{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CXSZUQHC4I7MRCRIBKRXWHPXSO","short_pith_number":"pith:CXSZUQHC","schema_version":"1.0","canonical_sha256":"15e59a40e2e23ec88a280aa37b1df793b0e2e6472cd44857ab98cf9bee42d194","source":{"kind":"arxiv","id":"2505.14719","version":3},"attestation_state":"computed","paper":{"title":"MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenlin Zhou, Jibin Wu, Wei Hua, Yangyang Shu, Yansong Chua","submitted_at":"2025-05-19T14:01:03Z","abstract_excerpt":"The combination of Spiking Neural Networks (SNNs) with Vision Transformer architectures has garnered significant attention due to their potential for energy-efficient and high-performance computing paradigms. However, a substantial performance gap still exists between SNN-based and ANN-based transformer architectures. While existing methods propose spiking self-attention mechanisms that are successfully combined with SNNs, the overall architectures proposed by these methods suffer from a bottleneck in effectively extracting features from different image scales. In this paper, we address this i"},"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":"2505.14719","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T14:01:03Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"74abccd727868bcd75fd58b20ed263273ce5a2162ffa1c1c10560452fbca8275","abstract_canon_sha256":"b28c88dc4d4387ae9ed3935e61c661dd0d768fedf14ce46b7cf38814f3d91541"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:23:28.299450Z","signature_b64":"Z7bxGhIsGGOswUHAWpR0RHHQ+M3vmeZeORnDwCrxPQ9t/B/SOTPdTdG399h53aA06z1FjvIHPhf70G4QxTUzDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15e59a40e2e23ec88a280aa37b1df793b0e2e6472cd44857ab98cf9bee42d194","last_reissued_at":"2026-07-05T11:23:28.298893Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:23:28.298893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSVIT: Improving Spiking Vision Transformer Using Multi-scale Attention Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chenlin Zhou, Jibin Wu, Wei Hua, Yangyang Shu, Yansong Chua","submitted_at":"2025-05-19T14:01:03Z","abstract_excerpt":"The combination of Spiking Neural Networks (SNNs) with Vision Transformer architectures has garnered significant attention due to their potential for energy-efficient and high-performance computing paradigms. However, a substantial performance gap still exists between SNN-based and ANN-based transformer architectures. While existing methods propose spiking self-attention mechanisms that are successfully combined with SNNs, the overall architectures proposed by these methods suffer from a bottleneck in effectively extracting features from different image scales. In this paper, we address this i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.14719","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/2505.14719/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":"2505.14719","created_at":"2026-07-05T11:23:28.298963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.14719v3","created_at":"2026-07-05T11:23:28.298963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.14719","created_at":"2026-07-05T11:23:28.298963+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXSZUQHC4I7M","created_at":"2026-07-05T11:23:28.298963+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXSZUQHC4I7MRCRI","created_at":"2026-07-05T11:23:28.298963+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXSZUQHC","created_at":"2026-07-05T11:23:28.298963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08270","citing_title":"SAFformer:Improving Spiking Transformer via Active Predictive Filtering","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CXSZUQHC4I7MRCRIBKRXWHPXSO","json":"https://pith.science/pith/CXSZUQHC4I7MRCRIBKRXWHPXSO.json","graph_json":"https://pith.science/api/pith-number/CXSZUQHC4I7MRCRIBKRXWHPXSO/graph.json","events_json":"https://pith.science/api/pith-number/CXSZUQHC4I7MRCRIBKRXWHPXSO/events.json","paper":"https://pith.science/paper/CXSZUQHC"},"agent_actions":{"view_html":"https://pith.science/pith/CXSZUQHC4I7MRCRIBKRXWHPXSO","download_json":"https://pith.science/pith/CXSZUQHC4I7MRCRIBKRXWHPXSO.json","view_paper":"https://pith.science/paper/CXSZUQHC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.14719&json=true","fetch_graph":"https://pith.science/api/pith-number/CXSZUQHC4I7MRCRIBKRXWHPXSO/graph.json","fetch_events":"https://pith.science/api/pith-number/CXSZUQHC4I7MRCRIBKRXWHPXSO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXSZUQHC4I7MRCRIBKRXWHPXSO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXSZUQHC4I7MRCRIBKRXWHPXSO/action/storage_attestation","attest_author":"https://pith.science/pith/CXSZUQHC4I7MRCRIBKRXWHPXSO/action/author_attestation","sign_citation":"https://pith.science/pith/CXSZUQHC4I7MRCRIBKRXWHPXSO/action/citation_signature","submit_replication":"https://pith.science/pith/CXSZUQHC4I7MRCRIBKRXWHPXSO/action/replication_record"}},"created_at":"2026-07-05T11:23:28.298963+00:00","updated_at":"2026-07-05T11:23:28.298963+00:00"}