{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3IOV7WKXWJZSGTCSIGELP7AMHZ","short_pith_number":"pith:3IOV7WKX","schema_version":"1.0","canonical_sha256":"da1d5fd957b273234c524188b7fc0c3e5040af8f4b45d2b4ab52866b46c046a5","source":{"kind":"arxiv","id":"2202.11946","version":3},"attestation_state":"computed","paper":{"title":"Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Shanghang Zhang, Shi Gu, Shikuang Deng, Yuhang Li","submitted_at":"2022-02-24T08:02:37Z","abstract_excerpt":"Recently, brain-inspired spiking neuron networks (SNNs) have attracted widespread research interest because of their event-driven and energy-efficient characteristics. Still, it is difficult to efficiently train deep SNNs due to the non-differentiability of its activation function, which disables the typically used gradient descent approaches for traditional artificial neural networks (ANNs). Although the adoption of surrogate gradient (SG) formally allows for the back-propagation of losses, the discrete spiking mechanism actually differentiates the loss landscape of SNNs from that of ANNs, fa"},"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":"2202.11946","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2022-02-24T08:02:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5f2f0f7c2f3691c7066442f06eb9fe558cb93c62414f3b527c1540027b055db2","abstract_canon_sha256":"dcbf50749cb5578e14cbcda992d8a5af9ae23aa643a91ddee645d3df88610cac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:23:25.599200Z","signature_b64":"NCDiF1TlFTNdpbnYYwqQvVifVz1yVa8huinJDn/hftUgmxzZ066uo69gwJ23rD06gM8ozDCFtlOWvZrw9ZCyBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da1d5fd957b273234c524188b7fc0c3e5040af8f4b45d2b4ab52866b46c046a5","last_reissued_at":"2026-07-05T04:23:25.598736Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:23:25.598736Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temporal Efficient Training of Spiking Neural Network via Gradient Re-weighting","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Shanghang Zhang, Shi Gu, Shikuang Deng, Yuhang Li","submitted_at":"2022-02-24T08:02:37Z","abstract_excerpt":"Recently, brain-inspired spiking neuron networks (SNNs) have attracted widespread research interest because of their event-driven and energy-efficient characteristics. Still, it is difficult to efficiently train deep SNNs due to the non-differentiability of its activation function, which disables the typically used gradient descent approaches for traditional artificial neural networks (ANNs). Although the adoption of surrogate gradient (SG) formally allows for the back-propagation of losses, the discrete spiking mechanism actually differentiates the loss landscape of SNNs from that of ANNs, fa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.11946","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/2202.11946/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":"2202.11946","created_at":"2026-07-05T04:23:25.598795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.11946v3","created_at":"2026-07-05T04:23:25.598795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.11946","created_at":"2026-07-05T04:23:25.598795+00:00"},{"alias_kind":"pith_short_12","alias_value":"3IOV7WKXWJZS","created_at":"2026-07-05T04:23:25.598795+00:00"},{"alias_kind":"pith_short_16","alias_value":"3IOV7WKXWJZSGTCS","created_at":"2026-07-05T04:23:25.598795+00:00"},{"alias_kind":"pith_short_8","alias_value":"3IOV7WKX","created_at":"2026-07-05T04:23:25.598795+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07657","citing_title":"QDS-SNN: Energy-efficient Quantum Deeply-Supervised Spiking Neural Network Algorithm for Traffic Sign Recognition","ref_index":21,"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":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23188","citing_title":"SpikingMoE: SDPrompt-Guided Dynamic Expert Fusion in Spiking Neural Networks","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13887","citing_title":"Breaking Global Self-Attention Bottlenecks in Transformer-based Spiking Neural Networks with Local Structure-Aware Self-Attention","ref_index":60,"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":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3IOV7WKXWJZSGTCSIGELP7AMHZ","json":"https://pith.science/pith/3IOV7WKXWJZSGTCSIGELP7AMHZ.json","graph_json":"https://pith.science/api/pith-number/3IOV7WKXWJZSGTCSIGELP7AMHZ/graph.json","events_json":"https://pith.science/api/pith-number/3IOV7WKXWJZSGTCSIGELP7AMHZ/events.json","paper":"https://pith.science/paper/3IOV7WKX"},"agent_actions":{"view_html":"https://pith.science/pith/3IOV7WKXWJZSGTCSIGELP7AMHZ","download_json":"https://pith.science/pith/3IOV7WKXWJZSGTCSIGELP7AMHZ.json","view_paper":"https://pith.science/paper/3IOV7WKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.11946&json=true","fetch_graph":"https://pith.science/api/pith-number/3IOV7WKXWJZSGTCSIGELP7AMHZ/graph.json","fetch_events":"https://pith.science/api/pith-number/3IOV7WKXWJZSGTCSIGELP7AMHZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3IOV7WKXWJZSGTCSIGELP7AMHZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3IOV7WKXWJZSGTCSIGELP7AMHZ/action/storage_attestation","attest_author":"https://pith.science/pith/3IOV7WKXWJZSGTCSIGELP7AMHZ/action/author_attestation","sign_citation":"https://pith.science/pith/3IOV7WKXWJZSGTCSIGELP7AMHZ/action/citation_signature","submit_replication":"https://pith.science/pith/3IOV7WKXWJZSGTCSIGELP7AMHZ/action/replication_record"}},"created_at":"2026-07-05T04:23:25.598795+00:00","updated_at":"2026-07-05T04:23:25.598795+00:00"}