{"id":"W4247289468","doi":"10.31222/osf.io/vtpmb","title":"Predicting and reasoning about replicability using structured groups","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Advanced Research Projects Agency; Defense Advanced Research Projects Agency","keywords":"Heuristics; Replication (statistics); Psychology; Replicate; Protocol (science); Social psychology; Qualitative property; Cognitive psychology; Subject (documents); Applied psychology; Computer science; Machine learning; Statistics","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":[0.7848277,0.003776251,0.006381484,0.02029598,0.004073699,0.01079274,0.00922931,0.007626312,0.004162645],"category_scores_gemma":[0.935755,0.00311606,0.009495526,0.01002493,0.01882506,0.01914742,0.01253521,0.008075823,0.0008696935],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.006830467,"about_ca_system_score_gemma":0.005804865,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001460311,"about_ca_topic_score_gemma":0.001585965,"domain_scores_codex":[0.1306962,0.7020383,0.0699476,0.03955239,0.05566819,0.002097323],"domain_scores_gemma":[0.02029532,0.8593283,0.03406001,0.070855,0.01471882,0.0007425869],"domain_codex":"methods","domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.009856021,0.001310026,0.1178724,0.04966104,0.03959673,0.004287996,0.1353481,0.02822971,0.009596059,0.2419942,0.01402946,0.3482183],"study_design_scores_gemma":[0.002629659,0.002754294,0.0195318,0.01083903,0.005862514,0.001620456,0.01010243,0.07905468,0.01048952,0.8324324,0.02373996,0.0009432501],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1342936,0.009438513,0.8034478,0.008326274,0.004102645,0.02897789,0.001331108,0.001084489,0.008997634],"genre_scores_gemma":[0.4628251,0.0008805795,0.5071993,0.001787252,0.0008627244,0.02513867,0.0006896834,0.0001976711,0.0004190012],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2151723,"threshold_uncertainty_score":0.2653458,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6507383695504559,"score_gpt":0.5206129468572342,"score_spread":0.1301254226932217,"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."}}