{"id":"W4398406215","doi":"10.7910/dvn/gzi7ia","title":"Data for: Identifying Metadata Quality Issues Across Cultures","year":2023,"lang":"en","type":"dataset","venue":"Harvard Dataverse","topic":"Library Science and Information Systems","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University; University of New Brunswick; Ontario Council of University Libraries; University of Toronto","funders":"","keywords":"Metadata; Data quality; Data science; Computer science; Quality (philosophy); Information retrieval; World Wide Web; Engineering","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":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.003486617,0.0004002303,0.0006014912,0.0001796143,0.0005642007,0.00576571,0.01828625,0.000261035,0.0002126969],"category_scores_gemma":[0.00083542,0.0003363745,0.0001431007,0.0007505075,0.0001228506,0.03874697,0.01141371,0.0003034918,0.1274391],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003870608,"about_ca_system_score_gemma":0.0002222042,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001414884,"about_ca_topic_score_gemma":0.0003937545,"domain_scores_codex":[0.995694,0.0001782319,0.00103391,0.001290824,0.001116393,0.0006866239],"domain_scores_gemma":[0.988758,0.0002437239,0.0006982665,0.009958431,0.0001393001,0.0002022576],"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":[0.000004333358,0.00001652112,0.000002262024,0.0002814395,0.00006374755,0.000009705904,0.0002495908,0.00000374205,0.000004828228,0.0006079925,0.9985192,0.0002366291],"study_design_scores_gemma":[0.0002540733,0.00001792872,0.00003964373,0.0000869013,0.00001381809,0.000009321054,0.0007620182,0.001060715,0.00002151285,0.0001500011,0.9971217,0.0004623745],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.000002190935,0.000007660934,0.02875873,0.00008811078,0.003432594,0.0005288014,0.9668315,0.0003211963,0.00002918066],"genre_scores_gemma":[6.256811e-7,0.0003720833,0.004983312,0.000888772,0.0005011669,0.00004856308,0.9907919,0.00001437249,0.002399199],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.1272264,"threshold_uncertainty_score":0.9999088,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1879032716468272,"score_gpt":0.4156928174724945,"score_spread":0.2277895458256673,"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."}}