{"id":"W2583699183","doi":"","title":"Data Ingestion for the Connected World.","year":2017,"lang":"en","type":"article","venue":"Conference on Innovative Data Systems Research","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":68,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Ingestion; Medicine","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":[],"domain":null,"study_design":"bench_or_experimental","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":[],"domain":null,"study_design":"not_applicable","genre":"software","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","sts","scholarly_communication","open_science","insufficient_payload"],"consensus_categories":["metaresearch","open_science"],"category_scores_codex":[0.06057546,0.0001804614,0.0003630426,0.0006285084,0.002669919,0.007006608,0.02731622,0.00007358223,0.0002100638],"category_scores_gemma":[0.07575348,0.0001063969,0.00001733666,0.001698861,0.001072163,0.002467089,0.01232761,0.000597105,0.0007861222],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000614393,"about_ca_system_score_gemma":0.0004424358,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001090417,"about_ca_topic_score_gemma":0.002129748,"domain_scores_codex":[0.9925039,0.001398064,0.0008736888,0.001551561,0.003095837,0.000576882],"domain_scores_gemma":[0.9432418,0.01550063,0.001044693,0.03154089,0.008521804,0.0001501352],"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":[0.0001051304,0.00003857412,0.0001399909,0.00002164601,0.00004079803,0.000002532953,0.00006615131,0.000001733041,0.00003463729,0.4347189,0.4871992,0.07763071],"study_design_scores_gemma":[0.0004705325,0.00009480969,0.004021222,0.0001702697,0.000006161026,0.000001234926,0.003682896,0.06365814,0.00003278553,0.01180344,0.9158978,0.000160641],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005522109,0.0006263262,0.4533053,0.1717604,0.01007029,0.01648564,0.1798762,0.0002678325,0.1620859],"genre_scores_gemma":[0.9747884,0.00006685773,0.0002893289,0.0001664004,0.0004852634,0.0002847146,0.00710516,0.00001804651,0.01679582],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9692663,"threshold_uncertainty_score":0.9999919,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9484017230905639,"score_gpt":0.6713623530691826,"score_spread":0.2770393700213813,"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."}}