{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q5MQFEPHWZSLE4PCMF3ZPNXUJO","short_pith_number":"pith:Q5MQFEPH","schema_version":"1.0","canonical_sha256":"87590291e7b664b271e2617797b6f44b8918b8b3eb519353a8b00f4aa9f74dcc","source":{"kind":"arxiv","id":"2502.20411","version":2},"attestation_state":"computed","paper":{"title":"Backpropagation-free Spiking Neural Networks with the Forward-Forward Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Bahar Farahani, Mahmood Fazlali, Mohammadnavid Ghader, Saeed Reza Kheradpisheh","submitted_at":"2025-02-19T12:44:26Z","abstract_excerpt":"Spiking Neural Networks (SNNs) offer a biologically inspired computational paradigm that emulates neuronal activity through discrete spike-based processing. Despite their advantages, training SNNs with traditional backpropagation (BP) remains challenging due to computational inefficiencies and a lack of biological plausibility. This study explores the Forward-Forward (FF) algorithm as an alternative learning framework for SNNs. Unlike backpropagation, which relies on forward and backward passes, the FF algorithm employs two forward passes, enabling layer-wise localized learning, enhanced compu"},"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":"2502.20411","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2025-02-19T12:44:26Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3b5263f0f9c414ad07240cd0deba499ce096f8c0b6a494a98582d34a32045d19","abstract_canon_sha256":"b3387dc0233afe5839959abf7408dddd6deffc9334c6f3c5e226b5dd6e6c9d74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:05.864070Z","signature_b64":"tPJ8cL9Devr5aVwRyMga4c9SYM20wQGfKmofd7lpr47IyuYYRDV9HLP4/H2MPc05HRJa2KLjKBW4yGqbc8KzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87590291e7b664b271e2617797b6f44b8918b8b3eb519353a8b00f4aa9f74dcc","last_reissued_at":"2026-07-05T11:10:05.863510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:05.863510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Backpropagation-free Spiking Neural Networks with the Forward-Forward Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.NE","authors_text":"Bahar Farahani, Mahmood Fazlali, Mohammadnavid Ghader, Saeed Reza Kheradpisheh","submitted_at":"2025-02-19T12:44:26Z","abstract_excerpt":"Spiking Neural Networks (SNNs) offer a biologically inspired computational paradigm that emulates neuronal activity through discrete spike-based processing. Despite their advantages, training SNNs with traditional backpropagation (BP) remains challenging due to computational inefficiencies and a lack of biological plausibility. This study explores the Forward-Forward (FF) algorithm as an alternative learning framework for SNNs. Unlike backpropagation, which relies on forward and backward passes, the FF algorithm employs two forward passes, enabling layer-wise localized learning, enhanced compu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20411","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/2502.20411/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":"2502.20411","created_at":"2026-07-05T11:10:05.863570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20411v2","created_at":"2026-07-05T11:10:05.863570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20411","created_at":"2026-07-05T11:10:05.863570+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5MQFEPHWZSL","created_at":"2026-07-05T11:10:05.863570+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5MQFEPHWZSLE4PC","created_at":"2026-07-05T11:10:05.863570+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5MQFEPH","created_at":"2026-07-05T11:10:05.863570+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.23643","citing_title":"FFGAF-SNN: The Forward-Forward Based Gradient Approximation Free Training Framework for Spiking Neural Networks","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5MQFEPHWZSLE4PCMF3ZPNXUJO","json":"https://pith.science/pith/Q5MQFEPHWZSLE4PCMF3ZPNXUJO.json","graph_json":"https://pith.science/api/pith-number/Q5MQFEPHWZSLE4PCMF3ZPNXUJO/graph.json","events_json":"https://pith.science/api/pith-number/Q5MQFEPHWZSLE4PCMF3ZPNXUJO/events.json","paper":"https://pith.science/paper/Q5MQFEPH"},"agent_actions":{"view_html":"https://pith.science/pith/Q5MQFEPHWZSLE4PCMF3ZPNXUJO","download_json":"https://pith.science/pith/Q5MQFEPHWZSLE4PCMF3ZPNXUJO.json","view_paper":"https://pith.science/paper/Q5MQFEPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20411&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5MQFEPHWZSLE4PCMF3ZPNXUJO/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5MQFEPHWZSLE4PCMF3ZPNXUJO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5MQFEPHWZSLE4PCMF3ZPNXUJO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5MQFEPHWZSLE4PCMF3ZPNXUJO/action/storage_attestation","attest_author":"https://pith.science/pith/Q5MQFEPHWZSLE4PCMF3ZPNXUJO/action/author_attestation","sign_citation":"https://pith.science/pith/Q5MQFEPHWZSLE4PCMF3ZPNXUJO/action/citation_signature","submit_replication":"https://pith.science/pith/Q5MQFEPHWZSLE4PCMF3ZPNXUJO/action/replication_record"}},"created_at":"2026-07-05T11:10:05.863570+00:00","updated_at":"2026-07-05T11:10:05.863570+00:00"}