{"id":"W3203262347","doi":"10.1002/ev.20477","title":"A learning agenda for the advocacy evaluation field's future","year":2021,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact","funders":"","keywords":"Field (mathematics); Context (archaeology); Value (mathematics); Set (abstract data type); Political science; Public relations; Engineering ethics; Sociology; Computer science; Engineering","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":[],"category_scores_codex":[0.01600373,0.0001498299,0.0001854911,0.0001868717,0.00126776,0.0004147694,0.0002675837,0.0001139876,0.005554328],"category_scores_gemma":[0.01832935,0.0001071028,0.0002743444,0.001030589,0.0000197179,0.0004791522,0.00003776214,0.000170514,0.0001073433],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002282328,"about_ca_system_score_gemma":0.002530747,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003486905,"about_ca_topic_score_gemma":0.0006329285,"domain_scores_codex":[0.9953591,0.0006964528,0.0006113049,0.0005176824,0.002575575,0.0002399354],"domain_scores_gemma":[0.9898591,0.004521762,0.0003291367,0.0005472681,0.004671899,0.00007081618],"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":[0.00004856,0.00003679707,0.0004324472,0.000003748105,0.00003984097,3.842633e-8,0.001235252,0.01836007,0.0003206586,0.0006668158,0.0830245,0.8958313],"study_design_scores_gemma":[0.001640714,0.0001415661,0.006834121,0.000009000799,0.0002508901,0.00000393466,0.00379956,0.4461832,0.001436178,0.01325734,0.5263349,0.000108549],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1023997,0.007745099,0.6805682,0.136775,0.02429066,0.01301636,0.00004821366,0.0003381291,0.03481866],"genre_scores_gemma":[0.9354746,0.0004216585,0.01063819,0.002486283,0.004643876,0.004459319,0.0005128452,0.00004919193,0.04131401],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8957227,"threshold_uncertainty_score":0.9953547,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2594203796997051,"score_gpt":0.5452853487151225,"score_spread":0.2858649690154174,"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."}}