{"id":"W2441041702","doi":"10.1111/medu.12985","title":"Taking the sting out of assessment: is there a role for progress testing?","year":2016,"lang":"en","type":"review","venue":"Medical Education","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":51,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Ottawa","funders":"","keywords":"Context (archaeology); Curriculum; Test (biology); Standardized test; Assessment for learning; Educational assessment; Formative assessment; Unintended consequences; Educational measurement; Risk assessment; Computer science; Psychology; Engineering ethics; Mathematics education; Engineering; Pedagogy; Political science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.2297475,0.001431315,0.002328632,0.004640185,0.00268813,0.01343818,0.007525182,0.008125965,0.006310282],"category_scores_gemma":[0.5259007,0.0007534522,0.001670314,0.002936902,0.02140061,0.03628654,0.009033089,0.01262129,0.002642701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006176354,"about_ca_system_score_gemma":0.02705321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005300208,"about_ca_topic_score_gemma":0.006281208,"domain_scores_codex":[0.8083539,0.1410538,0.008285033,0.006821796,0.0321536,0.003331764],"domain_scores_gemma":[0.3607556,0.4745783,0.03625763,0.03650757,0.06812955,0.02377131],"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":[0.0003475432,0.0002851535,0.02601042,0.002958675,0.0001342508,0.0004470561,0.00914927,0.0007038063,0.0004926733,0.07412907,0.02707369,0.8582683],"study_design_scores_gemma":[0.0003903221,0.003286911,0.04152511,0.05672312,0.0004945042,0.005364839,0.03235288,0.007550974,0.00531211,0.4115674,0.4345375,0.0008944237],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"review","genre_scores_codex":[0.02228635,0.06056247,0.155667,0.7116199,0.007709091,0.0007083075,0.0001812439,0.001900782,0.0393648],"genre_scores_gemma":[0.528823,0.0495937,0.2994311,0.1039042,0.005839964,0.002143391,0.0003738516,0.001135796,0.00875511],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.2297475,"threshold_uncertainty_score":0.9498585,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09766983136844255,"score_gpt":0.5079418249069397,"score_spread":0.4102719935384972,"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."}}