{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","research_integrity","insufficient_payload"],"consensus_categories":["research_integrity"],"category_scores_codex":[0.02781675,0.0003515324,0.0006508601,0.0001654918,0.0006583342,0.00006229485,0.001120675,0.001506659,0.001670316],"category_scores_gemma":[0.04331755,0.0003041948,0.000103737,0.0001374363,0.0005802551,0.0008292568,0.000163525,0.006772328,0.0001224923],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00148473,"about_ca_system_score_gemma":0.001364278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001443346,"about_ca_topic_score_gemma":0.00001299458,"domain_scores_codex":[0.9913657,0.002977224,0.0007574676,0.0007232249,0.003514166,0.0006622148],"domain_scores_gemma":[0.9898155,0.00816393,0.001169756,0.0003939326,0.0002260765,0.0002307991],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001025181,0.000003090553,0.0003951819,0.00009097833,0.00004131714,0.000008973178,0.008121329,0.0002253548,0.00001383731,0.0003309009,0.9838281,0.006930646],"study_design_scores_gemma":[0.0004121396,0.000261844,0.0001366376,0.000745586,0.0003815726,0.000002805897,0.002453736,0.0002467804,0.00000253411,0.002240961,0.9927972,0.0003182116],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"commentary","genre_scores_codex":[0.0001857106,0.001813911,0.01748585,0.9649321,0.001873977,0.001277243,0.00000956308,0.0001580399,0.01226364],"genre_scores_gemma":[0.006614666,0.01624795,0.008780054,0.7829272,0.07268331,0.0007755407,0.0007240537,0.0001610122,0.1110862],"genre_candidate":"commentary","genre_consensus":"commentary","teacher_disagreement_score":0.1820049,"threshold_uncertainty_score":0.999941,"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."}}