{"id":"W2606670574","doi":"10.3138/cjpe.327","title":"The Oral History of Evaluation: An Interview with Lyn Shulha","year":2017,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"","keywords":"Formative assessment; Scholarship; LYN; Oral history; Psychology; Evaluation methods; Pedagogy; Medical education; Sociology; Political science; Medicine; Engineering; Anthropology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.05068516,0.0001227339,0.0002582055,0.0002944285,0.000551541,0.0006001338,0.001125596,0.00005934594,0.002442188],"category_scores_gemma":[0.003867732,0.00007018106,0.0001139118,0.0001772916,0.0004244891,0.001361827,0.00001985237,0.0001920249,0.00002710537],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001059949,"about_ca_system_score_gemma":0.01538695,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006598737,"about_ca_topic_score_gemma":0.08782984,"domain_scores_codex":[0.9936028,0.001352885,0.0009702855,0.0001928306,0.003646839,0.0002344147],"domain_scores_gemma":[0.9887887,0.0001907229,0.002088967,0.0009327498,0.007617545,0.0003813068],"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":[0.00002663807,0.00002981948,0.01047103,0.000003279059,0.00003242689,0.000002256766,0.001112554,0.000513297,0.000008453749,0.0003907528,0.005895641,0.9815139],"study_design_scores_gemma":[0.002189405,0.002074605,0.3350661,0.0001591857,0.0003435991,0.00007701368,0.002234873,0.1451796,0.00004379822,0.009075994,0.5033405,0.0002153375],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9124907,0.009886858,0.00188707,0.02132958,0.007674767,0.004747633,0.00001292752,0.00001772502,0.0419527],"genre_scores_gemma":[0.9974117,0.00002601701,0.001492354,0.000146004,0.0001560065,0.00007139397,0.000005821499,0.000009677075,0.0006809911],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9812985,"threshold_uncertainty_score":0.9984697,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6363883769916328,"score_gpt":0.5707644898010387,"score_spread":0.06562388719059409,"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."}}