{"id":"W4393901348","doi":"10.3138/cjpe-2024-0014","title":"Exploring the Edges: Identifying the Next Generation of Evaluation Capacity Building Research and Practice Through Adjacency","year":2024,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; McGill University","funders":"","keywords":"Adjacency list; Computer science; Data science; Algorithm","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gpt","categories":[],"domain":null,"study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"},{"model":"opus","categories":["metaresearch"],"domain":"methods","study_design":"design_other","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.11673,0.0001114516,0.0001632952,0.0005679639,0.0008444909,0.001912417,0.0004269771,0.00005158637,0.0003224876],"category_scores_gemma":[0.02139352,0.00006293245,0.00008404123,0.001801551,0.0002990434,0.004436424,0.00003294631,0.000519515,0.00001859862],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005224562,"about_ca_system_score_gemma":0.00414481,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001181836,"about_ca_topic_score_gemma":0.006214315,"domain_scores_codex":[0.9893242,0.003893314,0.00102801,0.0002762985,0.005187348,0.0002908357],"domain_scores_gemma":[0.9876684,0.003256726,0.0005061209,0.000377832,0.00804322,0.0001476765],"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":[0.00001205139,0.00002002517,0.0002827678,0.00001648511,0.00004767217,0.000002105856,0.01631584,0.002468355,0.00189501,0.005943912,0.001708836,0.971287],"study_design_scores_gemma":[0.001036059,0.00103548,0.02302508,0.0006633711,0.0006353957,0.0004092969,0.0599138,0.7177952,0.005387249,0.09536388,0.0944412,0.0002940077],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9655131,0.008245965,0.005379184,0.01487624,0.002530932,0.001910114,0.000003372045,0.000008431551,0.001532676],"genre_scores_gemma":[0.9952447,0.0003584793,0.003423192,0.00008269404,0.0006328672,0.0002126971,0.000003996708,0.00001061289,0.00003069999],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9709929,"threshold_uncertainty_score":0.9991237,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9617855589426995,"score_gpt":0.6449060188564266,"score_spread":0.3168795400862728,"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."}}