{"id":"W4405366000","doi":"10.3138/cjpe-2023-0011","title":"When we say evaluation, it isn’t the same thing","year":2023,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Sociology; Computer science","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch","insufficient_payload"],"category_scores_codex":[0.07333303,0.0001615243,0.0002516611,0.0009754174,0.000658005,0.000977325,0.0009983879,0.00009847059,0.01245882],"category_scores_gemma":[0.009676247,0.000101471,0.0001929862,0.001806179,0.0001312754,0.000967689,0.00002971431,0.0003505508,0.001014627],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006170236,"about_ca_system_score_gemma":0.009163156,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005210097,"about_ca_topic_score_gemma":0.02759791,"domain_scores_codex":[0.990172,0.00176226,0.001289311,0.0002766362,0.006061411,0.000438326],"domain_scores_gemma":[0.9915784,0.0008549698,0.0009217213,0.0005463901,0.00566238,0.0004361093],"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":[0.000006773265,0.00001266639,0.004104524,0.000002590028,0.0000334785,0.000003047554,0.007778429,0.01050976,0.00001826348,0.0004230048,0.1890686,0.7880388],"study_design_scores_gemma":[0.0009510927,0.0002539149,0.04707082,0.00008079245,0.0001881347,0.00003854648,0.01018248,0.3825123,0.00003442703,0.0789678,0.4795385,0.0001811185],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.3947107,0.003754188,0.002659415,0.5453715,0.009123754,0.007657325,0.00003318272,0.0001127186,0.03657724],"genre_scores_gemma":[0.9927279,0.00006742164,0.001399749,0.002078971,0.0006328551,0.0002142577,0.0000326581,0.00002096427,0.002825222],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7878577,"threshold_uncertainty_score":0.9997632,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5162236582112425,"score_gpt":0.5551123995560459,"score_spread":0.03888874134480336,"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."}}