{"id":"W2170645625","doi":"10.1093/bioinformatics/btl346","title":"Detecting potential labeling errors in microarrays by data perturbation","year":2006,"lang":"en","type":"article","venue":"Bioinformatics","topic":"Gene expression and cancer classification","field":"Biochemistry, Genetics and Molecular Biology","cited_by":80,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Classifier (UML); Computation; Data mining; Support vector machine; Pattern recognition (psychology); Artificial intelligence; Algorithm; Machine learning","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01097945,0.0009311581,0.0009191743,0.001510775,0.0009971538,0.001035524,0.001130394,0.001354655,0.0004188793],"category_scores_gemma":[0.05385575,0.0004636883,0.0006185557,0.001531734,0.002527392,0.00149404,0.001256632,0.001199119,0.000336568],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001288326,"about_ca_system_score_gemma":0.0009019868,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0009477576,"about_ca_topic_score_gemma":0.0006811955,"domain_scores_codex":[0.9905103,0.004445053,0.000576804,0.001896991,0.002357737,0.0002130653],"domain_scores_gemma":[0.943909,0.04084117,0.006230607,0.005084523,0.003503939,0.0004307324],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.002403013,0.0004686906,0.07446575,0.0007537176,0.0003705464,0.0009887476,0.002086767,0.3332418,0.1940328,0.0148603,0.003233848,0.373094],"study_design_scores_gemma":[0.00004662457,0.0003333412,0.01574246,0.00004807111,0.00007138435,0.0009345288,0.0001790443,0.7912961,0.1640344,0.02556238,0.001667956,0.00008377828],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1187653,0.0002976557,0.8785138,0.0004304701,0.00006507945,0.0001298124,0.00008604041,0.001449455,0.0002624959],"genre_scores_gemma":[0.6009535,0.000135796,0.3971134,0.000333332,0.00008215704,0.0002105406,0.0004162038,0.000207489,0.0005474507],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9890205,"threshold_uncertainty_score":0.05806559,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01443092758167436,"score_gpt":0.2473545288707236,"score_spread":0.2329236012890492,"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."}}