{"id":"W1573990476","doi":"10.1023/a:1014585522084","title":"Measuring Self-assessment: Current State of the Art","year":2002,"lang":"en","type":"review","venue":"Advances in Health Sciences Education","topic":"Innovations in Medical Education","field":"Medicine","cited_by":406,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Conceptualization; Self-assessment; Computer science; Value (mathematics); Domain (mathematical analysis); Management science; Engineering ethics; Data science; Psychology; Artificial intelligence; Pedagogy; Engineering","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":[0.002128617,0.0002139121,0.0007729003,0.000562482,0.0002223091,0.00001785336,0.0004303273,0.00005524254,0.00003106211],"category_scores_gemma":[0.0003763234,0.00014139,0.0001146103,0.003397639,0.0002826935,0.0002919227,0.00004842858,0.000661357,0.00001854069],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001366893,"about_ca_system_score_gemma":0.009614828,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001632899,"about_ca_topic_score_gemma":0.00001430234,"domain_scores_codex":[0.9967279,0.0002511663,0.001384778,0.0004356408,0.0008495656,0.0003509428],"domain_scores_gemma":[0.9978052,0.0001310446,0.001328347,0.0004653041,0.0002088319,0.00006126858],"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":[3.575094e-7,0.0003386897,0.0005921003,0.02519639,0.000003312298,3.178377e-8,0.0002026814,0.00000836456,1.170049e-8,0.0004432458,0.0009759649,0.9722388],"study_design_scores_gemma":[0.00006660169,0.0000631213,0.000822668,0.03560242,0.00003825419,0.0000150375,0.00005853277,0.0001067206,2.643549e-7,0.0004334277,0.9626876,0.0001054056],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.00006455066,0.9895725,0.00007616299,0.0009440847,0.00561332,0.001662988,0.000002877721,0.00002281603,0.002040669],"genre_scores_gemma":[0.0001268062,0.9919024,0.006924108,0.0003034841,0.000234704,0.0003177038,0.00002533182,0.00001503242,0.0001504883],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9721335,"threshold_uncertainty_score":0.9959998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07726503835540625,"score_gpt":0.4905131216199736,"score_spread":0.4132480832645673,"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."}}