{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IFE7ZSCIHQUMZFXROZFSADIEG3","short_pith_number":"pith:IFE7ZSCI","schema_version":"1.0","canonical_sha256":"4149fcc8483c28cc96f1764b200d0436d35f459a99829def9395a05b08a66595","source":{"kind":"arxiv","id":"2408.14925","version":1},"attestation_state":"computed","paper":{"title":"Distance-Forward Learning: Enhancing the Forward-Forward Algorithm Towards High-Performance On-Chip Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Guoqi Li, Jibin Wu, Lei Deng, Mingkun Xu, Qinghao Wen, Siyuan Xu, Yujie Wu","submitted_at":"2024-08-27T10:01:43Z","abstract_excerpt":"The Forward-Forward (FF) algorithm was recently proposed as a local learning method to address the limitations of backpropagation (BP), offering biological plausibility along with memory-efficient and highly parallelized computational benefits. However, it suffers from suboptimal performance and poor generalization, largely due to inadequate theoretical support and a lack of effective learning strategies. In this work, we reformulate FF using distance metric learning and propose a distance-forward algorithm (DF) to improve FF performance in supervised vision tasks while preserving its local co"},"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":"2408.14925","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.NE","submitted_at":"2024-08-27T10:01:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e74529d4c7c9a2d1037c5a88318481ae4bb807ab92e726e63daa2b4f307bca8c","abstract_canon_sha256":"3d73a72423139328b51648a32ad676968b7644e30d07d4dfb17d4bf2dc76e78a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:59:40.863816Z","signature_b64":"gI2SpQw/mdP1WjRMtPM7jflL/nkaXU+fF3wUdGKcx8DC7Ok1p41K53QDMz1r8Qd8x+H3Y4NublzhXbTELw/eAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4149fcc8483c28cc96f1764b200d0436d35f459a99829def9395a05b08a66595","last_reissued_at":"2026-07-05T08:59:40.863417Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:59:40.863417Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distance-Forward Learning: Enhancing the Forward-Forward Algorithm Towards High-Performance On-Chip Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.NE","authors_text":"Guoqi Li, Jibin Wu, Lei Deng, Mingkun Xu, Qinghao Wen, Siyuan Xu, Yujie Wu","submitted_at":"2024-08-27T10:01:43Z","abstract_excerpt":"The Forward-Forward (FF) algorithm was recently proposed as a local learning method to address the limitations of backpropagation (BP), offering biological plausibility along with memory-efficient and highly parallelized computational benefits. However, it suffers from suboptimal performance and poor generalization, largely due to inadequate theoretical support and a lack of effective learning strategies. In this work, we reformulate FF using distance metric learning and propose a distance-forward algorithm (DF) to improve FF performance in supervised vision tasks while preserving its local co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14925","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/2408.14925/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":"2408.14925","created_at":"2026-07-05T08:59:40.863474+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14925v1","created_at":"2026-07-05T08:59:40.863474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14925","created_at":"2026-07-05T08:59:40.863474+00:00"},{"alias_kind":"pith_short_12","alias_value":"IFE7ZSCIHQUM","created_at":"2026-07-05T08:59:40.863474+00:00"},{"alias_kind":"pith_short_16","alias_value":"IFE7ZSCIHQUMZFXR","created_at":"2026-07-05T08:59:40.863474+00:00"},{"alias_kind":"pith_short_8","alias_value":"IFE7ZSCI","created_at":"2026-07-05T08:59:40.863474+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06240","citing_title":"Cumulative-Goodness Free-Riding in Forward-Forward Networks: Real, Repairable, but Not Accuracy-Dominant","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IFE7ZSCIHQUMZFXROZFSADIEG3","json":"https://pith.science/pith/IFE7ZSCIHQUMZFXROZFSADIEG3.json","graph_json":"https://pith.science/api/pith-number/IFE7ZSCIHQUMZFXROZFSADIEG3/graph.json","events_json":"https://pith.science/api/pith-number/IFE7ZSCIHQUMZFXROZFSADIEG3/events.json","paper":"https://pith.science/paper/IFE7ZSCI"},"agent_actions":{"view_html":"https://pith.science/pith/IFE7ZSCIHQUMZFXROZFSADIEG3","download_json":"https://pith.science/pith/IFE7ZSCIHQUMZFXROZFSADIEG3.json","view_paper":"https://pith.science/paper/IFE7ZSCI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14925&json=true","fetch_graph":"https://pith.science/api/pith-number/IFE7ZSCIHQUMZFXROZFSADIEG3/graph.json","fetch_events":"https://pith.science/api/pith-number/IFE7ZSCIHQUMZFXROZFSADIEG3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IFE7ZSCIHQUMZFXROZFSADIEG3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IFE7ZSCIHQUMZFXROZFSADIEG3/action/storage_attestation","attest_author":"https://pith.science/pith/IFE7ZSCIHQUMZFXROZFSADIEG3/action/author_attestation","sign_citation":"https://pith.science/pith/IFE7ZSCIHQUMZFXROZFSADIEG3/action/citation_signature","submit_replication":"https://pith.science/pith/IFE7ZSCIHQUMZFXROZFSADIEG3/action/replication_record"}},"created_at":"2026-07-05T08:59:40.863474+00:00","updated_at":"2026-07-05T08:59:40.863474+00:00"}