{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VZMAFJXM3JXPUQTVEI3PQCU6DX","short_pith_number":"pith:VZMAFJXM","schema_version":"1.0","canonical_sha256":"ae5802a6ecda6efa42752236f80a9e1dd49bf97eb1c8f40ac08b03e13b89e665","source":{"kind":"arxiv","id":"2402.04663","version":5},"attestation_state":"computed","paper":{"title":"CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Biao Pan, Bojun Cheng, Haotian Fu, Hongwei Ren, Xiaopeng Lin, Yue Zhou, Yulong Huang, Zunchang Liu","submitted_at":"2024-02-07T08:51:57Z","abstract_excerpt":"Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Compared to conventional deep Artificial Neural Networks (ANNs), SNNs exhibit superior efficiency and capability to process temporal information. However, it remains a challenge to train SNNs due to their undifferentiable spiking mechanism. The surrogate gradients method is commonly used to train SNNs, but often comes with an accuracy disadvantage over ANNs counterpart. We link the degraded accuracy to the vanishing of gradient on the temporal dimension through the analytical and experimental study of the trai"},"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":"2402.04663","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2024-02-07T08:51:57Z","cross_cats_sorted":[],"title_canon_sha256":"ceb75e335ee37fa105c6cc167b4508fc4ba5d23aa06c81f36a81f98bef1fe353","abstract_canon_sha256":"e0588fb3d088a5aa80a01cd3c44965f583e733c32cca00bfa9fb54aa2f7ce85c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:58.097334Z","signature_b64":"AKTD4dwMjuCLS4igpSzusRgOwJqO2c6SlTJhu1kUaZv35Trp9+98fE5cBn0JafxfiX/dHYzn131T1DDaTJd9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae5802a6ecda6efa42752236f80a9e1dd49bf97eb1c8f40ac08b03e13b89e665","last_reissued_at":"2026-07-05T10:16:58.096833Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:58.096833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CLIF: Complementary Leaky Integrate-and-Fire Neuron for Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Biao Pan, Bojun Cheng, Haotian Fu, Hongwei Ren, Xiaopeng Lin, Yue Zhou, Yulong Huang, Zunchang Liu","submitted_at":"2024-02-07T08:51:57Z","abstract_excerpt":"Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Compared to conventional deep Artificial Neural Networks (ANNs), SNNs exhibit superior efficiency and capability to process temporal information. However, it remains a challenge to train SNNs due to their undifferentiable spiking mechanism. The surrogate gradients method is commonly used to train SNNs, but often comes with an accuracy disadvantage over ANNs counterpart. We link the degraded accuracy to the vanishing of gradient on the temporal dimension through the analytical and experimental study of the trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04663","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/2402.04663/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":"2402.04663","created_at":"2026-07-05T10:16:58.096893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.04663v5","created_at":"2026-07-05T10:16:58.096893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04663","created_at":"2026-07-05T10:16:58.096893+00:00"},{"alias_kind":"pith_short_12","alias_value":"VZMAFJXM3JXP","created_at":"2026-07-05T10:16:58.096893+00:00"},{"alias_kind":"pith_short_16","alias_value":"VZMAFJXM3JXPUQTV","created_at":"2026-07-05T10:16:58.096893+00:00"},{"alias_kind":"pith_short_8","alias_value":"VZMAFJXM","created_at":"2026-07-05T10:16:58.096893+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.01866","citing_title":"ShiftLIF: Efficient Multi-Level Spiking Neurons with Power-of-Two Quantization","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VZMAFJXM3JXPUQTVEI3PQCU6DX","json":"https://pith.science/pith/VZMAFJXM3JXPUQTVEI3PQCU6DX.json","graph_json":"https://pith.science/api/pith-number/VZMAFJXM3JXPUQTVEI3PQCU6DX/graph.json","events_json":"https://pith.science/api/pith-number/VZMAFJXM3JXPUQTVEI3PQCU6DX/events.json","paper":"https://pith.science/paper/VZMAFJXM"},"agent_actions":{"view_html":"https://pith.science/pith/VZMAFJXM3JXPUQTVEI3PQCU6DX","download_json":"https://pith.science/pith/VZMAFJXM3JXPUQTVEI3PQCU6DX.json","view_paper":"https://pith.science/paper/VZMAFJXM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.04663&json=true","fetch_graph":"https://pith.science/api/pith-number/VZMAFJXM3JXPUQTVEI3PQCU6DX/graph.json","fetch_events":"https://pith.science/api/pith-number/VZMAFJXM3JXPUQTVEI3PQCU6DX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VZMAFJXM3JXPUQTVEI3PQCU6DX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VZMAFJXM3JXPUQTVEI3PQCU6DX/action/storage_attestation","attest_author":"https://pith.science/pith/VZMAFJXM3JXPUQTVEI3PQCU6DX/action/author_attestation","sign_citation":"https://pith.science/pith/VZMAFJXM3JXPUQTVEI3PQCU6DX/action/citation_signature","submit_replication":"https://pith.science/pith/VZMAFJXM3JXPUQTVEI3PQCU6DX/action/replication_record"}},"created_at":"2026-07-05T10:16:58.096893+00:00","updated_at":"2026-07-05T10:16:58.096893+00:00"}