{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JENYDP7ZEH4KBFHVNOC637DESU","short_pith_number":"pith:JENYDP7Z","schema_version":"1.0","canonical_sha256":"491b81bff921f8a094f56b85edfc649535095392fc8dc52d1bf022812d84331f","source":{"kind":"arxiv","id":"2411.16061","version":1},"attestation_state":"computed","paper":{"title":"Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Xu, Guoqi Li, Jiakui Hu, Jianxing Liao, Keyu Tian, Luziwei Leng, Man Yao, Tianxiang Hu, Xuerui Qiu, Yuhong Chou","submitted_at":"2024-11-25T03:05:41Z","abstract_excerpt":"The ambition of brain-inspired Spiking Neural Networks (SNNs) is to become a low-power alternative to traditional Artificial Neural Networks (ANNs). This work addresses two major challenges in realizing this vision: the performance gap between SNNs and ANNs, and the high training costs of SNNs. We identify intrinsic flaws in spiking neurons caused by binary firing mechanisms and propose a Spike Firing Approximation (SFA) method using integer training and spike-driven inference. This optimizes the spike firing pattern of spiking neurons, enhancing efficient training, reducing power consumption,"},"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":"2411.16061","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T03:05:41Z","cross_cats_sorted":[],"title_canon_sha256":"e5af34ffa17ce20c01d2879941b28622d009a3298c402bbf010aeccd2241243e","abstract_canon_sha256":"afc71afab1c09bb745753cff6bf3186365e75457fe3d95edcf32adf0a9466c89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:25.508112Z","signature_b64":"MvP7gIJe8A9I3YGcfcnFZAls3TfADZ2tlQOxwKVgY4mFM5yBMRisa4KV259ecNxHhQ3L9lPf1orOB/BCM2L1AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"491b81bff921f8a094f56b85edfc649535095392fc8dc52d1bf022812d84331f","last_reissued_at":"2026-07-05T10:02:25.507634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:25.507634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Spike-driven Transformer with Efficient Spike Firing Approximation Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bo Xu, Guoqi Li, Jiakui Hu, Jianxing Liao, Keyu Tian, Luziwei Leng, Man Yao, Tianxiang Hu, Xuerui Qiu, Yuhong Chou","submitted_at":"2024-11-25T03:05:41Z","abstract_excerpt":"The ambition of brain-inspired Spiking Neural Networks (SNNs) is to become a low-power alternative to traditional Artificial Neural Networks (ANNs). This work addresses two major challenges in realizing this vision: the performance gap between SNNs and ANNs, and the high training costs of SNNs. We identify intrinsic flaws in spiking neurons caused by binary firing mechanisms and propose a Spike Firing Approximation (SFA) method using integer training and spike-driven inference. This optimizes the spike firing pattern of spiking neurons, enhancing efficient training, reducing power consumption,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16061","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/2411.16061/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":"2411.16061","created_at":"2026-07-05T10:02:25.507692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.16061v1","created_at":"2026-07-05T10:02:25.507692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16061","created_at":"2026-07-05T10:02:25.507692+00:00"},{"alias_kind":"pith_short_12","alias_value":"JENYDP7ZEH4K","created_at":"2026-07-05T10:02:25.507692+00:00"},{"alias_kind":"pith_short_16","alias_value":"JENYDP7ZEH4KBFHV","created_at":"2026-07-05T10:02:25.507692+00:00"},{"alias_kind":"pith_short_8","alias_value":"JENYDP7Z","created_at":"2026-07-05T10:02:25.507692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13492","citing_title":"Quantized Spike-driven Transformer","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JENYDP7ZEH4KBFHVNOC637DESU","json":"https://pith.science/pith/JENYDP7ZEH4KBFHVNOC637DESU.json","graph_json":"https://pith.science/api/pith-number/JENYDP7ZEH4KBFHVNOC637DESU/graph.json","events_json":"https://pith.science/api/pith-number/JENYDP7ZEH4KBFHVNOC637DESU/events.json","paper":"https://pith.science/paper/JENYDP7Z"},"agent_actions":{"view_html":"https://pith.science/pith/JENYDP7ZEH4KBFHVNOC637DESU","download_json":"https://pith.science/pith/JENYDP7ZEH4KBFHVNOC637DESU.json","view_paper":"https://pith.science/paper/JENYDP7Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.16061&json=true","fetch_graph":"https://pith.science/api/pith-number/JENYDP7ZEH4KBFHVNOC637DESU/graph.json","fetch_events":"https://pith.science/api/pith-number/JENYDP7ZEH4KBFHVNOC637DESU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JENYDP7ZEH4KBFHVNOC637DESU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JENYDP7ZEH4KBFHVNOC637DESU/action/storage_attestation","attest_author":"https://pith.science/pith/JENYDP7ZEH4KBFHVNOC637DESU/action/author_attestation","sign_citation":"https://pith.science/pith/JENYDP7ZEH4KBFHVNOC637DESU/action/citation_signature","submit_replication":"https://pith.science/pith/JENYDP7ZEH4KBFHVNOC637DESU/action/replication_record"}},"created_at":"2026-07-05T10:02:25.507692+00:00","updated_at":"2026-07-05T10:02:25.507692+00:00"}