{"id":"W4213215405","doi":"10.4300/jgme-d-21-00602.1","title":"Development of and Preliminary Validity Evidence for the EFeCT Feedback Scoring Tool","year":2022,"lang":"en","type":"review","venue":"Journal of Graduate Medical Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; Shell (Canada); University of Calgary; University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; University of Alberta","keywords":"Generalizability theory; Summative assessment; Inter-rater reliability; Session (web analytics); Peer feedback; Construct validity; Quality (philosophy); Formative assessment; Reliability (semiconductor); Narrative; Psychology; Computer science; Applied psychology; Content validity; Medical education; Medicine; Psychometrics; Clinical psychology; Rating scale; Mathematics education; World Wide Web","routes":{"ca_aff":true,"ca_fund":true,"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":[0.345596,0.001289421,0.001765473,0.01097488,0.002331343,0.005487036,0.004710978,0.002980347,0.003494804],"category_scores_gemma":[0.5306453,0.001089756,0.006073241,0.005930988,0.004486304,0.005864986,0.005325735,0.003092981,0.001056811],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.009157811,"about_ca_system_score_gemma":0.02183966,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003588845,"about_ca_topic_score_gemma":0.00763639,"domain_scores_codex":[0.6583927,0.1492698,0.06520243,0.008802927,0.1151292,0.003202973],"domain_scores_gemma":[0.348786,0.3929882,0.03266805,0.02053544,0.2024401,0.002582235],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001618072,0.001943046,0.1782447,0.01738942,0.001402121,0.0003485347,0.01513767,0.002602774,0.004067944,0.0195435,0.01164738,0.7460549],"study_design_scores_gemma":[0.002900959,0.01973558,0.5865831,0.1120609,0.005566265,0.002591397,0.02719536,0.04315805,0.0361394,0.03817943,0.1247688,0.001120867],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3840436,0.01581043,0.4067956,0.01409874,0.002750414,0.08199203,0.004239693,0.001032325,0.08923719],"genre_scores_gemma":[0.4412395,0.003055188,0.5068415,0.001774851,0.000214361,0.04272243,0.002334121,0.0001551177,0.001663017],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.345596,"threshold_uncertainty_score":0.8069967,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3765100169265935,"score_gpt":0.4925390435888635,"score_spread":0.11602902666227,"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."}}