{"id":"W3137174954","doi":"10.1038/s41597-022-01143-6","title":"A large-scale study on research code quality and execution","year":2022,"lang":"en","type":"preprint","venue":"Scientific Data","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Engineering and Physical Sciences Research Council; Alan Turing Institute; Alfred P. Sloan Foundation","keywords":"Computer science; Code reuse; Reuse; Replication (statistics); Coding (social sciences); Code (set theory); Transparency (behavior); Database; Set (abstract data type); Programming language; Software; Computer security","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":["metaresearch","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science","insufficient_payload"],"category_scores_codex":[0.2356041,0.0003192822,0.000573075,0.00190938,0.003349602,0.01020507,0.01518916,0.0001097389,0.001452908],"category_scores_gemma":[0.01266495,0.0002639218,0.00009080756,0.003226952,0.0008009225,0.0004964623,0.1016788,0.001542004,0.0009159633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001742846,"about_ca_system_score_gemma":0.0004063984,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002961047,"about_ca_topic_score_gemma":0.001224531,"domain_scores_codex":[0.9705588,0.005085924,0.001629396,0.00889799,0.01282732,0.001000588],"domain_scores_gemma":[0.970955,0.002341125,0.0005481146,0.02517608,0.0006701946,0.0003095449],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000484356,0.001252583,0.003946444,0.00002414436,0.00002820695,0.00002142354,0.004421141,0.0002157801,0.00001738158,0.0008078281,0.9763145,0.01290211],"study_design_scores_gemma":[0.0005272541,0.000125333,0.06416018,0.0000479249,0.00002874931,0.000001428216,0.05163972,0.02078213,0.00000592224,0.02534096,0.8369264,0.0004139889],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8745673,0.0003111113,0.0052822,0.003468425,0.03012667,0.003295554,0.06922964,0.000275084,0.01344399],"genre_scores_gemma":[0.925193,0.000009253507,0.001231874,0.000163444,0.0003031856,0.0001305734,0.01476941,0.0000375836,0.05816167],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2229391,"threshold_uncertainty_score":0.9999813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7493102534435432,"score_gpt":0.600662037413241,"score_spread":0.1486482160303022,"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."}}