{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UYDPYLTC2RPIXRNWTX46VRJGAN","short_pith_number":"pith:UYDPYLTC","schema_version":"1.0","canonical_sha256":"a606fc2e62d45e8bc5b69df9eac526036a6a72bf4b1ae9264f07c234b7bdc13a","source":{"kind":"arxiv","id":"2303.09728","version":3},"attestation_state":"computed","paper":{"title":"The Cascaded Forward Algorithm for Neural Network Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congyan Lang, Gongpei Zhao, Haibin Ling, Tao Wang, Yidong Li, Yi Jin","submitted_at":"2023-03-17T02:01:11Z","abstract_excerpt":"Backpropagation algorithm has been widely used as a mainstream learning procedure for neural networks in the past decade, and has played a significant role in the development of deep learning. However, there exist some limitations associated with this algorithm, such as getting stuck in local minima and experiencing vanishing/exploding gradients, which have led to questions about its biological plausibility. To address these limitations, alternative algorithms to backpropagation have been preliminarily explored, with the Forward-Forward (FF) algorithm being one of the most well-known. In this "},"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":"2303.09728","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-17T02:01:11Z","cross_cats_sorted":[],"title_canon_sha256":"c4ce90021c2a27f1b16528d08eed110b3fde45db49ccbaa2670bdf45d5f4e0c8","abstract_canon_sha256":"35692f627536e8f6b5dbad846dfa4ffce73dc3e593b40f7c8382b2e08149d55f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:16.345826Z","signature_b64":"jM/rSpUtbijtCvxtwvkVUgG7mDueBhlTLAoX3srFiob5sUXa2hIWK2eM4okm/tluP95wDQuz1V05lqHiYThaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a606fc2e62d45e8bc5b69df9eac526036a6a72bf4b1ae9264f07c234b7bdc13a","last_reissued_at":"2026-07-05T07:22:16.341654Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:16.341654Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Cascaded Forward Algorithm for Neural Network Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Congyan Lang, Gongpei Zhao, Haibin Ling, Tao Wang, Yidong Li, Yi Jin","submitted_at":"2023-03-17T02:01:11Z","abstract_excerpt":"Backpropagation algorithm has been widely used as a mainstream learning procedure for neural networks in the past decade, and has played a significant role in the development of deep learning. However, there exist some limitations associated with this algorithm, such as getting stuck in local minima and experiencing vanishing/exploding gradients, which have led to questions about its biological plausibility. To address these limitations, alternative algorithms to backpropagation have been preliminarily explored, with the Forward-Forward (FF) algorithm being one of the most well-known. In this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09728","kind":"arxiv","version":3},"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/2303.09728/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":"2303.09728","created_at":"2026-07-05T07:22:16.342575+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09728v3","created_at":"2026-07-05T07:22:16.342575+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09728","created_at":"2026-07-05T07:22:16.342575+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYDPYLTC2RPI","created_at":"2026-07-05T07:22:16.342575+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYDPYLTC2RPIXRNW","created_at":"2026-07-05T07:22:16.342575+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYDPYLTC","created_at":"2026-07-05T07:22:16.342575+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21497","citing_title":"Breaking chains with trees: Deep learning with $\\mathcal{O}(\\log N)$ parallel time complexity","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UYDPYLTC2RPIXRNWTX46VRJGAN","json":"https://pith.science/pith/UYDPYLTC2RPIXRNWTX46VRJGAN.json","graph_json":"https://pith.science/api/pith-number/UYDPYLTC2RPIXRNWTX46VRJGAN/graph.json","events_json":"https://pith.science/api/pith-number/UYDPYLTC2RPIXRNWTX46VRJGAN/events.json","paper":"https://pith.science/paper/UYDPYLTC"},"agent_actions":{"view_html":"https://pith.science/pith/UYDPYLTC2RPIXRNWTX46VRJGAN","download_json":"https://pith.science/pith/UYDPYLTC2RPIXRNWTX46VRJGAN.json","view_paper":"https://pith.science/paper/UYDPYLTC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09728&json=true","fetch_graph":"https://pith.science/api/pith-number/UYDPYLTC2RPIXRNWTX46VRJGAN/graph.json","fetch_events":"https://pith.science/api/pith-number/UYDPYLTC2RPIXRNWTX46VRJGAN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYDPYLTC2RPIXRNWTX46VRJGAN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYDPYLTC2RPIXRNWTX46VRJGAN/action/storage_attestation","attest_author":"https://pith.science/pith/UYDPYLTC2RPIXRNWTX46VRJGAN/action/author_attestation","sign_citation":"https://pith.science/pith/UYDPYLTC2RPIXRNWTX46VRJGAN/action/citation_signature","submit_replication":"https://pith.science/pith/UYDPYLTC2RPIXRNWTX46VRJGAN/action/replication_record"}},"created_at":"2026-07-05T07:22:16.342575+00:00","updated_at":"2026-07-05T07:22:16.342575+00:00"}