{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:D3G3AAGXHYWNDOKNIKEOFX7BXY","short_pith_number":"pith:D3G3AAGX","schema_version":"1.0","canonical_sha256":"1ecdb000d73e2cd1b94d4288e2dfe1be39907ad53f4490e7a1cf35273b2b4bd4","source":{"kind":"arxiv","id":"2204.13271","version":2},"attestation_state":"computed","paper":{"title":"Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Yang Li, Yi Zeng","submitted_at":"2022-04-28T03:48:17Z","abstract_excerpt":"Spiking neural network (SNN), as a brain-inspired energy-efficient neural network, has attracted the interest of researchers. While the training of spiking neural networks is still an open problem. One effective way is to map the weight of trained ANN to SNN to achieve high reasoning ability. However, the converted spiking neural network often suffers from performance degradation and a considerable time delay. To speed up the inference process and obtain higher accuracy, we theoretically analyze the errors in the conversion process from three perspectives: the differences between IF and ReLU, "},"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":"2204.13271","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2022-04-28T03:48:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b7ba8eb12e47273ba1536db94e0912cdaf1edff08b522c961ed88ec2bb7d0da8","abstract_canon_sha256":"581576f1146c62176540f0950eea4dc29a359a67069033e7d61223cafc212753"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:21:12.831773Z","signature_b64":"T/N2ud4+cQ3X925VX8cnpBzWLlP1kP9FSEkXnlCCY76phpS85Cajl3XbU8nkuZPBWRHFbY0d72OoWA8c8a+NCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ecdb000d73e2cd1b94d4288e2dfe1be39907ad53f4490e7a1cf35273b2b4bd4","last_reissued_at":"2026-07-05T04:21:12.831302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:21:12.831302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient and Accurate Conversion of Spiking Neural Network with Burst Spikes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Yang Li, Yi Zeng","submitted_at":"2022-04-28T03:48:17Z","abstract_excerpt":"Spiking neural network (SNN), as a brain-inspired energy-efficient neural network, has attracted the interest of researchers. While the training of spiking neural networks is still an open problem. One effective way is to map the weight of trained ANN to SNN to achieve high reasoning ability. However, the converted spiking neural network often suffers from performance degradation and a considerable time delay. To speed up the inference process and obtain higher accuracy, we theoretically analyze the errors in the conversion process from three perspectives: the differences between IF and ReLU, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.13271","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/2204.13271/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":"2204.13271","created_at":"2026-07-05T04:21:12.831366+00:00"},{"alias_kind":"arxiv_version","alias_value":"2204.13271v2","created_at":"2026-07-05T04:21:12.831366+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.13271","created_at":"2026-07-05T04:21:12.831366+00:00"},{"alias_kind":"pith_short_12","alias_value":"D3G3AAGXHYWN","created_at":"2026-07-05T04:21:12.831366+00:00"},{"alias_kind":"pith_short_16","alias_value":"D3G3AAGXHYWNDOKN","created_at":"2026-07-05T04:21:12.831366+00:00"},{"alias_kind":"pith_short_8","alias_value":"D3G3AAGX","created_at":"2026-07-05T04:21:12.831366+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07207","citing_title":"Direct-to-Event Spiking Neural Network Transfer","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D3G3AAGXHYWNDOKNIKEOFX7BXY","json":"https://pith.science/pith/D3G3AAGXHYWNDOKNIKEOFX7BXY.json","graph_json":"https://pith.science/api/pith-number/D3G3AAGXHYWNDOKNIKEOFX7BXY/graph.json","events_json":"https://pith.science/api/pith-number/D3G3AAGXHYWNDOKNIKEOFX7BXY/events.json","paper":"https://pith.science/paper/D3G3AAGX"},"agent_actions":{"view_html":"https://pith.science/pith/D3G3AAGXHYWNDOKNIKEOFX7BXY","download_json":"https://pith.science/pith/D3G3AAGXHYWNDOKNIKEOFX7BXY.json","view_paper":"https://pith.science/paper/D3G3AAGX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2204.13271&json=true","fetch_graph":"https://pith.science/api/pith-number/D3G3AAGXHYWNDOKNIKEOFX7BXY/graph.json","fetch_events":"https://pith.science/api/pith-number/D3G3AAGXHYWNDOKNIKEOFX7BXY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D3G3AAGXHYWNDOKNIKEOFX7BXY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D3G3AAGXHYWNDOKNIKEOFX7BXY/action/storage_attestation","attest_author":"https://pith.science/pith/D3G3AAGXHYWNDOKNIKEOFX7BXY/action/author_attestation","sign_citation":"https://pith.science/pith/D3G3AAGXHYWNDOKNIKEOFX7BXY/action/citation_signature","submit_replication":"https://pith.science/pith/D3G3AAGXHYWNDOKNIKEOFX7BXY/action/replication_record"}},"created_at":"2026-07-05T04:21:12.831366+00:00","updated_at":"2026-07-05T04:21:12.831366+00:00"}