{"id":"W4377832494","doi":"10.1257/pandp.20231009","title":"Learning Curve: Progress in the Replication Crisis","year":2023,"lang":"en","type":"article","venue":"AEA Papers and Proceedings","topic":"School Choice and Performance","field":"Social Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"Impact","funders":"","keywords":"Replication (statistics); Fidelity; Scale (ratio); Computer science; Learning curve; Psychology; Geography; Mathematics; Statistics; Telecommunications; Cartography","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.5899963,0.00207391,0.003729558,0.002612286,0.003868575,0.00946796,0.008343097,0.006897257,0.01102061],"category_scores_gemma":[0.8307689,0.001951878,0.004687503,0.003311794,0.01229355,0.01683756,0.0115665,0.009605794,0.00378833],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.008150044,"about_ca_system_score_gemma":0.01869309,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004805591,"about_ca_topic_score_gemma":0.002688956,"domain_scores_codex":[0.3848576,0.4831554,0.03775787,0.03020137,0.05752266,0.00650516],"domain_scores_gemma":[0.1015953,0.5999184,0.05047037,0.1718303,0.07096051,0.005225079],"domain_codex":"methods","domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.02254627,0.003720297,0.09286506,0.01124952,0.004889261,0.001037762,0.03806398,0.00821087,0.004759139,0.1127797,0.06826056,0.6316175],"study_design_scores_gemma":[0.01953681,0.05236796,0.1526981,0.01690254,0.004922245,0.002061528,0.02497817,0.04126652,0.01823116,0.2743743,0.3913399,0.00132087],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3140855,0.02004615,0.4102325,0.1254069,0.01105445,0.0521241,0.007501347,0.00516633,0.05438271],"genre_scores_gemma":[0.8185382,0.001238923,0.1191668,0.01561993,0.001250482,0.03521155,0.001877516,0.0009024973,0.006194157],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.4100037,"threshold_uncertainty_score":0.5056076,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02538951414668429,"score_gpt":0.32865587355646,"score_spread":0.3032663594097758,"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."}}