{"id":"W4285335450","doi":"10.14778/3494124.3494149","title":"Ember","year":2021,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":15,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Joins; Schema (genetic algorithms); Context (archaeology); Code (set theory); Information retrieval; Theoretical computer science; Artificial intelligence; 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":[],"consensus_categories":[],"category_scores_codex":[0.001749888,0.00008337014,0.0001701068,0.00005396444,0.00009612089,0.0001821532,0.001006377,0.0000244414,0.0006661289],"category_scores_gemma":[0.001565547,0.0000482181,0.0001348915,0.0006024831,0.00007119311,0.0002527189,0.001100249,0.00007328689,0.0001752517],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002698995,"about_ca_system_score_gemma":0.00002674148,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001677757,"about_ca_topic_score_gemma":0.000008547709,"domain_scores_codex":[0.9977883,0.00001697295,0.0004301266,0.0003109235,0.00128322,0.0001704687],"domain_scores_gemma":[0.9988625,0.0001202438,0.0002385895,0.000312225,0.0004163158,0.00005009406],"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":[0.00002260473,0.0002920968,0.00675845,0.00005124116,0.00007451925,0.000002271176,0.001179965,0.00001320449,0.02283172,0.4469793,0.4881496,0.03364504],"study_design_scores_gemma":[0.0003398413,0.00002328787,0.007295904,0.00003628082,0.00002841088,0.000008421216,0.003498794,0.00004707495,0.1915247,0.1442529,0.6528277,0.0001166576],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.4012524,0.0003127599,0.0002659044,0.02831309,0.001368648,0.0005097799,0.00004447205,0.00005774049,0.5678751],"genre_scores_gemma":[0.9674962,0.00002976346,0.001386077,0.001360664,0.00006237678,0.00001844257,0.0000011414,0.000006318668,0.02963899],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5662438,"threshold_uncertainty_score":0.7293645,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1456944817584302,"score_gpt":0.3862504445530855,"score_spread":0.2405559627946553,"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."}}