{"id":"W4391790392","doi":"10.1177/20531680241233439","title":"Promoting Reproducibility and Replicability in Political Science","year":2024,"lang":"en","type":"article","venue":"Research & Politics","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":22,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Laura and John Arnold Foundation","keywords":"Reproducibility; Politics; Political science; Data science; Psychology; Computer science; Statistics; Mathematics; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.7696046,0.001618092,0.00350891,0.01389905,0.009161469,0.02283515,0.008437565,0.009719728,0.004608131],"category_scores_gemma":[0.8978714,0.002471839,0.003461668,0.0113958,0.04040703,0.03207879,0.02159845,0.01302264,0.002146727],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01168283,"about_ca_system_score_gemma":0.04717665,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003231534,"about_ca_topic_score_gemma":0.002406621,"domain_scores_codex":[0.1398815,0.7117491,0.05065042,0.01982262,0.07456183,0.00333461],"domain_scores_gemma":[0.03047486,0.7024124,0.03688687,0.1687747,0.05889494,0.002556326],"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":[0.0006310825,0.0003746957,0.02384206,0.007879073,0.001033542,0.0004533559,0.05313417,0.005975268,0.002334119,0.4349013,0.02902989,0.4404114],"study_design_scores_gemma":[0.0007892877,0.0009469677,0.01206208,0.01704576,0.0006138048,0.0008512106,0.008847037,0.009567384,0.007458949,0.709551,0.2317134,0.0005532589],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03158514,0.02735469,0.6761724,0.1850984,0.007182361,0.007847282,0.0006230376,0.001893677,0.06224309],"genre_scores_gemma":[0.5154763,0.009356702,0.4278211,0.02098454,0.008347686,0.01268466,0.0005473841,0.001028929,0.003752738],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.2303954,"threshold_uncertainty_score":0.2841187,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5427626271480739,"score_gpt":0.6652534810633781,"score_spread":0.1224908539153042,"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."}}