{"id":"W4362683301","doi":"10.3138/cjpe.18.002","title":"The Language of Evaluation Theory: Insights Gained from an Empirical Study of Evaluation Theory and Practice","year":2003,"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":"","funders":"","keywords":"Terminology; Ambiguity; Confusion; Epistemology; Field (mathematics); Vernacular; Empirical research; Psychology; Linguistics; Sociology; Computer science; Philosophy","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"],"category_scores_codex":[0.1491217,0.0001719756,0.0003484505,0.0005437812,0.0003601666,0.0002875756,0.000342345,0.0001052054,0.001111165],"category_scores_gemma":[0.05810173,0.0001099961,0.00008832866,0.0008890314,0.0002095192,0.001153712,0.00001592082,0.0002366886,0.000006750481],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003327773,"about_ca_system_score_gemma":0.0058984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005401118,"about_ca_topic_score_gemma":0.01566254,"domain_scores_codex":[0.9610741,0.02951003,0.001905381,0.0003949662,0.006831573,0.0002839711],"domain_scores_gemma":[0.9824272,0.005418119,0.002002459,0.000609451,0.009228049,0.0003147326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.0004898968,0.0005716317,0.01497759,0.000004238113,0.0002114077,0.000003867814,0.06494115,0.003619173,0.0003413564,0.003538861,0.0003215234,0.9109793],"study_design_scores_gemma":[0.007901782,0.005150538,0.2847515,0.00008693657,0.00235926,0.00006159814,0.3185617,0.1475002,0.0006815763,0.2276261,0.004966112,0.0003527231],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9908292,0.002529248,0.0006522984,0.000643299,0.0005075281,0.00279333,0.000006355074,0.000004693772,0.002034072],"genre_scores_gemma":[0.9986765,0.00001827799,0.000896304,0.0001234558,0.000106219,0.0001168942,0.00001959899,0.00001276623,0.00002993309],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9106266,"threshold_uncertainty_score":0.9998019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2871302531925219,"score_gpt":0.573348207363572,"score_spread":0.28621795417105,"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."}}