{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GGJCKKXS7DM7OAWAZ5BMVIBA2R","short_pith_number":"pith:GGJCKKXS","schema_version":"1.0","canonical_sha256":"3192252af2f8d9f702c0cf42caa020d46fdd7f846bdac66980a26562e49fd53f","source":{"kind":"arxiv","id":"2404.17456","version":1},"attestation_state":"computed","paper":{"title":"Converting High-Performance and Low-Latency SNNs through Explicit Modelling of Residual Error in ANNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Haoran Li, Jianhao Ding, Jian K. Liu, Ying Fang, Zhaofei Yu, Zhipeng Huang, Zhiyu Pan","submitted_at":"2024-04-26T14:50:46Z","abstract_excerpt":"Spiking neural networks (SNNs) have garnered interest due to their energy efficiency and superior effectiveness on neuromorphic chips compared with traditional artificial neural networks (ANNs). One of the mainstream approaches to implementing deep SNNs is the ANN-SNN conversion, which integrates the efficient training strategy of ANNs with the energy-saving potential and fast inference capability of SNNs. However, under extreme low-latency conditions, the existing conversion theory suggests that the problem of misrepresentation of residual membrane potentials in SNNs, i.e., the inability of I"},"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":"2404.17456","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2024-04-26T14:50:46Z","cross_cats_sorted":[],"title_canon_sha256":"64eebc1d46ab14460bdcac772d632635f7385530996e4cecf72273ed4cbd1735","abstract_canon_sha256":"e8bc367c976531ac110b91632bc4613d962fc6d98105b30d26dcfeed082881c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:37.987743Z","signature_b64":"fw9UX7fxN/WOSxysKcAQtE20s5/vqE5gJ1QzInW2/A56tp20cdHNDqsbnPgvL9btcT6xMvpJIrQMsNGWZdMTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3192252af2f8d9f702c0cf42caa020d46fdd7f846bdac66980a26562e49fd53f","last_reissued_at":"2026-07-05T08:12:37.987275Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:37.987275Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Converting High-Performance and Low-Latency SNNs through Explicit Modelling of Residual Error in ANNs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Haoran Li, Jianhao Ding, Jian K. Liu, Ying Fang, Zhaofei Yu, Zhipeng Huang, Zhiyu Pan","submitted_at":"2024-04-26T14:50:46Z","abstract_excerpt":"Spiking neural networks (SNNs) have garnered interest due to their energy efficiency and superior effectiveness on neuromorphic chips compared with traditional artificial neural networks (ANNs). One of the mainstream approaches to implementing deep SNNs is the ANN-SNN conversion, which integrates the efficient training strategy of ANNs with the energy-saving potential and fast inference capability of SNNs. However, under extreme low-latency conditions, the existing conversion theory suggests that the problem of misrepresentation of residual membrane potentials in SNNs, i.e., the inability of I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.17456","kind":"arxiv","version":1},"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/2404.17456/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":"2404.17456","created_at":"2026-07-05T08:12:37.987345+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.17456v1","created_at":"2026-07-05T08:12:37.987345+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.17456","created_at":"2026-07-05T08:12:37.987345+00:00"},{"alias_kind":"pith_short_12","alias_value":"GGJCKKXS7DM7","created_at":"2026-07-05T08:12:37.987345+00:00"},{"alias_kind":"pith_short_16","alias_value":"GGJCKKXS7DM7OAWA","created_at":"2026-07-05T08:12:37.987345+00:00"},{"alias_kind":"pith_short_8","alias_value":"GGJCKKXS","created_at":"2026-07-05T08:12:37.987345+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14520","citing_title":"Quantization Meets Spikes: Nearly Lossless Conversion at the First Timestep via Polarity Multi-Spike Mapping","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GGJCKKXS7DM7OAWAZ5BMVIBA2R","json":"https://pith.science/pith/GGJCKKXS7DM7OAWAZ5BMVIBA2R.json","graph_json":"https://pith.science/api/pith-number/GGJCKKXS7DM7OAWAZ5BMVIBA2R/graph.json","events_json":"https://pith.science/api/pith-number/GGJCKKXS7DM7OAWAZ5BMVIBA2R/events.json","paper":"https://pith.science/paper/GGJCKKXS"},"agent_actions":{"view_html":"https://pith.science/pith/GGJCKKXS7DM7OAWAZ5BMVIBA2R","download_json":"https://pith.science/pith/GGJCKKXS7DM7OAWAZ5BMVIBA2R.json","view_paper":"https://pith.science/paper/GGJCKKXS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.17456&json=true","fetch_graph":"https://pith.science/api/pith-number/GGJCKKXS7DM7OAWAZ5BMVIBA2R/graph.json","fetch_events":"https://pith.science/api/pith-number/GGJCKKXS7DM7OAWAZ5BMVIBA2R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GGJCKKXS7DM7OAWAZ5BMVIBA2R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GGJCKKXS7DM7OAWAZ5BMVIBA2R/action/storage_attestation","attest_author":"https://pith.science/pith/GGJCKKXS7DM7OAWAZ5BMVIBA2R/action/author_attestation","sign_citation":"https://pith.science/pith/GGJCKKXS7DM7OAWAZ5BMVIBA2R/action/citation_signature","submit_replication":"https://pith.science/pith/GGJCKKXS7DM7OAWAZ5BMVIBA2R/action/replication_record"}},"created_at":"2026-07-05T08:12:37.987345+00:00","updated_at":"2026-07-05T08:12:37.987345+00:00"}