{"id":"W2111340440","doi":"10.1177/1356389009105883","title":"How Legitimate and Justified are Judgments in Program Evaluation?","year":2009,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":43,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Value (mathematics); Function (biology); Psychology; Order (exchange); Social psychology; Computer science; Economics","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01836231,0.0001523123,0.0002203653,0.0004113478,0.0001533612,0.0007103499,0.0002271416,0.00008133375,0.000843833],"category_scores_gemma":[0.002661707,0.0001226223,0.00004232702,0.0008052549,0.00003987708,0.001124879,0.00003169938,0.0001248731,0.00011482],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002067434,"about_ca_system_score_gemma":0.0002784689,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000004404109,"about_ca_topic_score_gemma":0.0001010905,"domain_scores_codex":[0.9933326,0.000764783,0.0005463072,0.0005169652,0.004592764,0.0002466263],"domain_scores_gemma":[0.9976911,0.0001949909,0.000366344,0.0004201976,0.001241135,0.00008622392],"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":[0.00002510997,0.0001573245,0.01312211,0.000003075247,0.000004716643,6.298372e-7,0.0005798356,0.001941315,0.0003168528,0.0003987791,0.00183088,0.9816194],"study_design_scores_gemma":[0.001329937,0.0001236392,0.501936,0.00002351389,0.00003151119,0.00000167968,0.0008003042,0.4754462,0.0001009488,0.01774437,0.002347804,0.0001140537],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.967433,0.0003116457,0.0003725959,0.01679041,0.0004258271,0.003843633,0.000005646445,0.000062554,0.01075462],"genre_scores_gemma":[0.9968715,0.00001764372,0.001339965,0.0004808336,0.00008137139,0.0004849799,0.00004993959,0.000006013042,0.0006677705],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9815053,"threshold_uncertainty_score":0.9239379,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3428563984356187,"score_gpt":0.5551089461910942,"score_spread":0.2122525477554755,"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."}}