{"id":"W4362681378","doi":"10.3138/cjpe.18.001","title":"Evaluation and Research: Differences and Similarities","year":2003,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":57,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Generalization; Similarity (geometry); Relevance (law); Causality (physics); Psychology; Management science; Computer science; Knowledge management; Epistemology; Artificial intelligence; Political 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"],"category_scores_codex":[0.08505214,0.0000954722,0.0001893079,0.0009065759,0.0004349087,0.0008093224,0.0001902908,0.00007599516,0.001613657],"category_scores_gemma":[0.01742486,0.00007102668,0.00003748609,0.0006272737,0.0002954662,0.0006845726,0.00001092887,0.0002482963,0.00001161657],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002338544,"about_ca_system_score_gemma":0.005247738,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000255523,"about_ca_topic_score_gemma":0.01173654,"domain_scores_codex":[0.9910994,0.003073377,0.0006434766,0.0002176959,0.004689834,0.0002762164],"domain_scores_gemma":[0.9909535,0.0006852574,0.0003042629,0.000184083,0.007424066,0.0004488312],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.00000538315,0.00001839489,0.07548368,0.000003946727,0.00001920544,0.000001576365,0.002120622,0.00008591494,0.00001783085,0.003550024,0.001054728,0.9176387],"study_design_scores_gemma":[0.001673118,0.001028292,0.5774608,0.00008341578,0.0001759767,0.0001101379,0.0123404,0.07123373,0.00009436619,0.2831823,0.05240655,0.0002109959],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9844016,0.00381466,0.0001452874,0.002057424,0.000425475,0.001016421,0.000003009512,0.000003857947,0.008132269],"genre_scores_gemma":[0.99806,0.00008386681,0.001533728,0.00007177858,0.00006955137,0.00006099391,0.000001629731,0.000005473414,0.0001129416],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9174277,"threshold_uncertainty_score":0.999299,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7713106731453503,"score_gpt":0.617815743068949,"score_spread":0.1534949300764012,"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."}}