{"id":"W4406094149","doi":"10.1109/tcsi.2024.3524336","title":"Max-Pooling PD: A Machine Learning-Based Timing Recovery Method","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Circuits and Systems I Regular Papers","topic":"Semiconductor materials and devices","field":"Engineering","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Huawei Technologies (Canada); University of Toronto","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Pooling; Computer science; Robustness (evolution); Detector; Convolutional neural network; Baud; Artificial intelligence; Boosting (machine learning); Artificial neural network; Machine learning; Algorithm; Telecommunications","routes":{"ca_aff":true,"ca_fund":true,"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":[0.000933413,0.0009877048,0.0006157964,0.0006685755,0.00030191,0.0007240119,0.001733738,0.0005846571,0.003539378],"category_scores_gemma":[0.001691476,0.0003601618,0.0005445541,0.0006415258,0.0004530192,0.001355951,0.0009941377,0.0009559836,0.001448693],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005146894,"about_ca_system_score_gemma":0.00097016,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001311611,"about_ca_topic_score_gemma":0.001800925,"domain_scores_codex":[0.9995607,0.00006725659,0.0000249545,0.0001132458,0.0001828199,0.0000511916],"domain_scores_gemma":[0.9995832,0.0001214028,0.0000557634,0.0001111475,0.00010505,0.00002335205],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0003012544,0.00008452006,0.0006105843,0.0001393912,0.00006886658,0.0001201554,0.00006690016,0.04831792,0.0671096,0.008888898,0.005063129,0.8692289],"study_design_scores_gemma":[0.00003376877,0.0002177901,0.0006404078,0.0000174009,0.00004020361,0.0003076792,0.00002101441,0.8615596,0.1171451,0.006900023,0.01308358,0.00003348023],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.005382236,0.0002077893,0.9915019,0.00006755583,0.00003107018,0.00003474562,0.00006802123,0.001727992,0.0009787381],"genre_scores_gemma":[0.2177644,0.0003759172,0.7739859,0.0002322846,0.0001004915,0.000125843,0.0005571278,0.0003672225,0.006490854],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.003539378,"threshold_uncertainty_score":0.0118404,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01604958391782615,"score_gpt":0.2343685345413336,"score_spread":0.2183189506235075,"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."}}