{"id":"W4386601204","doi":"10.1162/qss_a_00264","title":"Tracing data: A survey investigating disciplinary differences in data citation","year":2023,"lang":"en","type":"article","venue":"Quantitative Science Studies","topic":"Research Data Management Practices","field":"Computer Science","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; Communications Research Centre Canada; Université de Montréal; Wilfrid Laurier University; University of Ottawa","funders":"High Energy Physics; CERN; Alfred P. Sloan Foundation","keywords":"Discipline; Citation; Data science; Tracing; Data sharing; TRACE (psycholinguistics); Computer science; Reuse; Survey data collection; Citation analysis; World Wide Web; Sociology; Social science; Statistics; Engineering; 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":["metaresearch","scholarly_communication","open_science"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.02321332,0.0001705708,0.0002759072,0.001011941,0.000895814,0.002037641,0.01116652,0.00001691972,7.586613e-7],"category_scores_gemma":[0.04404158,0.0001374608,0.00001031231,0.01019173,0.001636196,0.08056462,0.02031848,0.0002263825,0.00006275586],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006642719,"about_ca_system_score_gemma":0.000294285,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003568979,"about_ca_topic_score_gemma":0.00299132,"domain_scores_codex":[0.9951404,0.0007145258,0.0004115046,0.00167963,0.001398124,0.0006557922],"domain_scores_gemma":[0.9904703,0.005703674,0.0002790409,0.003077041,0.0003587889,0.0001111154],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0000309601,0.0002429013,0.5285851,0.0004170366,0.0002297494,0.0001944958,0.05339371,0.0005181614,0.002643399,0.3837839,0.008311634,0.02164895],"study_design_scores_gemma":[0.0001190218,0.00007519482,0.7036204,0.0001245808,0.000003773382,6.347409e-7,0.01513632,0.2752424,0.00003083619,0.005416737,0.00004494935,0.0001850891],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.904544,0.001178735,0.0805676,0.01057813,0.000916937,0.0007038926,0.0003316406,0.0003457699,0.0008333028],"genre_scores_gemma":[0.9547784,0.001093632,0.04367157,0.00004938598,0.00002096529,0.00002736367,0.0001896306,0.000006926514,0.0001620692],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3783672,"threshold_uncertainty_score":0.9989983,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.822593535018854,"score_gpt":0.5661646224853495,"score_spread":0.2564289125335045,"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."}}