{"id":"W3176879039","doi":"10.1097/acm.0000000000004089","title":"Numbers Encapsulate, Words Elaborate: Toward the Best Use of Comments for Assessment and Feedback on Entrustment Ratings","year":2021,"lang":"en","type":"article","venue":"Academic Medicine","topic":"Innovations in Medical Education","field":"Medicine","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia; University of Northern British Columbia; Western University; The Wilson Centre; Sinai Health System","funders":"","keywords":"Operationalization; Premise; Documentation; Formative assessment; Temptation; Set (abstract data type); Computer science; Psychology; CLARITY; Medical education; Mathematics education; Social psychology; Epistemology; Medicine","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":[],"consensus_categories":[],"category_scores_codex":[0.0009216231,0.0001726373,0.0003817184,0.00009320575,0.00009509682,0.000007621355,0.0001093,0.0001879816,0.0002270578],"category_scores_gemma":[0.002522764,0.0001110784,0.00003001007,0.000572015,0.000316066,0.00008147272,0.00005312579,0.000699105,0.000004459558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001889833,"about_ca_system_score_gemma":0.0003047129,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003710447,"about_ca_topic_score_gemma":7.018162e-7,"domain_scores_codex":[0.9981148,0.0000799431,0.0006708006,0.0002895659,0.0005978941,0.0002469731],"domain_scores_gemma":[0.9982886,0.0005190977,0.0002703403,0.0003449558,0.0004740196,0.0001029847],"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":[0.0006388355,0.0007036375,0.103106,0.001610137,0.0009039611,0.00003569392,0.03719866,0.00003721921,0.05148927,0.041046,0.6468766,0.116354],"study_design_scores_gemma":[0.03594461,0.00635121,0.1519671,0.01397355,0.003395091,0.0004656778,0.1724924,0.009243908,0.04619434,0.006999761,0.5517159,0.001256413],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.870393,0.0004687321,0.001619888,0.1249658,0.0008817789,0.000978118,0.00001157402,0.0000204467,0.0006606457],"genre_scores_gemma":[0.9669451,0.00118923,0.004090906,0.0250455,0.0005790585,0.0001382106,0.0002484455,0.00002642388,0.001737132],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1352938,"threshold_uncertainty_score":0.4529645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0919108077078394,"score_gpt":0.4182165258742775,"score_spread":0.3263057181664381,"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."}}