{"id":"W2014366393","doi":"10.1177/1356389003094006","title":"Evaluability Assessment: A Tool for Incorporating Evaluation in Social Change Programmes","year":2003,"lang":"en","type":"article","venue":"Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":61,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; University of Calgary","funders":"","keywords":"Behaviour change; Social change; Theory of change; Process management; Political science; Engineering ethics; Management science; Sociology; Public relations; Psychology; Engineering; Psychological intervention","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"opus","categories":[],"domain":null,"study_design":"theoretical_or_conceptual","genre":"methods","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1180866,0.0002294279,0.0003616562,0.0004726572,0.0004839381,0.0003664751,0.0003139536,0.0001600882,0.002436979],"category_scores_gemma":[0.01336003,0.0001987238,0.0001614175,0.001478611,0.00007076483,0.001369372,0.00004091121,0.0001898333,0.00008134908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009796759,"about_ca_system_score_gemma":0.001817545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002298492,"about_ca_topic_score_gemma":0.0003236529,"domain_scores_codex":[0.9859606,0.004320595,0.0015096,0.0008743553,0.006894502,0.0004403371],"domain_scores_gemma":[0.9941632,0.001079229,0.0007343861,0.0004998351,0.003461167,0.00006217799],"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":[0.00005073347,0.0003472197,0.1478976,0.00002194463,0.00001617358,1.509991e-7,0.00328059,0.00228102,0.0002612559,0.02023975,0.0007529138,0.8248506],"study_design_scores_gemma":[0.002676465,0.000147888,0.3620331,0.00001506147,0.00006425616,8.96538e-7,0.0009290943,0.4717394,0.0001041365,0.1593312,0.00274651,0.0002120115],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9666018,0.0001419988,0.008847391,0.002348061,0.0009464109,0.009916979,0.00001814176,0.00005711073,0.0111221],"genre_scores_gemma":[0.9837788,0.00000221546,0.008671657,0.0002821225,0.0002867167,0.006716622,0.000143138,0.00001779849,0.0001009823],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8246386,"threshold_uncertainty_score":0.998475,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4539931329436821,"score_gpt":0.5881362452183663,"score_spread":0.1341431122746842,"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."}}