{"id":"W2944024971","doi":"10.48550/arxiv.1905.05116","title":"Petabytes to Science","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Research Data Management Practices","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"High Energy Physics; Office of Science; Kavli Foundation; U.S. Department of Energy","keywords":"Petabyte; Computer science; Data mining; Big data","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":["metaepi_narrow","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["scholarly_communication","open_science"],"category_scores_codex":[0.001503892,0.0002528644,0.0002410256,0.0009833659,0.0002432063,0.003041368,0.0137071,0.00009004107,0.00003122196],"category_scores_gemma":[0.0005052182,0.0002839116,0.00009627525,0.002257037,0.000231744,0.01763423,0.02535743,0.0005649293,0.001115873],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003097917,"about_ca_system_score_gemma":0.0006697431,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000225424,"about_ca_topic_score_gemma":0.00002533631,"domain_scores_codex":[0.996581,0.0001340047,0.0001513373,0.002094853,0.0003853134,0.0006535136],"domain_scores_gemma":[0.994929,0.0001575741,0.0001806966,0.004076858,0.0003026332,0.0003532626],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00001268625,0.00006034607,0.001694797,0.00006972104,0.00003625619,0.0002076707,0.00008225213,0.08987411,0.0001012515,0.9063882,0.0009803217,0.00049238],"study_design_scores_gemma":[0.0005812556,0.0002266358,0.01316473,0.0002149048,0.00007021176,0.000005993759,0.0002129807,0.8868579,0.001096831,0.02330417,0.07276007,0.001504357],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0871582,0.00002822081,0.8727527,0.0008129855,0.0008852343,0.0006361902,0.00001341841,0.0002468697,0.03746619],"genre_scores_gemma":[0.9796045,0.000265617,0.007088592,0.0002454748,0.00004657774,0.000001287635,0.000005714997,0.00001179641,0.01273044],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8924463,"threshold_uncertainty_score":0.9999613,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.200391289578873,"score_gpt":0.2626425860806819,"score_spread":0.06225129650180886,"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."}}