{"id":"W4410614342","doi":"10.1109/tvlsi.2025.3566949","title":"<i>S</i> <sup>3</sup>A-NPU: A High-Performance Hardware Accelerator for Spiking Self-Supervised Learning With Dynamic Adaptive Memory Optimization","year":2025,"lang":"en","type":"article","venue":"IEEE Transactions on Very Large Scale Integration (VLSI) Systems","topic":"Advanced Memory and Neural Computing","field":"Engineering","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Institute for Information and Communications Technology Promotion; National Research Foundation of Korea","keywords":"Computer science; Computer hardware; Computer architecture; Artificial intelligence","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002326655,0.0003599311,0.0002816404,0.0001908821,0.000237266,0.0005723919,0.001229373,0.0004885009,0.01525111],"category_scores_gemma":[0.0005653815,0.000151581,0.0002223224,0.0003256696,0.0002048748,0.0006698013,0.0004375344,0.0006336548,0.003810707],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004711708,"about_ca_system_score_gemma":0.0006671145,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0007840441,"about_ca_topic_score_gemma":0.001384919,"domain_scores_codex":[0.999894,0.00001757809,0.000007225489,0.00001549492,0.00005021931,0.00001542957],"domain_scores_gemma":[0.9998349,0.00003379916,0.00001757395,0.00002892371,0.00006075795,0.00002402094],"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":[0.001501903,0.000410605,0.004794141,0.0006472939,0.0002134997,0.0009394737,0.0002318669,0.1937566,0.1587577,0.05997427,0.2056503,0.3731223],"study_design_scores_gemma":[0.00007232144,0.0003300189,0.0006553218,0.00001968222,0.00002110195,0.0001514351,0.00002165755,0.8718027,0.06412859,0.004557839,0.05821385,0.00002546609],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09586458,0.0007436355,0.8181923,0.001713637,0.000810632,0.0002475242,0.002015275,0.02620416,0.05420828],"genre_scores_gemma":[0.5906972,0.0003388895,0.3771417,0.0008620733,0.0001037903,0.0004539918,0.002973916,0.001192759,0.02623569],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01525111,"threshold_uncertainty_score":0.05102003,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.007721111867427429,"score_gpt":0.2098036926989963,"score_spread":0.2020825808315689,"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."}}