{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U5LUD73W22XKQDUEZYMX3DXCQJ","short_pith_number":"pith:U5LUD73W","schema_version":"1.0","canonical_sha256":"a75741ff76d6aea80e84ce197d8ee282441aa5020924ac50dc1a31bad7d17315","source":{"kind":"arxiv","id":"2501.13492","version":5},"attestation_state":"computed","paper":{"title":"Quantized Spike-driven Transformer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haizhou Li, Honglin Cao, Jieyuan Zhang, Junsheng Guo, Malu Zhang, Rui-Jie Zhu, Wenjie Wei, Xuerui Qiu, Yang Yang, Yimeng Shan","submitted_at":"2025-01-23T09:14:15Z","abstract_excerpt":"Spiking neural networks are emerging as a promising energy-efficient alternative to traditional artificial neural networks due to their spike-driven paradigm. However, recent research in the SNN domain has mainly focused on enhancing accuracy by designing large-scale Transformer structures, which typically rely on substantial computational resources, limiting their deployment on resource-constrained devices. To overcome this challenge, we propose a quantized spike-driven Transformer baseline (QSD-Transformer), which achieves reduced resource demands by utilizing a low bit-width parameter. Regr"},"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":"2501.13492","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-23T09:14:15Z","cross_cats_sorted":[],"title_canon_sha256":"851443b83cb93302d37616e95ac4319f007f0c79e439afe09a5e848f2218fa61","abstract_canon_sha256":"667e80fa69b0dddbb072381423f8947334b59398ea61be9e4d753d75ea88905f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:43.312885Z","signature_b64":"1Ua3TTGfhSHzU2d4PhZdbD6hmNXpXl8kDFmsXEYvDjVJ8Zapxzlqu9ibNoKkH/tWXbTeSPeW5pkbD75HZozfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a75741ff76d6aea80e84ce197d8ee282441aa5020924ac50dc1a31bad7d17315","last_reissued_at":"2026-07-05T10:37:43.312053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:43.312053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Quantized Spike-driven Transformer","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haizhou Li, Honglin Cao, Jieyuan Zhang, Junsheng Guo, Malu Zhang, Rui-Jie Zhu, Wenjie Wei, Xuerui Qiu, Yang Yang, Yimeng Shan","submitted_at":"2025-01-23T09:14:15Z","abstract_excerpt":"Spiking neural networks are emerging as a promising energy-efficient alternative to traditional artificial neural networks due to their spike-driven paradigm. However, recent research in the SNN domain has mainly focused on enhancing accuracy by designing large-scale Transformer structures, which typically rely on substantial computational resources, limiting their deployment on resource-constrained devices. To overcome this challenge, we propose a quantized spike-driven Transformer baseline (QSD-Transformer), which achieves reduced resource demands by utilizing a low bit-width parameter. Regr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.13492","kind":"arxiv","version":5},"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/2501.13492/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":"2501.13492","created_at":"2026-07-05T10:37:43.312156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.13492v5","created_at":"2026-07-05T10:37:43.312156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.13492","created_at":"2026-07-05T10:37:43.312156+00:00"},{"alias_kind":"pith_short_12","alias_value":"U5LUD73W22XK","created_at":"2026-07-05T10:37:43.312156+00:00"},{"alias_kind":"pith_short_16","alias_value":"U5LUD73W22XKQDUE","created_at":"2026-07-05T10:37:43.312156+00:00"},{"alias_kind":"pith_short_8","alias_value":"U5LUD73W","created_at":"2026-07-05T10:37:43.312156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.03648","citing_title":"SAFA-SNN: Sparsity-Aware On-Device Few-Shot Class-Incremental Learning with Fast-Adaptive Structure of Spiking Neural Network","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08270","citing_title":"SAFformer:Improving Spiking Transformer via Active Predictive Filtering","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U5LUD73W22XKQDUEZYMX3DXCQJ","json":"https://pith.science/pith/U5LUD73W22XKQDUEZYMX3DXCQJ.json","graph_json":"https://pith.science/api/pith-number/U5LUD73W22XKQDUEZYMX3DXCQJ/graph.json","events_json":"https://pith.science/api/pith-number/U5LUD73W22XKQDUEZYMX3DXCQJ/events.json","paper":"https://pith.science/paper/U5LUD73W"},"agent_actions":{"view_html":"https://pith.science/pith/U5LUD73W22XKQDUEZYMX3DXCQJ","download_json":"https://pith.science/pith/U5LUD73W22XKQDUEZYMX3DXCQJ.json","view_paper":"https://pith.science/paper/U5LUD73W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.13492&json=true","fetch_graph":"https://pith.science/api/pith-number/U5LUD73W22XKQDUEZYMX3DXCQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/U5LUD73W22XKQDUEZYMX3DXCQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U5LUD73W22XKQDUEZYMX3DXCQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U5LUD73W22XKQDUEZYMX3DXCQJ/action/storage_attestation","attest_author":"https://pith.science/pith/U5LUD73W22XKQDUEZYMX3DXCQJ/action/author_attestation","sign_citation":"https://pith.science/pith/U5LUD73W22XKQDUEZYMX3DXCQJ/action/citation_signature","submit_replication":"https://pith.science/pith/U5LUD73W22XKQDUEZYMX3DXCQJ/action/replication_record"}},"created_at":"2026-07-05T10:37:43.312156+00:00","updated_at":"2026-07-05T10:37:43.312156+00:00"}