{"id":"W2889372359","doi":"10.1109/spawc.2018.8445986","title":"Neural Successive Cancellation Decoding of Polar Codes","year":2018,"lang":"en","type":"article","venue":"","topic":"Error Correcting Code Techniques","field":"Computer Science","cited_by":49,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Decoding methods; Computer science; Soft-decision decoder; Sequential decoding; List decoding; Algorithm; Artificial neural network; Polar; Berlekamp–Welch algorithm; Latency (audio); Concatenated error correction code; Telecommunications; Artificial intelligence; Block code","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":[0.0001595675,0.00006164949,0.0000865875,0.00007814536,0.00006728016,0.00003515683,0.0004477674,0.00002960598,0.0000225786],"category_scores_gemma":[0.00007422912,0.00005510026,0.00002538307,0.0002531121,0.00004967471,0.0003176579,0.0001356117,0.00004876035,0.000007918554],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002621884,"about_ca_system_score_gemma":0.00002934741,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0005598865,"about_ca_topic_score_gemma":0.000442072,"domain_scores_codex":[0.9993985,0.00003162366,0.0001424581,0.0001715748,0.0001287727,0.0001270553],"domain_scores_gemma":[0.9993265,0.00009537725,0.0001023747,0.0002800074,0.0001682699,0.00002743753],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003090474,0.0001138689,0.194205,0.00007325606,0.00004333925,0.00001397858,0.008330999,0.0001438978,0.2554243,0.2359868,0.009104376,0.2965293],"study_design_scores_gemma":[0.00008249314,0.0001682715,0.003836292,0.000026047,0.000002613438,0.000007261028,0.00003734013,0.4339104,0.5584852,0.003029501,0.0002668731,0.0001476496],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1955632,0.00002456899,0.7927821,0.0002264215,0.0002864218,0.00006315901,4.46761e-7,0.0003660788,0.01068753],"genre_scores_gemma":[0.8996243,0.000001439307,0.1000776,0.00009871458,0.00005109903,0.000001641708,2.814774e-7,0.000003731737,0.0001411352],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7040611,"threshold_uncertainty_score":0.2246924,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01932340207593321,"score_gpt":0.2929403306562726,"score_spread":0.2736169285803394,"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."}}