{"id":"W4244320771","doi":"10.1137/1.9781611975482.61","title":"XOR Codes and Sparse Learning Parity with Noise","year":2019,"lang":"en","type":"book-chapter","venue":"Society for Industrial and Applied Mathematics eBooks","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"Chinese University of Hong Kong; National Science Foundation","keywords":"Mathematics; Random variable; Combinatorics; Modulo; Decoding methods; Discrete mathematics; Parity (physics); Algorithm; Statistics; Physics; Quantum mechanics","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":[0.001401795,0.0008033487,0.001282757,0.0004931511,0.0007272169,0.001726309,0.001591379,0.001451356,0.00620644],"category_scores_gemma":[0.0148542,0.0004967788,0.001097554,0.001008567,0.001650829,0.003668059,0.002663412,0.00311652,0.0008454479],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001806504,"about_ca_system_score_gemma":0.00174404,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002160239,"about_ca_topic_score_gemma":0.003044907,"domain_scores_codex":[0.9978849,0.0006596587,0.0001067237,0.0004645712,0.0005311568,0.0003529714],"domain_scores_gemma":[0.9915394,0.006401532,0.0005368109,0.0008928403,0.0004218581,0.0002074184],"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":[0.001133911,0.0002781347,0.004557582,0.0004083855,0.0001503273,0.0005323003,0.0005054972,0.5041249,0.005157478,0.3677273,0.01314035,0.1022837],"study_design_scores_gemma":[0.0001020752,0.00005880353,0.0002803101,0.00002090706,0.00001978676,0.00008741635,0.00005901595,0.6829956,0.002406925,0.3126738,0.001274351,0.00002101553],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.263104,0.0004894587,0.7134509,0.004745784,0.0001626914,0.0002102716,0.001305094,0.001704083,0.01482777],"genre_scores_gemma":[0.8399129,0.0001837103,0.1475748,0.0008096928,0.0001755295,0.0002820395,0.001184749,0.000323959,0.009552605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00620644,"threshold_uncertainty_score":0.02076268,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03669504724905,"score_gpt":0.2299703520996574,"score_spread":0.1932753048506074,"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."}}