{"id":"W160007757","doi":"","title":"Learning in the Limit with Adversarial Disturbances.","year":2008,"lang":"en","type":"article","venue":"","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Disturbance (geology); Generalization; Limit (mathematics); Computer science; Noise (video); Decision maker; Artificial intelligence; Position (finance); Data point; Process (computing); Binary number; Mathematical optimization; Mathematics","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":[0.0001963177,0.00006708474,0.00006859624,0.00003236634,0.0001648702,0.00004895332,0.0005144043,0.00001718859,0.00001051509],"category_scores_gemma":[0.00002714014,0.00003471528,0.00001952978,0.0003008645,0.00003698577,0.0001608045,0.00005237411,0.0002786198,0.00003157111],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007621361,"about_ca_system_score_gemma":0.00003153105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001897577,"about_ca_topic_score_gemma":0.00002934085,"domain_scores_codex":[0.9993004,0.00008888759,0.00007223062,0.0001761466,0.0002070428,0.0001553179],"domain_scores_gemma":[0.9996483,0.00009121886,0.00002749327,0.0001996011,0.00001200808,0.00002136191],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00006387309,0.0003901726,0.4408245,0.00001870115,0.00003914456,0.001178692,0.04556476,0.05060541,0.00003420029,0.07984793,0.008990409,0.3724422],"study_design_scores_gemma":[0.001876461,0.0007713323,0.3804365,0.00002771983,0.000004557461,0.0004405738,0.0005206757,0.4895086,0.00006392246,0.0004788672,0.1253929,0.0004779212],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2187159,0.0001070523,0.6201568,0.008602456,0.0003449014,0.0002085591,1.541285e-7,0.0005005636,0.1513636],"genre_scores_gemma":[0.9847125,0.00001021425,0.01207016,0.0003897227,0.00009499853,0.000005128983,6.002493e-7,0.000002993654,0.002713637],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7659966,"threshold_uncertainty_score":0.1415648,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.009667311698577555,"score_gpt":0.2046669185773232,"score_spread":0.1949996068787456,"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."}}