{"id":"W4366451145","doi":"10.3138/cjpe.031.1.v","title":"Editor’s Remarks","year":2016,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Psychology; 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":[{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"grok","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"opus","categories":[],"domain":null,"study_design":"not_applicable","genre":"editorial","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01783849,0.0000856546,0.0001660999,0.0005725179,0.00013778,0.0002499729,0.000456578,0.00007113878,0.008335228],"category_scores_gemma":[0.006238589,0.00004694643,0.0001139059,0.000471708,0.00008704193,0.0007777386,0.000008196827,0.0001003138,0.0003532674],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004004675,"about_ca_system_score_gemma":0.005503669,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001159423,"about_ca_topic_score_gemma":0.008389437,"domain_scores_codex":[0.9958554,0.0004423026,0.0008024528,0.0001537656,0.002507751,0.000238312],"domain_scores_gemma":[0.9944455,0.0003515647,0.0006013865,0.000285142,0.003805639,0.0005107857],"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":[0.00000698549,0.00001126541,0.01554654,6.105932e-7,0.000009550195,0.000002335162,0.0001586581,0.00004506719,0.00008708281,0.0002900746,0.09130763,0.8925342],"study_design_scores_gemma":[0.001129203,0.0004587134,0.08259363,0.00007258218,0.0000446287,0.00003873236,0.0003466939,0.003045673,0.0001957855,0.02192565,0.8900163,0.0001324588],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7073417,0.002193891,0.03592408,0.09790035,0.07559558,0.004779668,0.0000482933,0.00007085258,0.07614554],"genre_scores_gemma":[0.9935613,0.00001024463,0.00256914,0.0001905478,0.002768028,0.00002787489,0.000001781423,0.000007255042,0.0008637827],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8924018,"threshold_uncertainty_score":0.9925713,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2352312171100758,"score_gpt":0.5173110315008186,"score_spread":0.2820798143907428,"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."}}