{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LCNK7K6Q56PEGO6W4DVTUIMJME","short_pith_number":"pith:LCNK7K6Q","schema_version":"1.0","canonical_sha256":"589aafabd0ef9e433bd6e0eb3a2189613bea4d48070e29f4b7936e6277c97af3","source":{"kind":"arxiv","id":"2210.04195","version":2},"attestation_state":"computed","paper":{"title":"Online Training Through Time for Spiking Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Di He, Mingqing Xiao, Qingyan Meng, Zhouchen Lin, Zongpeng Zhang","submitted_at":"2022-10-09T07:47:56Z","abstract_excerpt":"Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Recent progress in training methods has enabled successful deep SNNs on large-scale tasks with low latency. Particularly, backpropagation through time (BPTT) with surrogate gradients (SG) is popularly used to achieve high performance in a very small number of time steps. However, it is at the cost of large memory consumption for training, lack of theoretical clarity for optimization, and inconsistency with the online property of biological learning and rules on neuromorphic hardware. Other works connect spike "},"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":"2210.04195","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.NE","submitted_at":"2022-10-09T07:47:56Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"45faf39adbbbd285c5d4c764556fc089a21757b1171d176020d9c48aa3c22be5","abstract_canon_sha256":"23680827a37149b313e08f1000c1875c84827db32c53e02b990de62e5fef5033"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:29:39.655272Z","signature_b64":"VxZHxvhQJ/ZTBLZwfCZ06haJM1iZljTyUiP7T5QIVBs/P7E6LRldVgZCJO5VBTnZ1qz725/I7g+FBe9WaSoKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"589aafabd0ef9e433bd6e0eb3a2189613bea4d48070e29f4b7936e6277c97af3","last_reissued_at":"2026-07-05T05:29:39.654872Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:29:39.654872Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Online Training Through Time for Spiking Neural Networks","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Di He, Mingqing Xiao, Qingyan Meng, Zhouchen Lin, Zongpeng Zhang","submitted_at":"2022-10-09T07:47:56Z","abstract_excerpt":"Spiking neural networks (SNNs) are promising brain-inspired energy-efficient models. Recent progress in training methods has enabled successful deep SNNs on large-scale tasks with low latency. Particularly, backpropagation through time (BPTT) with surrogate gradients (SG) is popularly used to achieve high performance in a very small number of time steps. However, it is at the cost of large memory consumption for training, lack of theoretical clarity for optimization, and inconsistency with the online property of biological learning and rules on neuromorphic hardware. Other works connect spike "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04195","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/2210.04195/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":"2210.04195","created_at":"2026-07-05T05:29:39.654929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.04195v2","created_at":"2026-07-05T05:29:39.654929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04195","created_at":"2026-07-05T05:29:39.654929+00:00"},{"alias_kind":"pith_short_12","alias_value":"LCNK7K6Q56PE","created_at":"2026-07-05T05:29:39.654929+00:00"},{"alias_kind":"pith_short_16","alias_value":"LCNK7K6Q56PEGO6W","created_at":"2026-07-05T05:29:39.654929+00:00"},{"alias_kind":"pith_short_8","alias_value":"LCNK7K6Q","created_at":"2026-07-05T05:29:39.654929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06636","citing_title":"Full Integer Arithmetic Online Training for Spiking Neural Networks","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LCNK7K6Q56PEGO6W4DVTUIMJME","json":"https://pith.science/pith/LCNK7K6Q56PEGO6W4DVTUIMJME.json","graph_json":"https://pith.science/api/pith-number/LCNK7K6Q56PEGO6W4DVTUIMJME/graph.json","events_json":"https://pith.science/api/pith-number/LCNK7K6Q56PEGO6W4DVTUIMJME/events.json","paper":"https://pith.science/paper/LCNK7K6Q"},"agent_actions":{"view_html":"https://pith.science/pith/LCNK7K6Q56PEGO6W4DVTUIMJME","download_json":"https://pith.science/pith/LCNK7K6Q56PEGO6W4DVTUIMJME.json","view_paper":"https://pith.science/paper/LCNK7K6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.04195&json=true","fetch_graph":"https://pith.science/api/pith-number/LCNK7K6Q56PEGO6W4DVTUIMJME/graph.json","fetch_events":"https://pith.science/api/pith-number/LCNK7K6Q56PEGO6W4DVTUIMJME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LCNK7K6Q56PEGO6W4DVTUIMJME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LCNK7K6Q56PEGO6W4DVTUIMJME/action/storage_attestation","attest_author":"https://pith.science/pith/LCNK7K6Q56PEGO6W4DVTUIMJME/action/author_attestation","sign_citation":"https://pith.science/pith/LCNK7K6Q56PEGO6W4DVTUIMJME/action/citation_signature","submit_replication":"https://pith.science/pith/LCNK7K6Q56PEGO6W4DVTUIMJME/action/replication_record"}},"created_at":"2026-07-05T05:29:39.654929+00:00","updated_at":"2026-07-05T05:29:39.654929+00:00"}