{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UM6J5SLRSYVFU3MVEQXTEPO4WI","short_pith_number":"pith:UM6J5SLR","schema_version":"1.0","canonical_sha256":"a33c9ec971962a5a6d95242f323ddcb203d46197df159e81c8246f9e324e0bb6","source":{"kind":"arxiv","id":"2405.16466","version":1},"attestation_state":"computed","paper":{"title":"High-Performance Temporal Reversible Spiking Neural Networks with $O(L)$ Training Memory and $O(1)$ Inference Cost","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Bo Xu, Guoqi Li, Jiakui Hu, Man Yao, Ning Qiao, Xuerui Qiu, Yonghong Tian, Yuhong Chou, Yuxuan Cai","submitted_at":"2024-05-26T07:26:56Z","abstract_excerpt":"Multi-timestep simulation of brain-inspired Spiking Neural Networks (SNNs) boost memory requirements during training and increase inference energy cost. Current training methods cannot simultaneously solve both training and inference dilemmas. This work proposes a novel Temporal Reversible architecture for SNNs (T-RevSNN) to jointly address the training and inference challenges by altering the forward propagation of SNNs. We turn off the temporal dynamics of most spiking neurons and design multi-level temporal reversible interactions at temporal turn-on spiking neurons, resulting in a $O(L)$ t"},"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":"2405.16466","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.NE","submitted_at":"2024-05-26T07:26:56Z","cross_cats_sorted":[],"title_canon_sha256":"db1d4542fb3ee7ef20e6adb03f230f5424e29f749f681a671704705a2b6b9204","abstract_canon_sha256":"7235a539c9bfbd0ca257545caa4020090a9fb8f71dab34703c12745f9f1f2ead"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:30.858903Z","signature_b64":"Un/fS2ga9+YHCbjPUtivBH4+swGUESpxSd68SlQagkxGpiit4pCGQEOHW/oy9/DKS57/VkJOPNym+LdZg6lSAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a33c9ec971962a5a6d95242f323ddcb203d46197df159e81c8246f9e324e0bb6","last_reissued_at":"2026-07-05T08:23:30.858350Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:30.858350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"High-Performance Temporal Reversible Spiking Neural Networks with $O(L)$ Training Memory and $O(1)$ Inference Cost","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.NE","authors_text":"Bo Xu, Guoqi Li, Jiakui Hu, Man Yao, Ning Qiao, Xuerui Qiu, Yonghong Tian, Yuhong Chou, Yuxuan Cai","submitted_at":"2024-05-26T07:26:56Z","abstract_excerpt":"Multi-timestep simulation of brain-inspired Spiking Neural Networks (SNNs) boost memory requirements during training and increase inference energy cost. Current training methods cannot simultaneously solve both training and inference dilemmas. This work proposes a novel Temporal Reversible architecture for SNNs (T-RevSNN) to jointly address the training and inference challenges by altering the forward propagation of SNNs. We turn off the temporal dynamics of most spiking neurons and design multi-level temporal reversible interactions at temporal turn-on spiking neurons, resulting in a $O(L)$ t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16466","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/2405.16466/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":"2405.16466","created_at":"2026-07-05T08:23:30.858427+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16466v1","created_at":"2026-07-05T08:23:30.858427+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16466","created_at":"2026-07-05T08:23:30.858427+00:00"},{"alias_kind":"pith_short_12","alias_value":"UM6J5SLRSYVF","created_at":"2026-07-05T08:23:30.858427+00:00"},{"alias_kind":"pith_short_16","alias_value":"UM6J5SLRSYVFU3MV","created_at":"2026-07-05T08:23:30.858427+00:00"},{"alias_kind":"pith_short_8","alias_value":"UM6J5SLR","created_at":"2026-07-05T08:23:30.858427+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.17674","citing_title":"SVL: Empowering Spiking Neural Networks for Efficient 3D Open-World Understanding","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16436","citing_title":"Fuzzy Encoding-Decoding to Improve Spiking Q-Learning Performance in Autonomous Driving","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UM6J5SLRSYVFU3MVEQXTEPO4WI","json":"https://pith.science/pith/UM6J5SLRSYVFU3MVEQXTEPO4WI.json","graph_json":"https://pith.science/api/pith-number/UM6J5SLRSYVFU3MVEQXTEPO4WI/graph.json","events_json":"https://pith.science/api/pith-number/UM6J5SLRSYVFU3MVEQXTEPO4WI/events.json","paper":"https://pith.science/paper/UM6J5SLR"},"agent_actions":{"view_html":"https://pith.science/pith/UM6J5SLRSYVFU3MVEQXTEPO4WI","download_json":"https://pith.science/pith/UM6J5SLRSYVFU3MVEQXTEPO4WI.json","view_paper":"https://pith.science/paper/UM6J5SLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16466&json=true","fetch_graph":"https://pith.science/api/pith-number/UM6J5SLRSYVFU3MVEQXTEPO4WI/graph.json","fetch_events":"https://pith.science/api/pith-number/UM6J5SLRSYVFU3MVEQXTEPO4WI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UM6J5SLRSYVFU3MVEQXTEPO4WI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UM6J5SLRSYVFU3MVEQXTEPO4WI/action/storage_attestation","attest_author":"https://pith.science/pith/UM6J5SLRSYVFU3MVEQXTEPO4WI/action/author_attestation","sign_citation":"https://pith.science/pith/UM6J5SLRSYVFU3MVEQXTEPO4WI/action/citation_signature","submit_replication":"https://pith.science/pith/UM6J5SLRSYVFU3MVEQXTEPO4WI/action/replication_record"}},"created_at":"2026-07-05T08:23:30.858427+00:00","updated_at":"2026-07-05T08:23:30.858427+00:00"}