{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.002099262,0.0009411397,0.0007336547,0.004670136,0.001094143,0.001836436,0.001451651,0.001120257,0.0335826],"category_scores_gemma":[0.01246167,0.0004358285,0.0006933491,0.007899582,0.0004019865,0.001008061,0.00235538,0.001345363,0.04128934],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001769313,"about_ca_system_score_gemma":0.002914817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02899771,"about_ca_topic_score_gemma":0.06497464,"domain_scores_codex":[0.9977211,0.0003971371,0.0004171348,0.0004325621,0.0006974185,0.0003346225],"domain_scores_gemma":[0.9936199,0.001316977,0.0008603241,0.001445312,0.002306909,0.0004506288],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001936423,0.00007295633,0.01127423,0.0008974612,0.00002708815,0.00007617293,0.0003638201,0.0002018262,0.0003908702,0.001267455,0.9763988,0.008835752],"study_design_scores_gemma":[0.0001365664,0.00003380064,0.03842077,0.0004765759,0.00002554842,0.0001475387,0.001118915,0.0002949482,0.000965383,0.0007961843,0.9575476,0.00003618131],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.00208536,0.00007002291,0.0001326257,0.0001055099,0.00002968403,0.00005130412,0.995836,0.0001245467,0.001564947],"genre_scores_gemma":[0.002470153,0.00004546935,0.0004966951,0.00005531222,0.00000896716,0.0002707426,0.9951834,0.00004891767,0.001420239],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.9979007,"threshold_uncertainty_score":0.112345,"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."}}