{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005484724,0.0001731842,0.0002374977,0.0001377959,0.000259149,0.0008886683,0.001706442,0.0002405381,0.000006882507],"category_scores_gemma":[0.007876324,0.0001635444,0.0000430766,0.0003305612,0.00008562582,0.0001062139,0.003950999,0.001316963,0.00006974064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000409673,"about_ca_system_score_gemma":0.0002934117,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001943558,"about_ca_topic_score_gemma":0.0003221888,"domain_scores_codex":[0.9963379,0.0001890881,0.0003892369,0.001877044,0.000677349,0.0005293848],"domain_scores_gemma":[0.9956334,0.000572218,0.0002330753,0.002803667,0.0006374818,0.0001202076],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003515455,0.0003836366,0.01467553,0.004258341,0.0002815103,0.0006678508,0.05458622,0.01197403,0.0002801565,0.7821849,0.02210879,0.1085639],"study_design_scores_gemma":[0.0002933719,0.0001022778,0.002876611,0.0004839854,0.00001857719,0.00001510361,0.0006403043,0.619463,0.001422034,0.3136609,0.06014948,0.0008743491],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02734352,0.001557853,0.9269851,0.009487922,0.006514351,0.000886646,0.0000199311,0.001497196,0.02570747],"genre_scores_gemma":[0.6743758,0.001306912,0.307996,0.00009253035,0.001650426,0.00009301721,0.000008958367,0.00004339439,0.01443297],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6470323,"threshold_uncertainty_score":0.9429264,"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."}}