{"id":"W2962759515","doi":"10.1080/0142159x.2019.1638503","title":"How can we reduce bias during an academic assessment reappraisal?","year":2019,"lang":"en","type":"article","venue":"Medical Teacher","topic":"Medical Education and Admissions","field":"Medicine","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Debiasing; Witness; Psychology; Process (computing); Non-response bias; Response bias; Cognitive psychology; Social psychology; Computer science; Econometrics; Economics","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0008070039,0.0001840504,0.0003541921,0.0001018484,0.00007344175,0.00002364918,0.0002438077,0.0004032649,0.04449895],"category_scores_gemma":[0.005427218,0.0001293722,0.00009043785,0.0002148527,0.0001267013,0.00008907969,0.00006865025,0.001777708,0.00015268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008319912,"about_ca_system_score_gemma":0.001777206,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003125835,"about_ca_topic_score_gemma":0.000003270752,"domain_scores_codex":[0.9973503,0.0001884741,0.0003193928,0.0004287433,0.00129989,0.0004132033],"domain_scores_gemma":[0.9957476,0.00006966481,0.00008572724,0.0005124055,0.0000498439,0.003534802],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000311968,0.004938487,0.4635403,0.001316862,0.0004157446,0.0006928636,0.009938087,0.000001334225,0.0358957,0.008943886,0.2422553,0.2317495],"study_design_scores_gemma":[0.003934536,0.0003307244,0.06884272,0.001105896,0.00009823047,0.0003782434,0.004228459,0.002013016,0.0006302876,0.0001295056,0.9178983,0.0004101065],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7623406,0.000214045,0.0000291746,0.2224014,0.0006483805,0.0002765376,0.000001089318,0.0001396042,0.01394912],"genre_scores_gemma":[0.8433008,0.0001692359,0.0003064224,0.002590673,0.001117452,0.000028693,0.00004457189,0.00003366722,0.1524085],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.675643,"threshold_uncertainty_score":0.9563745,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09215279995702202,"score_gpt":0.4255518770677294,"score_spread":0.3333990771107074,"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."}}