{"id":"W4315796871","doi":"10.31222/osf.io/rcews","title":"Reproducible research practices and transparency across linguistics","year":2023,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Transparency (behavior); Applied linguistics; Open science; Publishing; Empirical research; Data sharing; Best practice; Data science; Psychology; Sociology; Computer science; Public relations; Political science; Linguistics; Medicine; Statistics; Mathematics","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":[0.7294787,0.001795186,0.004227906,0.01766392,0.01099003,0.02907527,0.009062061,0.007960334,0.005235071],"category_scores_gemma":[0.8678921,0.003444985,0.003406088,0.01605356,0.03922171,0.03474104,0.0229473,0.01126498,0.002217136],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01088883,"about_ca_system_score_gemma":0.05017671,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005406103,"about_ca_topic_score_gemma":0.004409954,"domain_scores_codex":[0.1208733,0.6930621,0.07390971,0.03235382,0.0747927,0.005008385],"domain_scores_gemma":[0.03157609,0.5936176,0.08205645,0.2253281,0.06328849,0.004133287],"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":[0.001061033,0.0007362833,0.1133673,0.01418645,0.001824292,0.001571781,0.2520356,0.002711076,0.0069912,0.2351408,0.02134862,0.3490256],"study_design_scores_gemma":[0.0007308837,0.001077494,0.07280856,0.03055827,0.0008324461,0.001986948,0.06190304,0.007175587,0.01266315,0.6051767,0.2042295,0.0008573168],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.141196,0.02182403,0.5720747,0.1933653,0.004530591,0.01132034,0.002297353,0.002170546,0.05122119],"genre_scores_gemma":[0.7068905,0.003632133,0.2592587,0.01190867,0.001770678,0.01119494,0.001106545,0.0008122593,0.003425648],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.2705213,"threshold_uncertainty_score":0.3336011,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5162929941209532,"score_gpt":0.5143864763262007,"score_spread":0.001906517794752483,"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."}}