{"id":"W2048301263","doi":"10.1097/00001888-200310001-00021","title":"An Evaluation of Local Item Dependencies in the Medical Council of Canada Qualifying Examination Part I","year":2003,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Lakehead University","funders":"","keywords":"Statistic; Test (biology); Residual; Psychology; Curse of dimensionality; Medicine; Statistics; Computer science; Mathematics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1921403,0.00009335615,0.0003563292,0.0002170732,0.00005168394,0.00000374348,0.0008257203,0.000161317,0.0006276398],"category_scores_gemma":[0.5229076,0.00005042736,0.00001784739,0.001898722,0.0002507558,0.0001182571,0.00002224974,0.0004042395,5.936553e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002758772,"about_ca_system_score_gemma":0.00312843,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02726841,"about_ca_topic_score_gemma":0.03518127,"domain_scores_codex":[0.9753135,0.006182242,0.001783768,0.0003795658,0.01604628,0.0002946178],"domain_scores_gemma":[0.9468814,0.05045015,0.0007170592,0.0004823863,0.001352642,0.0001164171],"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":[0.00004310636,0.00005867273,0.2100387,0.00006964149,0.00003050725,0.00002178201,0.03710512,0.001784831,0.001424681,0.01677484,0.02389314,0.708755],"study_design_scores_gemma":[0.003863322,0.0005228777,0.4743492,0.0006835781,0.0001157907,0.000153046,0.3574352,0.07857206,0.002313814,0.06783411,0.01382072,0.0003362732],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9694723,0.001895796,0.0175388,0.0009910933,0.0005668579,0.0001863574,0.000001743011,0.00000518913,0.009341804],"genre_scores_gemma":[0.9991989,0.0000795898,0.0001340176,0.0004339018,0.00008597669,0.000009035669,0.000001604784,0.000003375537,0.000053641],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7084187,"threshold_uncertainty_score":0.9824241,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7671910957259485,"score_gpt":0.5281969235879826,"score_spread":0.2389941721379658,"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."}}