{"id":"W2777631817","doi":"10.1177/2515245918787489","title":"A Unified Framework to Quantify the Credibility of Scientific Findings","year":2018,"lang":"en","type":"article","venue":"Advances in Methods and Practices in Psychological Science","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":229,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Credibility; Scrutiny; Workflow; Data science; Transparency (behavior); Computer science; Falsifiability; Robustness (evolution); Crowdsourcing; Management science; Psychology; Epistemology; Political science; World Wide Web; Economics","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","insufficient_payload"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.4531389,0.0001893444,0.001278637,0.0005241164,0.0004075217,0.001034919,0.003994888,0.00009907527,0.001328973],"category_scores_gemma":[0.441217,0.00007562154,0.000188939,0.01164258,0.003557859,0.001351015,0.0004629791,0.0004240418,0.0001003908],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002327435,"about_ca_system_score_gemma":0.00004460505,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001498568,"about_ca_topic_score_gemma":0.00008283646,"domain_scores_codex":[0.9738176,0.01539097,0.004517906,0.002251926,0.003537521,0.0004840048],"domain_scores_gemma":[0.9261107,0.06112397,0.005513872,0.005626561,0.001339264,0.0002855627],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0001046077,0.0002261414,0.2737986,0.00002050664,0.000005999846,0.000003187886,0.002991002,0.00005427342,0.004236663,0.08564903,0.0002789319,0.6326311],"study_design_scores_gemma":[0.0001032273,0.0002807784,0.3512579,0.00006043494,0.00001524233,0.000009888914,0.001771546,0.002594066,0.0004597072,0.5243573,0.11892,0.0001699772],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8391091,0.001441396,0.1410084,0.002654719,0.001274202,0.000578229,0.000002210371,0.000003264017,0.01392852],"genre_scores_gemma":[0.600878,0.00009900812,0.3985267,0.0003488336,0.00002810053,0.00001623244,6.611124e-8,0.000001614522,0.0001014604],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6324611,"threshold_uncertainty_score":0.999584,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7627076276557118,"score_gpt":0.7394797943067195,"score_spread":0.02322783334899226,"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."}}