{"id":"W4402059671","doi":"10.1038/s42256-024-00884-w","title":"A step forward in tracing and documenting dataset provenance","year":2024,"lang":"en","type":"article","venue":"Nature Machine Intelligence","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"","keywords":"Provenance; Tracing; Computer science; Geology; Paleontology; Programming language","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.005613092,0.0001539149,0.0001899807,0.0004884696,0.0001072733,0.00133994,0.0008888415,0.00008469653,0.0001281073],"category_scores_gemma":[0.0022887,0.0001083603,0.0000434264,0.001570811,0.00007147353,0.000545101,0.0006417962,0.0006613698,0.0001625225],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003465673,"about_ca_system_score_gemma":0.00003058549,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001403894,"about_ca_topic_score_gemma":0.0002925746,"domain_scores_codex":[0.9970902,0.00009178909,0.0005591813,0.001064236,0.0008955204,0.0002991336],"domain_scores_gemma":[0.9980536,0.001006521,0.00007922121,0.0007384733,0.00004892744,0.00007327752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0000113307,0.00002389929,0.00170559,0.0000451242,0.00000825511,0.00009911135,0.0004390196,0.0004055723,0.00004180648,0.01297534,0.03564342,0.9486015],"study_design_scores_gemma":[0.00007500605,0.00003625495,0.001806598,0.0003228028,0.00001127164,0.00004069314,0.0004882939,0.4646604,0.0006014792,0.03908136,0.492599,0.0002768054],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0891527,0.043743,0.8282089,0.009661293,0.009043858,0.001425384,0.001868182,0.0004617682,0.01643491],"genre_scores_gemma":[0.9944846,0.00004591003,0.003860433,0.0002975177,0.0000757685,0.000006913816,0.00008550016,0.000008448731,0.001134905],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9483247,"threshold_uncertainty_score":0.9996968,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03803067718090124,"score_gpt":0.4079694461843914,"score_spread":0.3699387690034902,"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."}}