{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J2SJB5FD2URWXAD4TIVEJWOELZ","short_pith_number":"pith:J2SJB5FD","schema_version":"1.0","canonical_sha256":"4ea490f4a3d5236b807c9a2a44d9c45e54d659f6b05bb519c7f8acbbc42afbfc","source":{"kind":"arxiv","id":"2508.00387","version":3},"attestation_state":"computed","paper":{"title":"STF: Shallow-Level Temporal Feedback to Enhance Spiking Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"Changze Lv, Junfeng Tang, Yanchen Huang, Yaochu Jin, Yingchao Yu, Zeqi Zheng, Zhaofei Yu, Zizheng Zhu","submitted_at":"2025-08-01T07:30:59Z","abstract_excerpt":"Transformer-based Spiking Neural Networks (SNNs) suffer from a great performance gap compared to floating-point \\mbox{Artificial} Neural Networks (ANNs) due to the binary nature of spike trains. Recent efforts have introduced deep-level feedback loops to transmit high-level semantic information to narrow this gap. However, these designs often span \\mbox{multiple} deep layers, resulting in costly feature transformations, higher parameter overhead, increased energy consumption, and longer inference latency. To address this issue, we propose Shallow-level Temporal Feedback (STF), a lightweight pl"},"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":"2508.00387","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-08-01T07:30:59Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"14e2408ad981ed7e1cce85f43f1777a41b3ee3af14e0ea82636fbe8e6546ff10","abstract_canon_sha256":"2facb10a02cc25ba23420835b4a468eeda2dcfba45e3da133235de0e7461763e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:33.233269Z","signature_b64":"2ZLAAFyCi+32i4DG2B9+R6sfKnz45a4v6NwLFrZA3lrmau80iSV3fljXIx4SCID+KRCPheA5DM4ylPLVjjE3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ea490f4a3d5236b807c9a2a44d9c45e54d659f6b05bb519c7f8acbbc42afbfc","last_reissued_at":"2026-07-05T11:51:33.232745Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:33.232745Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"STF: Shallow-Level Temporal Feedback to Enhance Spiking Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.NE","authors_text":"Changze Lv, Junfeng Tang, Yanchen Huang, Yaochu Jin, Yingchao Yu, Zeqi Zheng, Zhaofei Yu, Zizheng Zhu","submitted_at":"2025-08-01T07:30:59Z","abstract_excerpt":"Transformer-based Spiking Neural Networks (SNNs) suffer from a great performance gap compared to floating-point \\mbox{Artificial} Neural Networks (ANNs) due to the binary nature of spike trains. Recent efforts have introduced deep-level feedback loops to transmit high-level semantic information to narrow this gap. However, these designs often span \\mbox{multiple} deep layers, resulting in costly feature transformations, higher parameter overhead, increased energy consumption, and longer inference latency. To address this issue, we propose Shallow-level Temporal Feedback (STF), a lightweight pl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00387","kind":"arxiv","version":3},"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/2508.00387/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":"2508.00387","created_at":"2026-07-05T11:51:33.232815+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.00387v3","created_at":"2026-07-05T11:51:33.232815+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00387","created_at":"2026-07-05T11:51:33.232815+00:00"},{"alias_kind":"pith_short_12","alias_value":"J2SJB5FD2URW","created_at":"2026-07-05T11:51:33.232815+00:00"},{"alias_kind":"pith_short_16","alias_value":"J2SJB5FD2URWXAD4","created_at":"2026-07-05T11:51:33.232815+00:00"},{"alias_kind":"pith_short_8","alias_value":"J2SJB5FD","created_at":"2026-07-05T11:51:33.232815+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00740","citing_title":"SpikeHash: Learning Binary Codes with Spiking Neural Networks for Cross-Modal Hashing Retrieval","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J2SJB5FD2URWXAD4TIVEJWOELZ","json":"https://pith.science/pith/J2SJB5FD2URWXAD4TIVEJWOELZ.json","graph_json":"https://pith.science/api/pith-number/J2SJB5FD2URWXAD4TIVEJWOELZ/graph.json","events_json":"https://pith.science/api/pith-number/J2SJB5FD2URWXAD4TIVEJWOELZ/events.json","paper":"https://pith.science/paper/J2SJB5FD"},"agent_actions":{"view_html":"https://pith.science/pith/J2SJB5FD2URWXAD4TIVEJWOELZ","download_json":"https://pith.science/pith/J2SJB5FD2URWXAD4TIVEJWOELZ.json","view_paper":"https://pith.science/paper/J2SJB5FD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.00387&json=true","fetch_graph":"https://pith.science/api/pith-number/J2SJB5FD2URWXAD4TIVEJWOELZ/graph.json","fetch_events":"https://pith.science/api/pith-number/J2SJB5FD2URWXAD4TIVEJWOELZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J2SJB5FD2URWXAD4TIVEJWOELZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J2SJB5FD2URWXAD4TIVEJWOELZ/action/storage_attestation","attest_author":"https://pith.science/pith/J2SJB5FD2URWXAD4TIVEJWOELZ/action/author_attestation","sign_citation":"https://pith.science/pith/J2SJB5FD2URWXAD4TIVEJWOELZ/action/citation_signature","submit_replication":"https://pith.science/pith/J2SJB5FD2URWXAD4TIVEJWOELZ/action/replication_record"}},"created_at":"2026-07-05T11:51:33.232815+00:00","updated_at":"2026-07-05T11:51:33.232815+00:00"}