{"id":"W2804173549","doi":"10.3138/jvme.0117-015r","title":"Teaching Tip: A Method for Evaluating Learning Evidence when Using Cumulative Final Examinations","year":2018,"lang":"en","type":"article","venue":"Journal of Veterinary Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Microsoft excel; Computer science; Medical education; Psychology; Mathematics education; Medicine","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"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":[0.009222986,0.00008101979,0.0001649881,0.0001522086,0.0008621474,0.00007932592,0.0002782838,0.00008749025,0.0004903349],"category_scores_gemma":[0.0160536,0.00007413837,0.0000870588,0.0001390603,0.0001412226,0.0006909993,0.0000453796,0.0003494854,0.000003373846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002864305,"about_ca_system_score_gemma":0.002274144,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003753307,"about_ca_topic_score_gemma":0.00002583527,"domain_scores_codex":[0.9971668,0.001073185,0.0004224476,0.0001299618,0.001009673,0.0001980063],"domain_scores_gemma":[0.9970118,0.001503807,0.0005274786,0.000060488,0.0007177674,0.0001786526],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002901907,0.0004872629,0.006222459,0.00006435514,0.00009146432,0.000005831957,0.1800115,0.00003898153,0.005989363,0.003117243,0.00217229,0.8015091],"study_design_scores_gemma":[0.004573631,0.02012577,0.05912802,0.00980132,0.00103721,0.0006862268,0.247092,0.3104106,0.0001761282,0.023575,0.3220623,0.001331837],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8599802,0.0002114317,0.1315334,0.004832127,0.001660597,0.0002310991,2.490278e-7,0.0000138113,0.001537087],"genre_scores_gemma":[0.792205,0.00002776378,0.2035899,0.0002303464,0.003031482,0.000009271907,0.0000010859,0.000009247093,0.0008958985],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8001773,"threshold_uncertainty_score":0.9922346,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4702388782930537,"score_gpt":0.6169445040889544,"score_spread":0.1467056257959007,"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."}}