{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FBAFIH72YUBMHAZHZW6EMGOBGI","short_pith_number":"pith:FBAFIH72","schema_version":"1.0","canonical_sha256":"2840541ffac502c38327cdbc4619c1321f22b1fd76c27bbfd51c7f23a91a8a79","source":{"kind":"arxiv","id":"2301.11929","version":1},"attestation_state":"computed","paper":{"title":"Training Full Spike Neural Networks via Auxiliary Accumulation Pathway","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Guangyao Chen, Guoqi Li, Peixi Peng, Yonghong Tian","submitted_at":"2023-01-27T02:33:40Z","abstract_excerpt":"Due to the binary spike signals making converting the traditional high-power multiply-accumulation (MAC) into a low-power accumulation (AC) available, the brain-inspired Spiking Neural Networks (SNNs) are gaining more and more attention. However, the binary spike propagation of the Full-Spike Neural Networks (FSNN) with limited time steps is prone to significant information loss. To improve performance, several state-of-the-art SNN models trained from scratch inevitably bring many non-spike operations. The non-spike operations cause additional computational consumption and may not be deployed "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2301.11929","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2023-01-27T02:33:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"896ade179e7131aa0a2c72d020866a61bd4aa0cdcaf7a6f6bc48619d5526be21","abstract_canon_sha256":"bff77815c7e7e658ca0f69028663d22429c1a0fae18dc95db0f2cb58f6bb3f8a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:33.593884Z","signature_b64":"t0yhl4IbzMZyX5GrFx0ks17ptrLn18vtWQHlp65v64MQlLXH+Do1Ysg/16dchZi+aR3uiO0QRZhfuEzZB+85CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2840541ffac502c38327cdbc4619c1321f22b1fd76c27bbfd51c7f23a91a8a79","last_reissued_at":"2026-07-05T05:36:33.593379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:33.593379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training Full Spike Neural Networks via Auxiliary Accumulation Pathway","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Guangyao Chen, Guoqi Li, Peixi Peng, Yonghong Tian","submitted_at":"2023-01-27T02:33:40Z","abstract_excerpt":"Due to the binary spike signals making converting the traditional high-power multiply-accumulation (MAC) into a low-power accumulation (AC) available, the brain-inspired Spiking Neural Networks (SNNs) are gaining more and more attention. However, the binary spike propagation of the Full-Spike Neural Networks (FSNN) with limited time steps is prone to significant information loss. To improve performance, several state-of-the-art SNN models trained from scratch inevitably bring many non-spike operations. The non-spike operations cause additional computational consumption and may not be deployed "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.11929","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2301.11929/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2301.11929","created_at":"2026-07-05T05:36:33.593440+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.11929v1","created_at":"2026-07-05T05:36:33.593440+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.11929","created_at":"2026-07-05T05:36:33.593440+00:00"},{"alias_kind":"pith_short_12","alias_value":"FBAFIH72YUBM","created_at":"2026-07-05T05:36:33.593440+00:00"},{"alias_kind":"pith_short_16","alias_value":"FBAFIH72YUBMHAZH","created_at":"2026-07-05T05:36:33.593440+00:00"},{"alias_kind":"pith_short_8","alias_value":"FBAFIH72","created_at":"2026-07-05T05:36:33.593440+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12033","citing_title":"SpikeTAD: Spiking Neural Networks for End-to-End Temporal Action Detection","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2403.16552","citing_title":"QKFormer: Hierarchical Spiking Transformer using Q-K Attention","ref_index":48,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FBAFIH72YUBMHAZHZW6EMGOBGI","json":"https://pith.science/pith/FBAFIH72YUBMHAZHZW6EMGOBGI.json","graph_json":"https://pith.science/api/pith-number/FBAFIH72YUBMHAZHZW6EMGOBGI/graph.json","events_json":"https://pith.science/api/pith-number/FBAFIH72YUBMHAZHZW6EMGOBGI/events.json","paper":"https://pith.science/paper/FBAFIH72"},"agent_actions":{"view_html":"https://pith.science/pith/FBAFIH72YUBMHAZHZW6EMGOBGI","download_json":"https://pith.science/pith/FBAFIH72YUBMHAZHZW6EMGOBGI.json","view_paper":"https://pith.science/paper/FBAFIH72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.11929&json=true","fetch_graph":"https://pith.science/api/pith-number/FBAFIH72YUBMHAZHZW6EMGOBGI/graph.json","fetch_events":"https://pith.science/api/pith-number/FBAFIH72YUBMHAZHZW6EMGOBGI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FBAFIH72YUBMHAZHZW6EMGOBGI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FBAFIH72YUBMHAZHZW6EMGOBGI/action/storage_attestation","attest_author":"https://pith.science/pith/FBAFIH72YUBMHAZHZW6EMGOBGI/action/author_attestation","sign_citation":"https://pith.science/pith/FBAFIH72YUBMHAZHZW6EMGOBGI/action/citation_signature","submit_replication":"https://pith.science/pith/FBAFIH72YUBMHAZHZW6EMGOBGI/action/replication_record"}},"created_at":"2026-07-05T05:36:33.593440+00:00","updated_at":"2026-07-05T05:36:33.593440+00:00"}