{"id":"W4384704291","doi":"10.3138/cjpe.38.1.ed-en","title":"Editor’s Remarks","year":2023,"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":"Philosophy; Psychology","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":["insufficient_payload"],"category_scores_codex":[0.02462782,0.00008301158,0.0001691798,0.001070132,0.0001982273,0.0003929544,0.0004595897,0.00007228107,0.00389038],"category_scores_gemma":[0.005499139,0.00006263263,0.0001180169,0.001647233,0.00006102372,0.0005616982,0.0000110807,0.0001752962,0.0009119622],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000258265,"about_ca_system_score_gemma":0.005348408,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001839598,"about_ca_topic_score_gemma":0.008594621,"domain_scores_codex":[0.9955053,0.000415694,0.0007865304,0.0001516792,0.002868767,0.0002720561],"domain_scores_gemma":[0.9953159,0.0002855457,0.0004931246,0.0002655536,0.003168753,0.0004710908],"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":[0.000004549832,0.000008382617,0.01163678,0.000001386721,0.00001085207,0.000006441872,0.0004763218,0.001654679,0.00001812847,0.000191203,0.2884231,0.6975682],"study_design_scores_gemma":[0.0006104685,0.0003107812,0.1334134,0.00003110775,0.00004028089,0.00002383805,0.001339773,0.07667341,0.00004251315,0.01696751,0.7704299,0.0001170214],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8371174,0.0009715643,0.002445411,0.03685035,0.06468003,0.003613423,0.00002920604,0.0001323375,0.05416026],"genre_scores_gemma":[0.9940449,0.00001322061,0.001443877,0.0002056386,0.003164809,0.0000453303,0.00001773646,0.000009942429,0.001054549],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6974512,"threshold_uncertainty_score":0.9998659,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3016607384097375,"score_gpt":0.5419447489581198,"score_spread":0.2402840105483823,"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."}}