{"id":"W4367030059","doi":"10.3138/cjpe.25.007","title":"S. Donaldson, C.A. Christie, and M.M. Mark. (2009) <i>What Counts as Credible Evidence in Applied Research and Evaluation Practice?</i> Thousand Oaks, CA: Sage. 265 pages.","year":2010,"lang":"en","type":"article","venue":"Canadian Journal of Program Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"SAGE; Psychology; Physics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.06571472,0.0001320375,0.0002231542,0.0008755207,0.000286458,0.001355794,0.0003024094,0.0001467292,0.002546331],"category_scores_gemma":[0.01113759,0.0001094794,0.00002937551,0.0009649599,0.0002575335,0.001761228,0.0000301146,0.0006690407,0.0001134205],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002778988,"about_ca_system_score_gemma":0.005868854,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006317727,"about_ca_topic_score_gemma":0.02345656,"domain_scores_codex":[0.9936177,0.0008903885,0.0007734778,0.0003419224,0.004023171,0.0003534061],"domain_scores_gemma":[0.9934585,0.001372374,0.0004905142,0.0003031648,0.003913913,0.0004614991],"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":[0.00006660221,0.0000447795,0.007211012,0.00001023358,0.00001283117,0.000009309807,0.0008108284,0.0001117844,0.0002290036,0.0003295726,0.01465211,0.976512],"study_design_scores_gemma":[0.003748184,0.001198731,0.1955788,0.0006451221,0.0002359465,0.0004056032,0.008365675,0.0880501,0.0002772612,0.0468626,0.6541066,0.0005253853],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9241366,0.02474648,0.0001388971,0.01741785,0.002668926,0.004242599,0.00001142327,0.00001353611,0.02662367],"genre_scores_gemma":[0.9948781,0.00191529,0.002160538,0.0002833547,0.0002283485,0.0001297083,0.000009910395,0.00001220623,0.0003826124],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9759865,"threshold_uncertainty_score":0.9997669,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3534349116066584,"score_gpt":0.5479246449963839,"score_spread":0.1944897333897255,"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."}}