{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7WZ54M7ID3QTSI7YAEKSJZ6AKV","short_pith_number":"pith:7WZ54M7I","schema_version":"1.0","canonical_sha256":"fdb3de33e81ee13923f8011524e7c055662b28fa4b30cf5e25cff811c1b805f8","source":{"kind":"arxiv","id":"2209.15425","version":2},"attestation_state":"computed","paper":{"title":"Spikformer: When Spiking Neural Network Meets Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.NE","authors_text":"Chao He, Li Yuan, Shuicheng Yan, Yaowei Wang, Yonghong Tian, Yuesheng Zhu, Zhaokun Zhou","submitted_at":"2022-09-29T14:16:49Z","abstract_excerpt":"We consider two biologically plausible structures, the Spiking Neural Network (SNN) and the self-attention mechanism. The former offers an energy-efficient and event-driven paradigm for deep learning, while the latter has the ability to capture feature dependencies, enabling Transformer to achieve good performance. It is intuitively promising to explore the marriage between them. In this paper, we consider leveraging both self-attention capability and biological properties of SNNs, and propose a novel Spiking Self Attention (SSA) as well as a powerful framework, named Spiking Transformer (Spik"},"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":"2209.15425","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2022-09-29T14:16:49Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"035989e08db871aa23d43cc229d24087d80e2286f5b97e6d632a618c4f22170b","abstract_canon_sha256":"f7bf3643fcd575a815bba2fcac4166b825061a2035acf8473a996caec0f02a58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:18:07.453754Z","signature_b64":"t2icFqonmjKmYqsYrI8Uzac/Ct4ch5IGjSzZCxL3MQt54ofQOdju4hsTzrg9g+CQeu3kAcM9CP/CP9DIjaHzBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fdb3de33e81ee13923f8011524e7c055662b28fa4b30cf5e25cff811c1b805f8","last_reissued_at":"2026-07-05T05:18:07.453301Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:18:07.453301Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spikformer: When Spiking Neural Network Meets Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.NE","authors_text":"Chao He, Li Yuan, Shuicheng Yan, Yaowei Wang, Yonghong Tian, Yuesheng Zhu, Zhaokun Zhou","submitted_at":"2022-09-29T14:16:49Z","abstract_excerpt":"We consider two biologically plausible structures, the Spiking Neural Network (SNN) and the self-attention mechanism. The former offers an energy-efficient and event-driven paradigm for deep learning, while the latter has the ability to capture feature dependencies, enabling Transformer to achieve good performance. It is intuitively promising to explore the marriage between them. In this paper, we consider leveraging both self-attention capability and biological properties of SNNs, and propose a novel Spiking Self Attention (SSA) as well as a powerful framework, named Spiking Transformer (Spik"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.15425","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/2209.15425/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":"2209.15425","created_at":"2026-07-05T05:18:07.453372+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.15425v2","created_at":"2026-07-05T05:18:07.453372+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.15425","created_at":"2026-07-05T05:18:07.453372+00:00"},{"alias_kind":"pith_short_12","alias_value":"7WZ54M7ID3QT","created_at":"2026-07-05T05:18:07.453372+00:00"},{"alias_kind":"pith_short_16","alias_value":"7WZ54M7ID3QTSI7Y","created_at":"2026-07-05T05:18:07.453372+00:00"},{"alias_kind":"pith_short_8","alias_value":"7WZ54M7I","created_at":"2026-07-05T05:18:07.453372+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12895","citing_title":"LongSpike: Fractional Order Spiking State Space Models for Efficient Long Sequence Learning","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06856","citing_title":"FS-DVS: A Frequency-Selective Dynamic Visual Sensing Paradigm for Enhancing Information Completeness","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07657","citing_title":"QDS-SNN: Energy-efficient Quantum Deeply-Supervised Spiking Neural Network Algorithm for Traffic Sign Recognition","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01135","citing_title":"Spiking and Event-driven Neuromorphic Mamba Models for Efficient Speech Recognition","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00740","citing_title":"SpikeHash: Learning Binary Codes with Spiking Neural Networks for Cross-Modal Hashing Retrieval","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27412","citing_title":"Advancing Direct Training for Spiking Neural Networks with Circulate-Firing Neurons and Learnable Gradients","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23188","citing_title":"SpikingMoE: SDPrompt-Guided Dynamic Expert Fusion in Spiking Neural Networks","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23796","citing_title":"UniSpike: Accelerating Spiking Neural Networks on Neuromorphic Systems via Eliminating Address Redundancy","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18328","citing_title":"EventCrab: Harnessing Frame and Point Synergy for Event-based Action Recognition and Beyond","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2501.06786","citing_title":"Temporal-Aware Spiking Transformer Hashing Based on 3D-DWT","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20289","citing_title":"Plug-and-Play Spiking Operators: Breaking the Nonlinearity Bottleneck in Spiking Transformers","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20802","citing_title":"ELSA: An ELastic SNN Inference Architecture for Efficient Neuromorphic Computing","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13859","citing_title":"BiSpikCLM: A Spiking Language Model integrating Softmax-Free Spiking Attention and Spike-Aware Alignment Distillation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09276","citing_title":"Uncertainty-Aware Token Importance Estimation in Spiking Transformers","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00662","citing_title":"Spiking Sequence Machines and Transformers","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00604","citing_title":"Affinity Is Not Enough: Recovering the Free Energy Principle in Mixture-of-Experts","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10458","citing_title":"Towards Green Wearable Computing: A Physics-Aware Spiking Neural Network for Energy-Efficient IMU-based Human Activity Recognition","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16436","citing_title":"Fuzzy Encoding-Decoding to Improve Spiking Q-Learning Performance in Autonomous Driving","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01866","citing_title":"ShiftLIF: Efficient Multi-Level Spiking Neurons with Power-of-Two Quantization","ref_index":58,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7WZ54M7ID3QTSI7YAEKSJZ6AKV","json":"https://pith.science/pith/7WZ54M7ID3QTSI7YAEKSJZ6AKV.json","graph_json":"https://pith.science/api/pith-number/7WZ54M7ID3QTSI7YAEKSJZ6AKV/graph.json","events_json":"https://pith.science/api/pith-number/7WZ54M7ID3QTSI7YAEKSJZ6AKV/events.json","paper":"https://pith.science/paper/7WZ54M7I"},"agent_actions":{"view_html":"https://pith.science/pith/7WZ54M7ID3QTSI7YAEKSJZ6AKV","download_json":"https://pith.science/pith/7WZ54M7ID3QTSI7YAEKSJZ6AKV.json","view_paper":"https://pith.science/paper/7WZ54M7I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.15425&json=true","fetch_graph":"https://pith.science/api/pith-number/7WZ54M7ID3QTSI7YAEKSJZ6AKV/graph.json","fetch_events":"https://pith.science/api/pith-number/7WZ54M7ID3QTSI7YAEKSJZ6AKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7WZ54M7ID3QTSI7YAEKSJZ6AKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7WZ54M7ID3QTSI7YAEKSJZ6AKV/action/storage_attestation","attest_author":"https://pith.science/pith/7WZ54M7ID3QTSI7YAEKSJZ6AKV/action/author_attestation","sign_citation":"https://pith.science/pith/7WZ54M7ID3QTSI7YAEKSJZ6AKV/action/citation_signature","submit_replication":"https://pith.science/pith/7WZ54M7ID3QTSI7YAEKSJZ6AKV/action/replication_record"}},"created_at":"2026-07-05T05:18:07.453372+00:00","updated_at":"2026-07-05T05:18:07.453372+00:00"}