{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.003440811,0.00180489,0.001142079,0.002454439,0.0009337822,0.004738721,0.004336457,0.001904731,0.1738705],"category_scores_gemma":[0.01493629,0.001345709,0.001503762,0.00225144,0.0008296848,0.009637265,0.007541079,0.002998531,0.1854739],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00096914,"about_ca_system_score_gemma":0.001914199,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0020466,"about_ca_topic_score_gemma":0.003287041,"domain_scores_codex":[0.9968394,0.0004563312,0.0002820342,0.0009313436,0.001231054,0.0002598669],"domain_scores_gemma":[0.993372,0.001247558,0.0002680411,0.003694175,0.001032267,0.0003860666],"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":[0.0004884751,0.0001651608,0.001516293,0.0007956821,0.00009612227,0.00023642,0.000374478,0.001932755,0.00578054,0.03313354,0.6703464,0.2851342],"study_design_scores_gemma":[0.0000941572,0.00008752719,0.0009743797,0.0001257642,0.00003176534,0.0003352855,0.00009984496,0.01480494,0.009047331,0.03030812,0.944025,0.00006595549],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"software","genre_gemma":"other","genre_scores_codex":[0.004436628,0.001176781,0.3334717,0.002318927,0.001029293,0.0007672585,0.05970363,0.4829467,0.1141491],"genre_scores_gemma":[0.05525114,0.001793576,0.3960297,0.003434078,0.000576931,0.001296132,0.2602469,0.07820662,0.2031649],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.8261294,"threshold_uncertainty_score":0,"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."}}