{"id":"W2559640429","doi":"10.4300/jgme-d-16-00540.1","title":"Using Data From Program Evaluations for Qualitative Research","year":2016,"lang":"en","type":"article","venue":"Journal of Graduate Medical Education","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":14,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Wilson Centre; University of Toronto","funders":"","keywords":"Computer science; Qualitative research; Constructive; Flexibility (engineering); Data science; Qualitative property; Quality (philosophy); Research program; Management science; Process (computing); Epistemology; Sociology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"not_applicable","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["metaresearch"],"domain":"methods","study_design":"qualitative","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05893738,0.00007646662,0.0002219217,0.0004322425,0.0002183172,0.0001527063,0.00123464,0.00007213275,0.002069754],"category_scores_gemma":[0.09004665,0.00003942726,0.00007563989,0.0006511335,0.000212233,0.001009917,0.0001145584,0.0002382018,0.000101998],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001871106,"about_ca_system_score_gemma":0.009236262,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004622716,"about_ca_topic_score_gemma":0.00005702351,"domain_scores_codex":[0.9899004,0.001835347,0.001177787,0.0002691738,0.006608981,0.0002083178],"domain_scores_gemma":[0.9829689,0.008663792,0.0007808179,0.0006498304,0.006582296,0.000354378],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006764074,0.0005285211,0.0006425341,0.000003323374,0.00003132761,3.503632e-7,0.003757244,0.000004006332,0.0003278106,0.001239326,0.1244902,0.8689077],"study_design_scores_gemma":[0.002861595,0.00101371,0.01571405,0.0007538229,0.0001151425,0.00003046955,0.03934366,0.07441708,0.0004444128,0.6558953,0.2091608,0.000249978],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6905332,0.0003246214,0.1533713,0.15056,0.003551955,0.0008492637,0.00007564368,0.00001260669,0.0007213973],"genre_scores_gemma":[0.9357293,0.0001329141,0.0611864,0.0004731542,0.001604817,0.00004503786,0.00004470892,0.00001183483,0.0007717832],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8686578,"threshold_uncertainty_score":0.9988425,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.952474250576773,"score_gpt":0.8161911414528664,"score_spread":0.1362831091239066,"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."}}