{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DGT3CIALS75DISZ456ATEJHLE3","short_pith_number":"pith:DGT3CIAL","schema_version":"1.0","canonical_sha256":"19a7b1200b97fa344b3cef813224eb26cdf590cdc248d071ae43148a2c1967bc","source":{"kind":"arxiv","id":"2409.07387","version":2},"attestation_state":"computed","paper":{"title":"A Contrastive Symmetric Forward-Forward Algorithm (SFFA) for Continual Learning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Erik B. Terres-Escudero, Javier Del Ser, Pablo Garcia Bringas","submitted_at":"2024-09-11T16:21:44Z","abstract_excerpt":"The so-called Forward-Forward Algorithm (FFA) has recently gained momentum as an alternative to the conventional back-propagation algorithm for neural network learning, yielding competitive performance across various modeling tasks. By replacing the backward pass of gradient back-propagation with two contrastive forward passes, the FFA avoids several shortcomings undergone by its predecessor (e.g., vanishing/exploding gradient) by enabling layer-wise training heuristics. In classification tasks, this contrastive method has been proven to effectively create a latent sparse representation of the"},"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":"2409.07387","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-09-11T16:21:44Z","cross_cats_sorted":[],"title_canon_sha256":"24b1bb146dca943b7c1c3effdc1709541a3c885fe0c5327303486503f0871c1d","abstract_canon_sha256":"99851075be8a8960f047eece49ad9ca7324f3491879027e9ecdb31dd5318e885"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:59.815150Z","signature_b64":"2VoPpmkCvYrYg49PcIEzIUFLO+3M7c05vsz1gGfcGHU/UPqKnEfShzZK+LE9yJrOfN8eqlcWm+MfOAE2NSWnCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19a7b1200b97fa344b3cef813224eb26cdf590cdc248d071ae43148a2c1967bc","last_reissued_at":"2026-07-05T09:58:59.814646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:59.814646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Contrastive Symmetric Forward-Forward Algorithm (SFFA) for Continual Learning Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Erik B. Terres-Escudero, Javier Del Ser, Pablo Garcia Bringas","submitted_at":"2024-09-11T16:21:44Z","abstract_excerpt":"The so-called Forward-Forward Algorithm (FFA) has recently gained momentum as an alternative to the conventional back-propagation algorithm for neural network learning, yielding competitive performance across various modeling tasks. By replacing the backward pass of gradient back-propagation with two contrastive forward passes, the FFA avoids several shortcomings undergone by its predecessor (e.g., vanishing/exploding gradient) by enabling layer-wise training heuristics. In classification tasks, this contrastive method has been proven to effectively create a latent sparse representation of the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07387","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/2409.07387/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":"2409.07387","created_at":"2026-07-05T09:58:59.814701+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07387v2","created_at":"2026-07-05T09:58:59.814701+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07387","created_at":"2026-07-05T09:58:59.814701+00:00"},{"alias_kind":"pith_short_12","alias_value":"DGT3CIALS75D","created_at":"2026-07-05T09:58:59.814701+00:00"},{"alias_kind":"pith_short_16","alias_value":"DGT3CIALS75DISZ4","created_at":"2026-07-05T09:58:59.814701+00:00"},{"alias_kind":"pith_short_8","alias_value":"DGT3CIAL","created_at":"2026-07-05T09:58:59.814701+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08697","citing_title":"Reshaping the Forward-Forward Algorithm with a Similarity-Based Objective","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DGT3CIALS75DISZ456ATEJHLE3","json":"https://pith.science/pith/DGT3CIALS75DISZ456ATEJHLE3.json","graph_json":"https://pith.science/api/pith-number/DGT3CIALS75DISZ456ATEJHLE3/graph.json","events_json":"https://pith.science/api/pith-number/DGT3CIALS75DISZ456ATEJHLE3/events.json","paper":"https://pith.science/paper/DGT3CIAL"},"agent_actions":{"view_html":"https://pith.science/pith/DGT3CIALS75DISZ456ATEJHLE3","download_json":"https://pith.science/pith/DGT3CIALS75DISZ456ATEJHLE3.json","view_paper":"https://pith.science/paper/DGT3CIAL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07387&json=true","fetch_graph":"https://pith.science/api/pith-number/DGT3CIALS75DISZ456ATEJHLE3/graph.json","fetch_events":"https://pith.science/api/pith-number/DGT3CIALS75DISZ456ATEJHLE3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DGT3CIALS75DISZ456ATEJHLE3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DGT3CIALS75DISZ456ATEJHLE3/action/storage_attestation","attest_author":"https://pith.science/pith/DGT3CIALS75DISZ456ATEJHLE3/action/author_attestation","sign_citation":"https://pith.science/pith/DGT3CIALS75DISZ456ATEJHLE3/action/citation_signature","submit_replication":"https://pith.science/pith/DGT3CIALS75DISZ456ATEJHLE3/action/replication_record"}},"created_at":"2026-07-05T09:58:59.814701+00:00","updated_at":"2026-07-05T09:58:59.814701+00:00"}