{"id":"W2125410695","doi":"10.1002/ev.221","title":"The partnership of <i>new directions for evaluation</i> and the American evaluation association","year":2007,"lang":"en","type":"article","venue":"New Directions for Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Association (psychology); General partnership; Political science; Computer science; Sociology; Psychology; Law","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","sts"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1213972,0.0002408433,0.0004173595,0.0004138996,0.001835755,0.0004247575,0.000400664,0.0001165505,0.0002831326],"category_scores_gemma":[0.04209621,0.0001533337,0.0003339234,0.001967295,0.0002394326,0.000597711,0.00004352318,0.0001757478,0.00002656018],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009668489,"about_ca_system_score_gemma":0.002148149,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004474797,"about_ca_topic_score_gemma":0.006918659,"domain_scores_codex":[0.989427,0.001832735,0.001596897,0.0006445365,0.006022083,0.0004766887],"domain_scores_gemma":[0.9735965,0.0158574,0.002088497,0.0007377647,0.007550178,0.000169655],"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":[0.000623482,0.00006357041,0.004061639,0.000004261307,0.0001362876,5.473777e-9,0.001669293,0.002687977,0.0001423198,0.004862284,0.05034848,0.9354004],"study_design_scores_gemma":[0.01220988,0.0003335925,0.1080528,0.00002406954,0.001555553,0.000003044249,0.003718077,0.4506046,0.001471977,0.137317,0.2844199,0.0002894347],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5878284,0.009630384,0.2028703,0.08705153,0.01136335,0.04423831,0.0001480553,0.0003752683,0.05649438],"genre_scores_gemma":[0.9803578,0.0004153797,0.002589941,0.0004964293,0.001190442,0.002527056,0.0001458182,0.0000389554,0.01223819],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.935111,"threshold_uncertainty_score":0.9994637,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2183850463981323,"score_gpt":0.5369309968417352,"score_spread":0.3185459504436029,"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."}}