{"id":"W2460400726","doi":"10.1097/acm.0000000000000723","title":"Towards Robust Validity Evidence for Learning Environment Assessment Tools","year":2015,"lang":"en","type":"letter","venue":"Academic Medicine","topic":"Evaluation of Teaching Practices","field":"Social Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; Predictive validity; Internal validity; External validity; Internal consistency; Reliability (semiconductor); Medical education; Applied psychology; Clinical psychology; Social psychology; Psychometrics; Medicine; Statistics; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3894013,0.001512353,0.005230692,0.01145553,0.002905098,0.0168153,0.0103614,0.02531722,0.005786158],"category_scores_gemma":[0.8504341,0.001949923,0.003895998,0.007225266,0.01171207,0.0133689,0.01197214,0.02660628,0.002852141],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007638294,"about_ca_system_score_gemma":0.0208783,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00237098,"about_ca_topic_score_gemma":0.002699926,"domain_scores_codex":[0.6149722,0.2077731,0.07700793,0.0141449,0.08285736,0.003244497],"domain_scores_gemma":[0.07582667,0.7530659,0.03353018,0.01415446,0.1209801,0.002442732],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0008892942,0.0002423433,0.004390822,0.05866072,0.00269854,0.0005594573,0.002256049,0.0003243871,0.000382347,0.01694222,0.6285486,0.2841052],"study_design_scores_gemma":[0.0009637083,0.0006131787,0.008973323,0.2200197,0.002958241,0.0007787326,0.001533536,0.001848252,0.001018406,0.03609083,0.7248698,0.0003322912],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.001262914,0.1367116,0.005568101,0.6888273,0.1633722,0.000646963,0.0005718092,0.0001549161,0.002884116],"genre_scores_gemma":[0.04156204,0.08943962,0.02714584,0.5841188,0.2510998,0.003864842,0.0007788123,0.0003992964,0.00159103],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.6105987,"threshold_uncertainty_score":0.7529769,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.712991305753745,"score_gpt":0.5566709861773476,"score_spread":0.1563203195763975,"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."}}