{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M3CHH347NJ4HFSR2JKVHY7WKSE","short_pith_number":"pith:M3CHH347","schema_version":"1.0","canonical_sha256":"66c473ef9f6a7872ca3a4aaa7c7eca9125f3cb9419eaf63107f07223c3f65674","source":{"kind":"arxiv","id":"2401.04486","version":2},"attestation_state":"computed","paper":{"title":"Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Weihang Peng, Xiaode Liu, Yuanpei Chen, Yufei Guo, Yuhan Zhang, Zecheng Hao, Zhe Ma, Zhou Jie","submitted_at":"2024-01-09T10:54:41Z","abstract_excerpt":"The Spiking Neural Network (SNN) is a biologically inspired neural network infrastructure that has recently garnered significant attention. It utilizes binary spike activations to transmit information, thereby replacing multiplications with additions and resulting in high energy efficiency. However, training an SNN directly poses a challenge due to the undefined gradient of the firing spike process. Although prior works have employed various surrogate gradient training methods that use an alternative function to replace the firing process during back-propagation, these approaches ignore an int"},"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":"2401.04486","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-09T10:54:41Z","cross_cats_sorted":[],"title_canon_sha256":"32cfbeeacf8f88f8a9d5adb38bf3f98d1fb1beb5a5a19f8c92d6eec7a3e68c2d","abstract_canon_sha256":"031fe0ae1e448eed26450067da5a7ca90ba01f0528c51a1a2d51159479d6ba37"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:58.386610Z","signature_b64":"dhrdcW61k9/3gY+PmMAcbIU9a8gWrEhvOGcRSgAV6npDiKgRioss7kK7hlWD2ALNogykdZd7URk92CkffNZ0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66c473ef9f6a7872ca3a4aaa7c7eca9125f3cb9419eaf63107f07223c3f65674","last_reissued_at":"2026-07-05T09:12:58.386138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:58.386138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Weihang Peng, Xiaode Liu, Yuanpei Chen, Yufei Guo, Yuhan Zhang, Zecheng Hao, Zhe Ma, Zhou Jie","submitted_at":"2024-01-09T10:54:41Z","abstract_excerpt":"The Spiking Neural Network (SNN) is a biologically inspired neural network infrastructure that has recently garnered significant attention. It utilizes binary spike activations to transmit information, thereby replacing multiplications with additions and resulting in high energy efficiency. However, training an SNN directly poses a challenge due to the undefined gradient of the firing spike process. Although prior works have employed various surrogate gradient training methods that use an alternative function to replace the firing process during back-propagation, these approaches ignore an int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.04486","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/2401.04486/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":"2401.04486","created_at":"2026-07-05T09:12:58.386198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.04486v2","created_at":"2026-07-05T09:12:58.386198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.04486","created_at":"2026-07-05T09:12:58.386198+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3CHH347NJ4H","created_at":"2026-07-05T09:12:58.386198+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3CHH347NJ4HFSR2","created_at":"2026-07-05T09:12:58.386198+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3CHH347","created_at":"2026-07-05T09:12:58.386198+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.02960","citing_title":"Optimization of Low-Latency Spiking Neural Networks Utilizing Historical Dynamics of Refractory Periods","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3CHH347NJ4HFSR2JKVHY7WKSE","json":"https://pith.science/pith/M3CHH347NJ4HFSR2JKVHY7WKSE.json","graph_json":"https://pith.science/api/pith-number/M3CHH347NJ4HFSR2JKVHY7WKSE/graph.json","events_json":"https://pith.science/api/pith-number/M3CHH347NJ4HFSR2JKVHY7WKSE/events.json","paper":"https://pith.science/paper/M3CHH347"},"agent_actions":{"view_html":"https://pith.science/pith/M3CHH347NJ4HFSR2JKVHY7WKSE","download_json":"https://pith.science/pith/M3CHH347NJ4HFSR2JKVHY7WKSE.json","view_paper":"https://pith.science/paper/M3CHH347","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.04486&json=true","fetch_graph":"https://pith.science/api/pith-number/M3CHH347NJ4HFSR2JKVHY7WKSE/graph.json","fetch_events":"https://pith.science/api/pith-number/M3CHH347NJ4HFSR2JKVHY7WKSE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3CHH347NJ4HFSR2JKVHY7WKSE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3CHH347NJ4HFSR2JKVHY7WKSE/action/storage_attestation","attest_author":"https://pith.science/pith/M3CHH347NJ4HFSR2JKVHY7WKSE/action/author_attestation","sign_citation":"https://pith.science/pith/M3CHH347NJ4HFSR2JKVHY7WKSE/action/citation_signature","submit_replication":"https://pith.science/pith/M3CHH347NJ4HFSR2JKVHY7WKSE/action/replication_record"}},"created_at":"2026-07-05T09:12:58.386198+00:00","updated_at":"2026-07-05T09:12:58.386198+00:00"}