{"id":"W4407632769","doi":"10.1109/icmlcn64995.2025.11140226","title":"Doing More With Less: Towards More Data-Efficient Syndrome-Based Neural Decoders","year":2025,"lang":"en","type":"preprint","venue":"","topic":"Fractal and DNA sequence analysis","field":"Biochemistry, Genetics and Molecular Biology","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"CODE; Agence Nationale de la Recherche","keywords":"Computer science; Heuristics; Decoding methods; Machine learning; Training set; Artificial intelligence; Artificial neural network; Training (meteorology); Quality (philosophy); Neural decoding; Algorithm","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001661017,0.0004409351,0.0004376605,0.0001379796,0.0001020859,0.0001022425,0.001109763,0.0003773977,0.00004744744],"category_scores_gemma":[0.00003865617,0.0003325713,0.0002118204,0.000191148,0.000201059,0.000004019336,0.001540775,0.0003534355,0.000004273737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003728054,"about_ca_system_score_gemma":0.0006787214,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001183178,"about_ca_topic_score_gemma":0.0003367258,"domain_scores_codex":[0.9976715,0.00004812024,0.0003243042,0.001245449,0.0003343954,0.000376213],"domain_scores_gemma":[0.9975879,0.00001216646,0.0001623051,0.001958424,0.0001516518,0.0001275626],"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":[0.0003870084,0.0004560925,0.003395113,0.0008853701,0.001513654,0.0004162803,0.0001100835,0.9510571,0.009317685,0.00003221363,0.004488405,0.02794105],"study_design_scores_gemma":[0.002975113,0.0008070056,0.00424542,0.001156837,0.002410638,0.0001954467,0.003155249,0.8508031,0.09576058,0.00004973761,0.03416912,0.004271696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9254149,0.001288222,0.06577662,0.002416797,0.0002467909,0.000455803,0.0006633867,0.00007939127,0.003658057],"genre_scores_gemma":[0.9810523,0.00006910138,0.009022104,0.001656645,0.00007686623,0.00005047005,0.006479491,0.00002834314,0.001564674],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1002539,"threshold_uncertainty_score":0.9999126,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02406726154624671,"score_gpt":0.2926643497550825,"score_spread":0.2685970882088358,"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."}}