{"id":"W3011592252","doi":"10.14778/3236187.3236199","title":"Efficient construction of approximate ad-hoc ML models through materialization and reuse","year":2018,"lang":"en","type":"article","venue":"Proceedings of the VLDB Endowment","topic":"Data Management and Algorithms","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Online analytical processing; Reuse; Dimension (graph theory); Cluster analysis; Variety (cybernetics); Data warehouse; Data mining; Construct (python library); Mixture model; Machine learning; Artificial intelligence; Mathematics; 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":[0.0002316687,0.00009892955,0.0001305484,0.0000532114,0.00008775175,0.00009616457,0.0007454169,0.00002467096,0.000004329851],"category_scores_gemma":[0.00002152758,0.00007025754,0.0000279853,0.0002512145,0.0001736484,0.0004486792,0.001026945,0.00002742059,0.000001443698],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001998862,"about_ca_system_score_gemma":0.000007353367,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001066903,"about_ca_topic_score_gemma":2.05003e-7,"domain_scores_codex":[0.9990968,0.000005253396,0.0002421501,0.0002453575,0.0002692093,0.0001412084],"domain_scores_gemma":[0.999293,0.000005437957,0.0002692447,0.0002477779,0.0001633846,0.00002115575],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00006234717,0.0001949797,0.0002098889,0.0004396009,0.00007376381,1.972354e-7,0.006750353,0.0001753305,0.06799204,0.90664,0.001709526,0.01575201],"study_design_scores_gemma":[0.001051344,0.0002910898,0.0002295471,0.0002400194,0.00005543244,0.00001337667,0.0005180683,0.3404569,0.5452298,0.109847,0.001810669,0.000256773],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8782429,0.0001761049,0.1115356,0.001254818,0.001144053,0.0009492957,0.00002052307,0.0001404192,0.006536236],"genre_scores_gemma":[0.857347,0.0001203077,0.1423334,0.0000538596,0.0000464698,0.00001767999,0.000001489288,0.000008131737,0.00007159434],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.796793,"threshold_uncertainty_score":0.2865019,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0167162247919843,"score_gpt":0.2200566624691846,"score_spread":0.2033404376772003,"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."}}