{"id":"W2889053599","doi":"10.5555/3236187.3269462","title":"Efficient construction of approximate ad-hoc ML models through materialization and reuse","year":2018,"lang":"en","type":"article","venue":"Very Large Data Bases","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Online analytical processing; Reuse; Dimension (graph theory); Cluster analysis; Data warehouse; Data mining; Construct (python library); Variety (cybernetics); Mixture model; Data modeling; Machine learning; Artificial intelligence; Database; 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":[0.005564487,0.002129485,0.002567809,0.001993426,0.001317107,0.004627422,0.004590313,0.001905928,0.00334876],"category_scores_gemma":[0.02663322,0.001818752,0.003146503,0.003299475,0.002278772,0.008489148,0.006687189,0.003700565,0.001626874],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002661781,"about_ca_system_score_gemma":0.003800732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.009461256,"about_ca_topic_score_gemma":0.01184294,"domain_scores_codex":[0.9944278,0.001888928,0.0004198019,0.0009655513,0.001800718,0.0004972133],"domain_scores_gemma":[0.9821231,0.009989939,0.0009999617,0.005292078,0.001231597,0.0003634155],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001697883,0.0001949274,0.002363377,0.0001232735,0.0001107807,0.0002026261,0.0003685901,0.8129876,0.002688573,0.03874538,0.003974192,0.1380709],"study_design_scores_gemma":[0.00001250512,0.00001854849,0.00005762854,0.000004064723,0.00001035434,0.00002758663,0.00005189094,0.9792669,0.001092299,0.0186411,0.0008088931,0.000008232639],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01375913,0.0001238022,0.9825075,0.0002482537,0.0000126769,0.00008296494,0.0001310182,0.002357139,0.0007774842],"genre_scores_gemma":[0.2288459,0.0001985333,0.7668522,0.0002110931,0.00006104561,0.0002463768,0.001187121,0.0008229409,0.001574758],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.009461256,"threshold_uncertainty_score":0.02942812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04435581347020066,"score_gpt":0.2676946544767879,"score_spread":0.2233388410065872,"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."}}