{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02896227,0.001439573,0.005031454,0.003985937,0.002466375,0.00513718,0.00784435,0.00541053,0.005020238],"category_scores_gemma":[0.06281885,0.002310308,0.00358787,0.003514089,0.005642083,0.007998941,0.004813591,0.005509546,0.001145473],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003415514,"about_ca_system_score_gemma":0.003248833,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00917977,"about_ca_topic_score_gemma":0.008347616,"domain_scores_codex":[0.988277,0.006926228,0.0004267306,0.001909179,0.001814731,0.000646107],"domain_scores_gemma":[0.9125906,0.07676171,0.002204055,0.004733904,0.002601099,0.001108474],"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":[0.0006115454,0.0004234712,0.005263226,0.0002752563,0.0003784273,0.0003498978,0.0006337821,0.5302946,0.0009468098,0.3883322,0.004813729,0.06767718],"study_design_scores_gemma":[0.00003459049,0.00001952617,0.0001118394,0.00001706898,0.00002551796,0.00002311859,0.00001186187,0.9291798,0.0001343774,0.07015195,0.0002780841,0.00001220669],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01073152,0.0002918735,0.9872181,0.0006165838,0.00006886005,0.0001637442,0.0001299909,0.000236208,0.0005431006],"genre_scores_gemma":[0.5377534,0.001184787,0.4467075,0.0009876913,0.001057238,0.001650913,0.001933767,0.0004114807,0.008313198],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02896227,"threshold_uncertainty_score":0.153169,"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."}}