{"id":"W1986967177","doi":"10.3109/0142159x.2010.486063","title":"Assessment steers learning down the right road: Impact of progress testing on licensing examination performance","year":2010,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":121,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; McMaster University","funders":"","keywords":"Formative assessment; Test (biology); Curriculum; Psychology; Medicine; Medical education; Mathematics education; Pedagogy","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003853756,0.0001057026,0.0001415954,0.00004873321,0.0005301847,0.00007418874,0.0003150327,0.0001380663,0.001686484],"category_scores_gemma":[0.001045943,0.00006294251,0.00006732045,0.000291735,0.0004619003,0.0001409634,0.00005274032,0.0008718335,0.00001624208],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001049584,"about_ca_system_score_gemma":0.0002250835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003287865,"about_ca_topic_score_gemma":0.0001149875,"domain_scores_codex":[0.9976656,0.0003575294,0.0002036826,0.0001665694,0.001308992,0.0002976546],"domain_scores_gemma":[0.999244,0.0002453075,0.0001564206,0.0001302764,0.0001015612,0.0001223886],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00000352221,0.0001157798,0.7888505,0.00000476341,0.00002324766,0.000001865684,0.004602669,0.000006891829,0.0001127418,0.0004188263,0.0001406532,0.2057185],"study_design_scores_gemma":[0.0002525103,0.000155625,0.9850033,0.00005550816,0.00001358477,8.035344e-7,0.001733734,0.0108064,0.00001290379,0.00001071345,0.00185983,0.00009508433],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8681741,0.0000105879,0.00001398906,0.0005715039,0.0002633554,0.0001830477,1.103636e-7,0.00005148966,0.1307318],"genre_scores_gemma":[0.9976144,0.000007531216,0.0002433726,0.00002060754,0.0005083873,0.00001120355,0.000002435537,0.000009662216,0.00158235],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2056234,"threshold_uncertainty_score":0.9992261,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02780155950402934,"score_gpt":0.3811736229013911,"score_spread":0.3533720633973618,"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."}}