{"id":"W2792331414","doi":"10.1186/s12859-018-2391-z","title":"Valection: design optimization for validation and verification studies","year":2018,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Adversarial Robustness in Machine Learning","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Princess Margaret Cancer Centre; University Health Network; University of Toronto; Ontario Institute for Cancer Research","funders":"National Institute of General Medical Sciences; Natural Sciences and Engineering Research Council of Canada; Canada Foundation for Innovation; Prostate Cancer Canada; Government of Ontario; Canadian Institutes of Health Research; Genome Canada; National Cancer Institute; National Institutes of Health; Ontario Institute for Cancer Research; Terry Fox Research Institute; Movember Foundation","keywords":"Computer science; Software; Selection (genetic algorithm); Inference; Data mining; Machine learning; Artificial intelligence; Programming language","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0005161094,0.00008363675,0.00009028169,0.00008489872,0.000309616,0.0001277773,0.0001719225,0.00004761407,0.000002745168],"category_scores_gemma":[0.0004949022,0.00007784799,0.00001782882,0.0002269929,0.0000647652,0.000985507,0.00007667927,0.00004051116,0.000009928109],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004114242,"about_ca_system_score_gemma":0.00004180002,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":7.007475e-7,"about_ca_topic_score_gemma":4.997149e-7,"domain_scores_codex":[0.9993728,0.00004320659,0.0002300472,0.0001183786,0.0001196798,0.0001158746],"domain_scores_gemma":[0.9991265,0.000207173,0.0001702954,0.000209651,0.0002594092,0.00002700132],"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":[0.00002901787,0.00001515913,0.0002279155,0.000185397,0.00003104833,4.62706e-8,0.006214987,0.9341195,0.00002252104,0.02292283,0.00110796,0.03512363],"study_design_scores_gemma":[0.0002577206,0.0001214595,0.00007526656,0.00001465433,0.00001133775,0.000004343295,0.0002055982,0.9970192,0.0006479888,0.001220092,0.0003268068,0.00009549813],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000141903,0.00003657862,0.9986105,0.0001317533,0.000429067,0.0003231426,5.196327e-7,0.0001405023,0.0001860616],"genre_scores_gemma":[0.007240308,0.00002703438,0.9924403,0.00006667315,0.0001349501,0.0000270348,0.000006361918,0.000005549945,0.00005179568],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.06289975,"threshold_uncertainty_score":0.3174549,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09419023023291122,"score_gpt":0.3327364530797012,"score_spread":0.2385462228467899,"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."}}