{"id":"W2619928717","doi":"10.2147/amep.s128321","title":"Investigating a self-scoring interview simulation for learning and assessment in the medical consultation","year":2017,"lang":"en","type":"article","venue":"Advances in Medical Education and Practice","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Generalizability theory; Reliability (semiconductor); Medical education; Computer science; Variance (accounting); Objective structured clinical examination; Psychology; Applied psychology; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.005201396,0.00006976983,0.0001550792,0.00003956314,0.0001705351,0.00006927025,0.00006634948,0.00009314869,0.00003399704],"category_scores_gemma":[0.6499876,0.00005043395,0.00001486367,0.000065733,0.0001411283,0.0003845303,0.00003301404,0.0005584417,7.193482e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002855919,"about_ca_system_score_gemma":0.0006574613,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006335496,"about_ca_topic_score_gemma":0.00006175582,"domain_scores_codex":[0.9986258,0.0003447733,0.0003286102,0.0001896022,0.0004006671,0.0001105144],"domain_scores_gemma":[0.9156787,0.08327941,0.0003940866,0.0001806804,0.0001794762,0.0002876777],"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":[0.00004308363,0.000327674,0.04898203,0.0001344303,0.000006679276,0.000009324544,0.002285371,0.00001539549,7.142934e-7,0.002600352,0.00002741753,0.9455675],"study_design_scores_gemma":[0.0127607,0.0007673504,0.368929,0.0165917,0.0002555349,0.000678185,0.024424,0.2510526,0.000003503797,0.009879049,0.3143032,0.0003551312],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5686616,0.01668253,0.01464622,0.3740969,0.001422436,0.00203404,0.000001163173,0.00006838617,0.02238668],"genre_scores_gemma":[0.9660909,0.01005599,0.01639179,0.007110949,0.0001872573,0.0001187646,0.00001368967,0.000005907392,0.00002480557],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9452124,"threshold_uncertainty_score":0.3529607,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06238171820043661,"score_gpt":0.5473635698218368,"score_spread":0.4849818516214002,"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."}}