{"id":"W4393902987","doi":"10.3138/cjpe-2024-0005","title":"Learning From Evaluation Data: Discoveries From the Inaugural Evaluation Capacity Case Challenge","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; University of Alberta; McGill University; Queen's University","funders":"","keywords":"Data science; Computer science","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.05805152,0.0002533434,0.0003345252,0.0004648863,0.0007363304,0.002455966,0.001060998,0.0001530358,0.008664388],"category_scores_gemma":[0.01340631,0.0001664076,0.000168476,0.001008462,0.0002101501,0.00345421,0.00007261075,0.0007291111,0.0001974657],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001179679,"about_ca_system_score_gemma":0.009957348,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.01433878,"about_ca_topic_score_gemma":0.1976535,"domain_scores_codex":[0.9867783,0.004224114,0.001399749,0.0006318744,0.006595043,0.0003709165],"domain_scores_gemma":[0.9913881,0.001883727,0.0008035486,0.0009767503,0.004570361,0.0003775486],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001844699,0.00002892939,0.004858145,0.000003684158,0.0001280126,0.00004139897,0.008711324,0.01038222,0.00002571126,0.0001874857,0.004610563,0.9710041],"study_design_scores_gemma":[0.0008474298,0.0003012954,0.02700274,0.0001446216,0.0008754138,0.0001313224,0.009872369,0.885741,0.00002425181,0.02896019,0.04588688,0.0002124874],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9725843,0.00907597,0.001529029,0.008627242,0.004032643,0.002397955,0.0002169805,0.00003087639,0.001504977],"genre_scores_gemma":[0.9964861,0.00006537492,0.001023369,0.0001222355,0.001302575,0.0001781281,0.0007477723,0.00002299766,0.00005142291],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9707916,"threshold_uncertainty_score":0.9985796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7100870622061499,"score_gpt":0.544183741665453,"score_spread":0.1659033205406969,"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."}}