{"id":"W2216178707","doi":"","title":"Big data curation","year":2014,"lang":"en","type":"article","venue":"International Conference on Management of Data","topic":"Big Data Technologies and Applications","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Big data; Computer science; Data science; Data curation; Variety (cybernetics); Data management; Analytics; Semantics (computer science); Data modeling; Data mining; Database; Artificial intelligence","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":["open_science"],"consensus_categories":[],"category_scores_codex":[0.001473769,0.00008721791,0.0001168282,0.0001786091,0.00005315273,0.0002281345,0.01170412,0.00003662635,0.0004302857],"category_scores_gemma":[0.0004970837,0.00006815664,0.00001529183,0.0002724064,0.00009156787,0.001007236,0.004996412,0.0000819113,0.0004806917],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000009660845,"about_ca_system_score_gemma":0.00001404068,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002094882,"about_ca_topic_score_gemma":0.00003471841,"domain_scores_codex":[0.997626,0.00003703537,0.0004293331,0.0007013965,0.001106019,0.0001002069],"domain_scores_gemma":[0.9942467,0.0001665003,0.0002664218,0.005107256,0.0001855,0.0000276828],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000005251692,0.0000393765,0.00009350134,0.000001812521,0.00001830531,3.544104e-7,0.000001746248,0.000003275216,0.00004129806,0.4844884,0.03617602,0.4791307],"study_design_scores_gemma":[0.0002230688,0.00003218862,0.002783115,0.00003878957,0.00001386139,6.292803e-7,0.0003140316,0.08182675,0.00007077421,0.1296061,0.7849844,0.0001062175],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002421388,0.00001706678,0.6792082,0.03396322,0.001073302,0.0003499206,0.005483822,0.0001197018,0.2773634],"genre_scores_gemma":[0.9827741,0.0001781225,0.01126054,0.0001907024,0.0001007873,0.000008815004,0.004116593,0.000004773391,0.001365581],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9803527,"threshold_uncertainty_score":0.993643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7668386003949124,"score_gpt":0.4910349129574692,"score_spread":0.2758036874374432,"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."}}