{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.05404024,0.0001976245,0.000697678,0.01380603,0.001588589,0.004059137,0.001209457,0.00115223,0.001262757],"category_scores_gemma":[0.2220657,0.0004430009,0.0004731427,0.02196889,0.001635477,0.004919727,0.003077381,0.0009391494,0.0004789985],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001831735,"about_ca_system_score_gemma":0.00277793,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003519187,"about_ca_topic_score_gemma":0.004053115,"domain_scores_codex":[0.951144,0.02427742,0.009703171,0.003311047,0.0101715,0.001392907],"domain_scores_gemma":[0.5712348,0.2982,0.06853728,0.01526921,0.04087337,0.0058854],"domain_codex":null,"domain_gemma":"reporting","domain_candidate":"reporting","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00008607671,0.00009378694,0.8643249,0.0009792191,0.0001315216,0.0001574813,0.06222489,0.0001500228,0.0008065452,0.001520054,0.001735826,0.06778955],"study_design_scores_gemma":[0.00001856299,0.0002070825,0.8146099,0.001277403,0.00008467467,0.0008592387,0.1485053,0.001092401,0.001162842,0.002549202,0.029534,0.00009942872],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9904957,0.002471432,0.001685192,0.001617211,0.00002313638,0.00006884045,0.0009083652,0.0000262111,0.002703989],"genre_scores_gemma":[0.9946656,0.001966477,0.001729195,0.0003428449,0.00002661653,0.0001298946,0.0006727628,0.00002465478,0.0004420185],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.986194,"threshold_uncertainty_score":0.2857955,"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."}}