{"id":"W4319662944","doi":"10.1016/j.evalprogplan.2023.102257","title":"Learning from experiences of evaluators implementing theory-driven evaluations in diverse settings: Building on the contributions of John Mayne","year":2023,"lang":"en","type":"review","venue":"Evaluation and Program Planning","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Honor; Theory of change; Set (abstract data type); Sociology; Engineering ethics; Work (physics); Epistemology; Management science; Psychology; Computer science; Engineering; Philosophy","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":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.04340444,0.0003687064,0.001207827,0.000994964,0.0005987486,0.0002629472,0.0006681592,0.0001762843,0.001515902],"category_scores_gemma":[0.01865708,0.0002392356,0.0003104505,0.002240495,0.0002244147,0.0002827809,0.0002904717,0.0005708483,0.00003520068],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001122024,"about_ca_system_score_gemma":0.0008803715,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003253707,"about_ca_topic_score_gemma":0.00001340372,"domain_scores_codex":[0.9864076,0.006005603,0.002476533,0.0007502797,0.003912264,0.000447657],"domain_scores_gemma":[0.9831658,0.01225753,0.003111901,0.0005071894,0.0008726526,0.00008492757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001517115,0.00005867648,0.0009223409,0.0001737718,0.000129513,7.659045e-7,0.019638,0.00393559,0.00001226724,0.001658647,0.0001301393,0.9733251],"study_design_scores_gemma":[0.003662909,0.001188924,0.002533066,0.03382849,0.002916228,0.000006798986,0.3734897,0.4225227,0.0001901716,0.01453769,0.1438054,0.001317947],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.2000936,0.7854216,0.0008106215,0.0003412154,0.0009476532,0.009305432,0.0002416178,0.0001707792,0.002667499],"genre_scores_gemma":[0.5956558,0.3954026,0.002273139,0.00009644897,0.000323214,0.005006321,0.0009798184,0.00009291028,0.0001697519],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9720072,"threshold_uncertainty_score":0.9993969,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3687882346319569,"score_gpt":0.6091828399366908,"score_spread":0.2403946053047338,"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."}}