{"id":"W7134163353","doi":"10.1109/bigdata66926.2025.11400965","title":"Enhancing Interpretability in Self-Training with Tsetlin Machines for Mitigating Noisy Pseudo-Labels","year":2025,"lang":"","type":"article","venue":"","topic":"Machine Learning and Data Classification","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Interpretability; Noisy data; Feature (linguistics); Noise (video); Pattern recognition (psychology)","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":[0.00419916,0.001267707,0.00106513,0.000938957,0.0008099118,0.001891864,0.001374443,0.002247884,0.003052678],"category_scores_gemma":[0.02923165,0.0004418805,0.0006533624,0.0007536723,0.001218358,0.003113935,0.002414897,0.003268992,0.001083932],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005976565,"about_ca_system_score_gemma":0.0008410721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001160548,"about_ca_topic_score_gemma":0.002115398,"domain_scores_codex":[0.9969502,0.001440405,0.0001960429,0.000618594,0.0006174011,0.0001772934],"domain_scores_gemma":[0.9844704,0.0106194,0.0007054056,0.001853275,0.002116432,0.0002351266],"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":[0.001227426,0.0004104633,0.007113867,0.0003766515,0.000135983,0.0004532906,0.001098874,0.2062692,0.03783357,0.0182929,0.008098071,0.7186897],"study_design_scores_gemma":[0.00001714369,0.0001155995,0.0005782182,0.00002940464,0.00002205265,0.00008915026,0.00006627791,0.9733056,0.01391849,0.0106817,0.001164156,0.00001214005],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09919089,0.0004386742,0.8941282,0.0006350235,0.0001924655,0.00008189642,0.00012283,0.002907236,0.0023028],"genre_scores_gemma":[0.7289618,0.0001515362,0.2654295,0.0004344769,0.0001426943,0.0001339581,0.0006080334,0.0006946371,0.003443328],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00419916,"threshold_uncertainty_score":0.02220756,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0142521620139618,"score_gpt":0.2914397057257438,"score_spread":0.277187543711782,"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."}}