{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.000156264,0.00008371427,0.00006165787,0.00004654433,0.00005822347,0.00003339046,0.0002180556,0.00009932647,0.000007186789],"category_scores_gemma":[0.00003887915,0.00008093974,0.00001871532,0.00009200905,0.00001807172,0.00001427428,0.00009768467,0.00005802674,0.00000895846],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000159474,"about_ca_system_score_gemma":0.00003655,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002820302,"about_ca_topic_score_gemma":0.00002921928,"domain_scores_codex":[0.9993296,0.00001599026,0.0002677272,0.0001448106,0.00009885131,0.0001430566],"domain_scores_gemma":[0.9994653,0.000003053525,0.0001089851,0.0003678911,0.00003039689,0.00002434292],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0000146375,0.00002674713,0.0005480134,0.00002030572,0.000003869591,2.017208e-7,0.00005176547,0.0003485792,0.9720042,0.00001482644,0.02033774,0.006629132],"study_design_scores_gemma":[0.001640721,0.0001021211,0.002049308,0.00005798754,0.00002275792,0.00001819545,0.001150221,0.1290267,0.702279,0.0001563366,0.1629203,0.0005764313],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.909007,0.001186696,0.08340363,0.0003411012,0.0004196977,0.0003006117,0.0001009914,0.00004031847,0.005200019],"genre_scores_gemma":[0.987597,0.00006738226,0.009959436,0.0001523121,0.0001251416,0.000006552041,0.001534854,0.00001083411,0.0005464263],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2697252,"threshold_uncertainty_score":0.3300627,"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."}}