{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006050371,0.0001687919,0.0001806518,0.0001065792,0.0005890729,0.00009077561,0.001176514,0.0000181229,0.00004565838],"category_scores_gemma":[0.00005524087,0.0001192863,0.000120315,0.0004065546,0.00004167911,0.0001181296,0.001475232,0.0004972352,0.000003351928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009988542,"about_ca_system_score_gemma":0.00002136491,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009070305,"about_ca_topic_score_gemma":2.501114e-7,"domain_scores_codex":[0.9983054,0.00003059281,0.0002310215,0.0003690586,0.0007713962,0.0002925151],"domain_scores_gemma":[0.9993998,0.0000476047,0.0002580055,0.0001891424,0.00005285247,0.0000526291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004129985,0.0003101949,0.0007936276,0.00006430878,0.00003727841,0.000001372066,0.003496643,0.4570872,0.003340173,0.5279143,0.0007094203,0.006204132],"study_design_scores_gemma":[0.0004104302,0.000250817,0.0001357919,0.00002551737,0.000007677729,0.0000145184,0.0001231592,0.9787383,0.005531528,0.01189161,0.002710026,0.0001606033],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9128671,0.0006099934,0.03276918,0.006280823,0.00158292,0.001284984,0.00002242533,0.0008368159,0.04374577],"genre_scores_gemma":[0.9948067,0.000006707136,0.003475812,0.0002441752,0.00002872093,0.00008645527,9.852125e-7,0.00001562511,0.001334802],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5216511,"threshold_uncertainty_score":0.4864355,"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."}}