577871],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001034642,0.0002946014,0.005110035,0.0003187716,0.0003588629,0.0001524944,0.0002451521,0.06025653,0.003222622,0.07308504,0.01233028,0.843591],"study_design_scores_gemma":[0.0003189293,0.0005077505,0.00534604,0.0001956811,0.0002075187,0.0006319068,0.00009557696,0.6658161,0.0079523,0.3088784,0.009813498,0.0002361608],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01673786,0.0007586259,0.9739218,0.000400008,0.0001311919,0.0002541391,0.0004497081,0.0008231261,0.006523633],"genre_scores_gemma":[0.2418703,0.0005096319,0.752017,0.0003876731,0.0001472163,0.000469653,0.00115337,0.0002862606,0.003158857],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01710184,"threshold_uncertainty_score":0.09044427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3522251289511596,"score_gpt":0.4970637307263445,"score_spread":0.1448386017751849,"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."}}