{"id":"W4393552829","doi":"10.5281/zenodo.10060518","title":"Replication package for the study \"Broken Windows: Correlating historical and new code quality\"","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Replication (statistics); Computer science; Code (set theory); Operating system; Parallel computing; Programming language; Biology","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","sts","scholarly_communication","insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.01547407,0.000215602,0.000324258,0.0004563748,0.003838911,0.003787068,0.004077487,0.00009290644,0.001011211],"category_scores_gemma":[0.0370758,0.0001628594,0.00009128479,0.001420501,0.0001200316,0.000213202,0.004799908,0.0004016729,0.009115235],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002901743,"about_ca_system_score_gemma":0.00001275701,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005009336,"about_ca_topic_score_gemma":0.00002182901,"domain_scores_codex":[0.9945854,0.0008948236,0.0008818295,0.001596179,0.001667242,0.0003745325],"domain_scores_gemma":[0.9929498,0.001609168,0.0005922487,0.003921958,0.0007104319,0.0002163355],"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":[0.00003362368,0.00008064406,0.000004258908,0.00001952561,0.00003735486,0.000002835706,0.0004012557,0.00003477351,0.000005020673,0.0000962805,0.8822224,0.117062],"study_design_scores_gemma":[0.0004638472,0.0002024448,0.001056978,0.00002045227,0.00005316642,0.000008788682,0.001431344,0.0006518142,7.876228e-7,0.0003871857,0.9955368,0.0001863825],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0003106678,0.0001980425,0.02893988,0.004174061,0.001901468,0.003282288,0.9589643,0.0007998365,0.001429484],"genre_scores_gemma":[0.0008925123,0.00009441896,0.0002015183,0.0002248359,0.0007097493,6.161295e-7,0.9778424,0.0007756542,0.01925829],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1168757,"threshold_uncertainty_score":0.999902,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3380435744248693,"score_gpt":0.4102314932907791,"score_spread":0.0721879188659098,"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."}}