{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NWBWX34UORWM3NYIC6AAJM2OAG","short_pith_number":"pith:NWBWX34U","schema_version":"1.0","canonical_sha256":"6d836bef94746ccdb708178004b34e0192eca08be052a2ffc9bb41c4489abf69","source":{"kind":"arxiv","id":"2507.23643","version":2},"attestation_state":"computed","paper":{"title":"FFGAF-SNN: The Forward-Forward Based Gradient Approximation Free Training Framework for Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqing Xu, Guiqi Mo, Hao Zeng, XinFang Liao, Yi Liu, Yintang Yang, Ziqiang Yang","submitted_at":"2025-07-31T15:22:23Z","abstract_excerpt":"Spiking Neural Networks (SNNs) offer a biologically plausible framework for energy-efficient neuromorphic computing. However, it is a challenge to train SNNs due to their non-differentiability, efficiently. Existing gradient approximation approaches frequently sacrifice accuracy and face deployment limitations on edge devices due to the substantial computational requirements of backpropagation. To address these challenges, we propose a Forward-Forward (FF) based gradient approximation-free training framework for Spiking Neural Networks, which treats spiking activations as black-box modules, th"},"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":"2507.23643","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-31T15:22:23Z","cross_cats_sorted":[],"title_canon_sha256":"f2352653e2cf77b95b6fbff31cf92a3612b3840a3336dd24946ce3f4cf68cd18","abstract_canon_sha256":"331a9e2180efe3d0ce1bf146e4b92b6034551511a01d2cf09dde83bd3a342fae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:47.170481Z","signature_b64":"A/ccmbys9kixJ71CX9A5w0TAvZePa/5sh0EFn9lxntTY7BGDD6Sdsoid/4RBCSVAoM6AXpBcK7K+12Ba5eE1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d836bef94746ccdb708178004b34e0192eca08be052a2ffc9bb41c4489abf69","last_reissued_at":"2026-07-05T11:46:47.169982Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:47.169982Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FFGAF-SNN: The Forward-Forward Based Gradient Approximation Free Training Framework for Spiking Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changqing Xu, Guiqi Mo, Hao Zeng, XinFang Liao, Yi Liu, Yintang Yang, Ziqiang Yang","submitted_at":"2025-07-31T15:22:23Z","abstract_excerpt":"Spiking Neural Networks (SNNs) offer a biologically plausible framework for energy-efficient neuromorphic computing. However, it is a challenge to train SNNs due to their non-differentiability, efficiently. Existing gradient approximation approaches frequently sacrifice accuracy and face deployment limitations on edge devices due to the substantial computational requirements of backpropagation. To address these challenges, we propose a Forward-Forward (FF) based gradient approximation-free training framework for Spiking Neural Networks, which treats spiking activations as black-box modules, th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23643","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/2507.23643/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":"2507.23643","created_at":"2026-07-05T11:46:47.170043+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.23643v2","created_at":"2026-07-05T11:46:47.170043+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23643","created_at":"2026-07-05T11:46:47.170043+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWBWX34UORWM","created_at":"2026-07-05T11:46:47.170043+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWBWX34UORWM3NYI","created_at":"2026-07-05T11:46:47.170043+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWBWX34U","created_at":"2026-07-05T11:46:47.170043+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NWBWX34UORWM3NYIC6AAJM2OAG","json":"https://pith.science/pith/NWBWX34UORWM3NYIC6AAJM2OAG.json","graph_json":"https://pith.science/api/pith-number/NWBWX34UORWM3NYIC6AAJM2OAG/graph.json","events_json":"https://pith.science/api/pith-number/NWBWX34UORWM3NYIC6AAJM2OAG/events.json","paper":"https://pith.science/paper/NWBWX34U"},"agent_actions":{"view_html":"https://pith.science/pith/NWBWX34UORWM3NYIC6AAJM2OAG","download_json":"https://pith.science/pith/NWBWX34UORWM3NYIC6AAJM2OAG.json","view_paper":"https://pith.science/paper/NWBWX34U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.23643&json=true","fetch_graph":"https://pith.science/api/pith-number/NWBWX34UORWM3NYIC6AAJM2OAG/graph.json","fetch_events":"https://pith.science/api/pith-number/NWBWX34UORWM3NYIC6AAJM2OAG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWBWX34UORWM3NYIC6AAJM2OAG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWBWX34UORWM3NYIC6AAJM2OAG/action/storage_attestation","attest_author":"https://pith.science/pith/NWBWX34UORWM3NYIC6AAJM2OAG/action/author_attestation","sign_citation":"https://pith.science/pith/NWBWX34UORWM3NYIC6AAJM2OAG/action/citation_signature","submit_replication":"https://pith.science/pith/NWBWX34UORWM3NYIC6AAJM2OAG/action/replication_record"}},"created_at":"2026-07-05T11:46:47.170043+00:00","updated_at":"2026-07-05T11:46:47.170043+00:00"}