{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.07067816,0.001471325,0.0028242,0.01040353,0.003653172,0.02735069,0.007552304,0.005276559,0.004808839],"category_scores_gemma":[0.2395056,0.001933412,0.004088167,0.009758541,0.004321236,0.038192,0.01369206,0.01323732,0.004276966],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003002577,"about_ca_system_score_gemma":0.02269381,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01771741,"about_ca_topic_score_gemma":0.02494861,"domain_scores_codex":[0.9450209,0.02089168,0.008515835,0.007115324,0.01738814,0.001068242],"domain_scores_gemma":[0.5670145,0.1108247,0.01321665,0.2461479,0.05778111,0.005015121],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009183274,0.0009782789,0.02782228,0.004013249,0.001025416,0.0008576241,0.007162862,0.01074833,0.0198424,0.2003119,0.07554578,0.6507736],"study_design_scores_gemma":[0.0002155746,0.0003879225,0.00604018,0.004117564,0.0007437547,0.00154044,0.003417782,0.1184912,0.02725814,0.4049674,0.4323108,0.0005091728],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.004725361,0.002226434,0.9606228,0.01306006,0.0006801834,0.001208288,0.003910007,0.01128974,0.002277018],"genre_scores_gemma":[0.02895681,0.001187604,0.9589719,0.001024542,0.0001686177,0.0003031789,0.006984796,0.001018097,0.001384383],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9293218,"threshold_uncertainty_score":0.3737863,"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."}}