{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WXDS3T2VDO7MTHLYQZLW7JKPHP","short_pith_number":"pith:WXDS3T2V","schema_version":"1.0","canonical_sha256":"b5c72dcf551bbec99d7886576fa54f3befb137e8c3f1998ec0ce31398c3fbfa0","source":{"kind":"arxiv","id":"2403.16552","version":2},"attestation_state":"computed","paper":{"title":"QKFormer: Hierarchical Spiking Transformer using Q-K Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.NE","authors_text":"Chenlin Zhou, Han Zhang, Huihui Zhou, Liutao Yu, Liwei Huang, Li Yuan, Xiaopeng Fan, Yonghong Tian, Zhaokun Zhou, Zhengyu Ma","submitted_at":"2024-03-25T08:57:27Z","abstract_excerpt":"Spiking Transformers, which integrate Spiking Neural Networks (SNNs) with Transformer architectures, have attracted significant attention due to their potential for energy efficiency and high performance. However, existing models in this domain still suffer from suboptimal performance. We introduce several innovations to improve the performance: i) We propose a novel spike-form Q-K attention mechanism, tailored for SNNs, which efficiently models the importance of token or channel dimensions through binary vectors with linear complexity. ii) We incorporate the hierarchical structure, which sign"},"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":"2403.16552","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2024-03-25T08:57:27Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"f4e4befaadc9b141ad76fcdebfd5bdb59416e2004bab733a994fa59820014d64","abstract_canon_sha256":"0a60722cb814348432dc0667e479f7f15d179ac916ef0e8544f9a61c1d3b3b18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:39.440475Z","signature_b64":"I6E7zGq0DmAUGxvmsz0rlphuB3B+6Nb+h5OOWAhAyV0AuzdLjdMZ9pxCHmuZkTJlxZ+t6va1jPFVQzHih3ijDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b5c72dcf551bbec99d7886576fa54f3befb137e8c3f1998ec0ce31398c3fbfa0","last_reissued_at":"2026-05-22T01:03:39.439817Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:39.439817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"QKFormer: Hierarchical Spiking Transformer using Q-K Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.NE","authors_text":"Chenlin Zhou, Han Zhang, Huihui Zhou, Liutao Yu, Liwei Huang, Li Yuan, Xiaopeng Fan, Yonghong Tian, Zhaokun Zhou, Zhengyu Ma","submitted_at":"2024-03-25T08:57:27Z","abstract_excerpt":"Spiking Transformers, which integrate Spiking Neural Networks (SNNs) with Transformer architectures, have attracted significant attention due to their potential for energy efficiency and high performance. However, existing models in this domain still suffer from suboptimal performance. We introduce several innovations to improve the performance: i) We propose a novel spike-form Q-K attention mechanism, tailored for SNNs, which efficiently models the importance of token or channel dimensions through binary vectors with linear complexity. ii) We incorporate the hierarchical structure, which sign"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.16552","kind":"arxiv","version":2},"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/2403.16552/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":"2403.16552","created_at":"2026-05-22T01:03:39.439907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.16552v2","created_at":"2026-05-22T01:03:39.439907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.16552","created_at":"2026-05-22T01:03:39.439907+00:00"},{"alias_kind":"pith_short_12","alias_value":"WXDS3T2VDO7M","created_at":"2026-05-22T01:03:39.439907+00:00"},{"alias_kind":"pith_short_16","alias_value":"WXDS3T2VDO7MTHLY","created_at":"2026-05-22T01:03:39.439907+00:00"},{"alias_kind":"pith_short_8","alias_value":"WXDS3T2V","created_at":"2026-05-22T01:03:39.439907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2501.06786","citing_title":"Temporal-Aware Spiking Transformer Hashing Based on 3D-DWT","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25188","citing_title":"Image Classification via Random Dilated Convolution with Multi-Branch Feature Extraction and Context Excitation","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WXDS3T2VDO7MTHLYQZLW7JKPHP","json":"https://pith.science/pith/WXDS3T2VDO7MTHLYQZLW7JKPHP.json","graph_json":"https://pith.science/api/pith-number/WXDS3T2VDO7MTHLYQZLW7JKPHP/graph.json","events_json":"https://pith.science/api/pith-number/WXDS3T2VDO7MTHLYQZLW7JKPHP/events.json","paper":"https://pith.science/paper/WXDS3T2V"},"agent_actions":{"view_html":"https://pith.science/pith/WXDS3T2VDO7MTHLYQZLW7JKPHP","download_json":"https://pith.science/pith/WXDS3T2VDO7MTHLYQZLW7JKPHP.json","view_paper":"https://pith.science/paper/WXDS3T2V","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.16552&json=true","fetch_graph":"https://pith.science/api/pith-number/WXDS3T2VDO7MTHLYQZLW7JKPHP/graph.json","fetch_events":"https://pith.science/api/pith-number/WXDS3T2VDO7MTHLYQZLW7JKPHP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WXDS3T2VDO7MTHLYQZLW7JKPHP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WXDS3T2VDO7MTHLYQZLW7JKPHP/action/storage_attestation","attest_author":"https://pith.science/pith/WXDS3T2VDO7MTHLYQZLW7JKPHP/action/author_attestation","sign_citation":"https://pith.science/pith/WXDS3T2VDO7MTHLYQZLW7JKPHP/action/citation_signature","submit_replication":"https://pith.science/pith/WXDS3T2VDO7MTHLYQZLW7JKPHP/action/replication_record"}},"created_at":"2026-05-22T01:03:39.439907+00:00","updated_at":"2026-05-22T01:03:39.439907+00:00"}