{"id":"W4406230481","doi":"10.5334/pme.1551","title":"Introducing the Next Era in Assessment","year":2025,"lang":"en","type":"article","venue":"Perspectives on Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"National Board of Medical Examiners","keywords":"Accountability; Engineering ethics; Summative assessment; Health care; Context (archaeology); Transformational leadership; Formative assessment; Computer science; Political science; Medical education; Public relations; Medicine; Psychology; Pedagogy; Engineering","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00125526,0.0001224219,0.0001844643,0.0004447699,0.0001370441,0.00003653043,0.0001895002,0.0001313473,0.0010898],"category_scores_gemma":[0.009533786,0.00008604172,0.00004690678,0.001366233,0.0002207199,0.00008802028,0.00003248325,0.001071101,0.00003795035],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001040545,"about_ca_system_score_gemma":0.004176698,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001199975,"about_ca_topic_score_gemma":0.00001476879,"domain_scores_codex":[0.9982606,0.0001202669,0.000358549,0.0003772021,0.0006741612,0.0002091993],"domain_scores_gemma":[0.998904,0.0001834549,0.0000676751,0.0004830893,0.0002959236,0.0000658649],"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":[0.00008604247,0.003862798,0.0121822,0.0001142617,0.00005733837,0.000003006783,0.01190704,0.000015544,0.0001575644,0.2750192,0.1010984,0.5954965],"study_design_scores_gemma":[0.002116944,0.0002783827,0.7067979,0.001951363,0.00009923915,0.00003661943,0.1976981,0.008829485,0.0001488085,0.006964927,0.07479663,0.0002815597],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4889419,0.000723382,0.002930613,0.4458368,0.002369805,0.0007398209,2.932372e-7,0.00006194855,0.05839542],"genre_scores_gemma":[0.9698026,0.0002158437,0.003700077,0.023538,0.0008285603,0.0002590251,0.00002663644,0.00001158579,0.00161763],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6946157,"threshold_uncertainty_score":0.9998233,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01175858592176682,"score_gpt":0.3984350546035804,"score_spread":0.3866764686818136,"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."}}