{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HECQ2P45ELRAAFZLGVIK3IZYC3","short_pith_number":"pith:HECQ2P45","schema_version":"1.0","canonical_sha256":"39050d3f9d22e200172b3550ada33816d690a25f7bc271442743f8a94ac4d367","source":{"kind":"arxiv","id":"2504.21662","version":2},"attestation_state":"computed","paper":{"title":"On Advancements of the Forward-Forward Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arne P. Raulf, Markus Lange, Mauricio Ortiz Torres","submitted_at":"2025-04-30T14:03:52Z","abstract_excerpt":"The Forward-Forward algorithm has evolved in machine learning research, tackling more complex tasks that mimic real-life applications. In the last years, it has been improved by several techniques to perform better than its original version, handling a challenging dataset like CIFAR10 without losing its flexibility and low memory usage. We have shown in our results that improvements are achieved through a combination of convolutional channel grouping, learning rate schedules, and independent block structures during training that lead to a 20\\% decrease in test error percentage. Additionally, 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":"2504.21662","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-30T14:03:52Z","cross_cats_sorted":[],"title_canon_sha256":"f73e09822bebe55eebd981c122afbf9d0dc256b926640791076120a18ee7fbeb","abstract_canon_sha256":"f9395331247fc2ea0e1cdeed80f5926cce8580b7704660350ce81452a81738bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:26:50.711838Z","signature_b64":"AQ0AwDUGx8DBJJ2btnmVfCaFr34pdcNkgTo06XPLi4pK4XsfysclXryPWACyhEb8YkwbTnI6MHO9EegXXTyCDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39050d3f9d22e200172b3550ada33816d690a25f7bc271442743f8a94ac4d367","last_reissued_at":"2026-07-05T11:26:50.707694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:26:50.707694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On Advancements of the Forward-Forward Algorithm","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arne P. Raulf, Markus Lange, Mauricio Ortiz Torres","submitted_at":"2025-04-30T14:03:52Z","abstract_excerpt":"The Forward-Forward algorithm has evolved in machine learning research, tackling more complex tasks that mimic real-life applications. In the last years, it has been improved by several techniques to perform better than its original version, handling a challenging dataset like CIFAR10 without losing its flexibility and low memory usage. We have shown in our results that improvements are achieved through a combination of convolutional channel grouping, learning rate schedules, and independent block structures during training that lead to a 20\\% decrease in test error percentage. Additionally, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21662","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/2504.21662/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":"2504.21662","created_at":"2026-07-05T11:26:50.707799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21662v2","created_at":"2026-07-05T11:26:50.707799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21662","created_at":"2026-07-05T11:26:50.707799+00:00"},{"alias_kind":"pith_short_12","alias_value":"HECQ2P45ELRA","created_at":"2026-07-05T11:26:50.707799+00:00"},{"alias_kind":"pith_short_16","alias_value":"HECQ2P45ELRAAFZL","created_at":"2026-07-05T11:26:50.707799+00:00"},{"alias_kind":"pith_short_8","alias_value":"HECQ2P45","created_at":"2026-07-05T11:26:50.707799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.12406","citing_title":"LightTune: Lightweight Forward-Only Online Fine-Tuning with Applications to Link Adaptation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01928","citing_title":"Training Non-Differentiable Networks via Optimal Transport","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12406","citing_title":"LightTune: Lightweight Forward-Only Online Fine-Tuning with Applications to Link Adaptation","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HECQ2P45ELRAAFZLGVIK3IZYC3","json":"https://pith.science/pith/HECQ2P45ELRAAFZLGVIK3IZYC3.json","graph_json":"https://pith.science/api/pith-number/HECQ2P45ELRAAFZLGVIK3IZYC3/graph.json","events_json":"https://pith.science/api/pith-number/HECQ2P45ELRAAFZLGVIK3IZYC3/events.json","paper":"https://pith.science/paper/HECQ2P45"},"agent_actions":{"view_html":"https://pith.science/pith/HECQ2P45ELRAAFZLGVIK3IZYC3","download_json":"https://pith.science/pith/HECQ2P45ELRAAFZLGVIK3IZYC3.json","view_paper":"https://pith.science/paper/HECQ2P45","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21662&json=true","fetch_graph":"https://pith.science/api/pith-number/HECQ2P45ELRAAFZLGVIK3IZYC3/graph.json","fetch_events":"https://pith.science/api/pith-number/HECQ2P45ELRAAFZLGVIK3IZYC3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HECQ2P45ELRAAFZLGVIK3IZYC3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HECQ2P45ELRAAFZLGVIK3IZYC3/action/storage_attestation","attest_author":"https://pith.science/pith/HECQ2P45ELRAAFZLGVIK3IZYC3/action/author_attestation","sign_citation":"https://pith.science/pith/HECQ2P45ELRAAFZLGVIK3IZYC3/action/citation_signature","submit_replication":"https://pith.science/pith/HECQ2P45ELRAAFZLGVIK3IZYC3/action/replication_record"}},"created_at":"2026-07-05T11:26:50.707799+00:00","updated_at":"2026-07-05T11:26:50.707799+00:00"}