{"id":"W4393717180","doi":"10.5281/zenodo.7555363","title":"A dataset from a survey investigating disciplinary differences in data citation","year":2023,"lang":"en","type":"dataset","venue":"Zenodo (CERN European Organization for Nuclear Research)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa; Université de Montréal","funders":"","keywords":"Citation; Discipline; Data science; Information retrieval; Computer science; Library science; Sociology; Social science","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","metaepi_narrow","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["open_science","insufficient_payload"],"category_scores_codex":[0.0138985,0.00029286,0.0004810998,0.001014923,0.001498358,0.004135063,0.010968,0.0001628795,0.005633729],"category_scores_gemma":[0.03510141,0.0002685714,0.00003785125,0.00262218,0.0003304069,0.001111178,0.02239304,0.0006504412,0.06178365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001125367,"about_ca_system_score_gemma":0.00001624947,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004757983,"about_ca_topic_score_gemma":0.001204928,"domain_scores_codex":[0.9909254,0.00373293,0.00107541,0.001687248,0.002110624,0.0004683846],"domain_scores_gemma":[0.9933506,0.001420372,0.0005893459,0.004023308,0.0003840479,0.0002323806],"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":[0.00003166454,0.0001122002,0.00001479699,0.00004475355,0.00003798103,0.00003178431,0.0002454098,0.000008841506,0.000004880675,0.00003960733,0.9890459,0.01038217],"study_design_scores_gemma":[0.0002993017,0.00006455775,0.01350283,0.0001150302,0.00002153484,0.000003045413,0.0008458822,0.0007177711,4.380943e-7,0.002046588,0.982086,0.0002970044],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.0006657566,0.00003556006,0.000409553,0.0008546799,0.0003286638,0.0005007829,0.9967476,0.0001816018,0.0002757836],"genre_scores_gemma":[0.0004251965,0.0001592714,0.0001244292,0.0001965944,0.0001490437,1.184781e-7,0.9982652,0.0004496351,0.0002304983],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.05614992,"threshold_uncertainty_score":0.9999766,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5749845184576483,"score_gpt":0.4361656372237258,"score_spread":0.1388188812339226,"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."}}