{"id":"W2894980798","doi":"10.1007/s10618-018-0592-8","title":"Classification with label noise: a Markov chain sampling framework","year":2018,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":13,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University","funders":"Australian Research Council","keywords":"Markov chain; Computer science; Probabilistic logic; Correctness; Artificial intelligence; Noise (video); Markov chain Monte Carlo; Pattern recognition (psychology); Sampling (signal processing); Machine learning; Probability distribution; Variable-order Markov model; Hidden Markov model; Algorithm; Markov model; Bayesian probability; Mathematics; Statistics","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":[0.0006908232,0.0001772872,0.0001649451,0.0001178067,0.000358787,0.0006726836,0.001150664,0.00008838509,0.000005665167],"category_scores_gemma":[0.0003800834,0.0001436595,0.00001183737,0.0004526023,0.000164915,0.001665706,0.0007258132,0.0001856509,0.00005346184],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002022254,"about_ca_system_score_gemma":0.0001277631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002668343,"about_ca_topic_score_gemma":0.0000754251,"domain_scores_codex":[0.9984034,0.0001076902,0.0002120543,0.0008380105,0.0001691349,0.0002696565],"domain_scores_gemma":[0.9975516,0.0003080966,0.0001381769,0.001820747,0.00008496294,0.00009647956],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008546699,0.0002554094,0.02588989,0.0001006351,0.00005781489,0.000004055011,0.004877334,8.878618e-7,0.0009901616,0.07178422,0.007658148,0.888296],"study_design_scores_gemma":[0.001324303,0.0006088335,0.1589111,0.000942092,0.00008025403,0.0000731676,0.001823422,0.7161181,0.0001380723,0.001072691,0.1177576,0.001150333],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06412975,0.0005763149,0.92931,0.0008459876,0.0003342037,0.0001156974,0.0001276444,0.0001993171,0.004361038],"genre_scores_gemma":[0.7611699,0.00007204751,0.236362,0.0001517253,0.0004664535,0.00001529379,0.000831924,0.00001959235,0.0009110174],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8871456,"threshold_uncertainty_score":0.6486704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0757148656264769,"score_gpt":0.3395744944047306,"score_spread":0.2638596287782538,"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."}}