{"id":"W4321448342","doi":"10.14778/3574245.3574273","title":"On Efficient Approximate Queries over Machine Learning Models","year":2022,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Agence Nationale de la Recherche","keywords":"Oracle; Computer science; Heuristic; Quality (philosophy); Random oracle; Machine learning; Artificial intelligence; Data mining; Theoretical computer science; Information retrieval; 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":[],"consensus_categories":[],"category_scores_codex":[0.01416676,0.003248347,0.005197742,0.003149838,0.001462558,0.006029329,0.005526994,0.004878509,0.00760768],"category_scores_gemma":[0.08743069,0.001377393,0.002079493,0.006457785,0.003443226,0.01389726,0.006789324,0.004908165,0.002594885],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002996698,"about_ca_system_score_gemma":0.003909574,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005233924,"about_ca_topic_score_gemma":0.006559593,"domain_scores_codex":[0.9835022,0.007767187,0.001323804,0.002508776,0.003851475,0.00104667],"domain_scores_gemma":[0.9192941,0.06585629,0.002200134,0.008974548,0.002729246,0.0009457336],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"not_applicable","study_design_scores_codex":[0.001876442,0.0007223448,0.005279224,0.0007802875,0.0002676119,0.0003497601,0.0007157454,0.5524603,0.002519952,0.1156137,0.02812665,0.291288],"study_design_scores_gemma":[0.00008557879,0.00008180733,0.0002087502,0.00002984082,0.00002622841,0.0001066292,0.0001051209,0.8998637,0.0008774767,0.09719487,0.00140209,0.00001778478],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02927036,0.00231432,0.9576523,0.002556995,0.0001131805,0.0002383558,0.0008361059,0.003996655,0.003021801],"genre_scores_gemma":[0.424165,0.001155703,0.5612234,0.001980552,0.0007558248,0.0006720955,0.004439263,0.0009271111,0.004681053],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01416676,"threshold_uncertainty_score":0.07492185,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01161523234869004,"score_gpt":0.2104266141063533,"score_spread":0.1988113817576632,"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."}}