{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002797947,0.00009798915,0.0001218214,0.00006537694,0.0001067553,0.0001785723,0.001038089,0.00002646972,0.00002721712],"category_scores_gemma":[0.00004554371,0.00008822668,0.00001032386,0.0002315282,0.0001070423,0.001705019,0.002208212,0.00002289819,0.00001240146],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006925625,"about_ca_system_score_gemma":0.00001542013,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001708505,"about_ca_topic_score_gemma":0.000003632128,"domain_scores_codex":[0.9990007,0.00004123656,0.0001925751,0.0004124481,0.0001831187,0.0001699489],"domain_scores_gemma":[0.9981805,0.00001868836,0.0001072831,0.001609816,0.00005686275,0.00002686286],"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":[0.0002173772,0.00110049,0.000525477,0.000838341,0.0002123488,0.00004077152,0.002870074,0.0005514217,0.004961374,0.8115037,0.1088829,0.06829573],"study_design_scores_gemma":[0.0004481464,0.00007473589,0.00006025383,0.00005447022,0.00002141638,0.000007159435,0.0000712256,0.9639546,0.003698264,0.003755713,0.02769329,0.0001607811],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.06484899,0.0001753722,0.9318442,0.0001152202,0.0006737309,0.0001664619,0.001794881,0.0001158671,0.0002652736],"genre_scores_gemma":[0.3167988,0.000747927,0.677894,0.0003709241,0.0002378528,0.00001203448,0.003831743,0.00002557194,0.00008111493],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9634031,"threshold_uncertainty_score":0.359778,"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."}}