{"id":"W4384704311","doi":"10.3138/cjpe.76031","title":"<i>Ethics for Evaluation. Beyond “Doing No Harm” to “Tackling Bad” and “Doing Good”</i> , par Rob van den Berg, Penny Hawkins et Nicoletta Stame (dir.)","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":false,"ca_institutions":"","funders":"","keywords":"Harm; Psychology; Social 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":"review","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":"commentary","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":"commentary","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.07364395,0.001420319,0.002125959,0.002057136,0.004638542,0.01382748,0.002265208,0.01844709,0.009137097],"category_scores_gemma":[0.1146255,0.000938415,0.00128714,0.002158573,0.02179815,0.01267079,0.005472525,0.02415841,0.007148097],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01277872,"about_ca_system_score_gemma":0.02377133,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02820055,"about_ca_topic_score_gemma":0.05304781,"domain_scores_codex":[0.9024673,0.05833368,0.005518034,0.003351111,0.02751745,0.002812491],"domain_scores_gemma":[0.8712116,0.08855741,0.005050232,0.005006727,0.02536151,0.004812379],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001589842,0.000005942098,0.00007333773,0.0002779892,0.00001151698,0.00002406601,0.000367466,0.0000240396,0.0000434016,0.03316538,0.9482549,0.01773606],"study_design_scores_gemma":[0.0000216676,0.00001771603,0.0006969647,0.002180409,0.00001439276,0.0001685654,0.000642209,0.0001091313,0.0001117503,0.07716455,0.9188427,0.00002988586],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"commentary","genre_gemma":"review","genre_scores_codex":[0.00006091165,0.1078341,0.001605876,0.8480071,0.02455444,0.00004670236,0.00009184448,0.0000841943,0.01771479],"genre_scores_gemma":[0.01154112,0.09038875,0.008678679,0.7676393,0.07018544,0.0006785678,0.0002248102,0.0004778708,0.05018549],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.07364395,"threshold_uncertainty_score":0,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2641401555920312,"score_gpt":0.5229258898039616,"score_spread":0.2587857342119304,"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."}}