{"id":"W6910386758","doi":"10.48448/bws7-dy90","title":"Toward Robustness in Multi-Label Classification: A Data Augmentation Strategy against Imbalance and Noise | VIDEO","year":2024,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kootenay Association for Science & Technology","funders":"","keywords":"Robustness (evolution); Noisy data; Noise (video); Training set; Benchmark (surveying); Code (set theory); 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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001614558,0.0005094541,0.0004497864,0.0014725,0.0001115916,0.0006521104,0.001956251,0.0002746091,0.0001583849],"category_scores_gemma":[0.0001993984,0.0004875814,0.00001802647,0.002602719,0.001601801,0.0009920399,0.0007738121,0.0005432962,0.001478746],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000484225,"about_ca_system_score_gemma":0.001147065,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004272368,"about_ca_topic_score_gemma":0.004559652,"domain_scores_codex":[0.9954765,0.00009948415,0.0006008274,0.002145692,0.001022414,0.0006550777],"domain_scores_gemma":[0.9975613,0.00004718548,0.0004123336,0.001604214,0.0001427241,0.0002322509],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001195764,0.002009885,0.002272263,0.002064738,0.0001885448,0.0004042728,0.001380846,0.002819098,0.0619555,0.007854433,0.7607524,0.1581784],"study_design_scores_gemma":[0.001491188,0.00004330494,0.00114368,0.0007435489,0.00005764501,0.00001891165,0.0008199454,0.9825941,0.00004905649,0.0001305528,0.01219138,0.000716721],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"other","genre_gemma":"other","genre_scores_codex":[0.01857164,0.05137434,0.2028082,0.008329689,0.01299952,0.02039481,0.04357424,0.009939065,0.6320085],"genre_scores_gemma":[0.2742784,0.002891596,0.3138946,0.000844339,0.001532699,0.000478791,0.01203637,0.004101143,0.389942],"genre_candidate":"other","genre_consensus":"other","teacher_disagreement_score":0.979775,"threshold_uncertainty_score":0.9997576,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2115885690971196,"score_gpt":0.3919645326143992,"score_spread":0.1803759635172796,"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."}}