{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:JZ43ZQMXXKFMIGYHE43TY2WLB4","short_pith_number":"pith:JZ43ZQMX","schema_version":"1.0","canonical_sha256":"4e79bcc197ba8ac41b0727373c6acb0f2cfaee8c8c38dd5ffe3b13672266b096","source":{"kind":"arxiv","id":"1906.04554","version":1},"attestation_state":"computed","paper":{"title":"Principled Training of Neural Networks with Direct Feedback Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Florent Krzakala, Iacopo Poli, Julien Launay","submitted_at":"2019-06-11T13:08:19Z","abstract_excerpt":"The backpropagation algorithm has long been the canonical training method for neural networks. Modern paradigms are implicitly optimized for it, and numerous guidelines exist to ensure its proper use. Recently, synthetic gradients methods -where the error gradient is only roughly approximated - have garnered interest. These methods not only better portray how biological brains are learning, but also open new computational possibilities, such as updating layers asynchronously. Even so, they have failed to scale past simple tasks like MNIST or CIFAR-10. This is in part due to a lack of standards"},"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":"1906.04554","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2019-06-11T13:08:19Z","cross_cats_sorted":["cs.LG","cs.NE"],"title_canon_sha256":"ec1212b74552dba56c1c99823c1680fa30fed6b8db7013cb3491456f6658a250","abstract_canon_sha256":"f1b85e2043e34f4c2138acdde5477abd5243e58004b6871bea73d431541392b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:38.915473Z","signature_b64":"EL/ZyLRytvvn+08clqard5MgLTNisnjt/lsHfkmKocabr/VYftNZIXOu4YUpahvRA+WgDPSTLt8wewmbps5NAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e79bcc197ba8ac41b0727373c6acb0f2cfaee8c8c38dd5ffe3b13672266b096","last_reissued_at":"2026-05-17T23:43:38.914739Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:38.914739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Principled Training of Neural Networks with Direct Feedback Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE"],"primary_cat":"stat.ML","authors_text":"Florent Krzakala, Iacopo Poli, Julien Launay","submitted_at":"2019-06-11T13:08:19Z","abstract_excerpt":"The backpropagation algorithm has long been the canonical training method for neural networks. Modern paradigms are implicitly optimized for it, and numerous guidelines exist to ensure its proper use. Recently, synthetic gradients methods -where the error gradient is only roughly approximated - have garnered interest. These methods not only better portray how biological brains are learning, but also open new computational possibilities, such as updating layers asynchronously. Even so, they have failed to scale past simple tasks like MNIST or CIFAR-10. This is in part due to a lack of standards"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04554","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":""},"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":"1906.04554","created_at":"2026-05-17T23:43:38.914851+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.04554v1","created_at":"2026-05-17T23:43:38.914851+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04554","created_at":"2026-05-17T23:43:38.914851+00:00"},{"alias_kind":"pith_short_12","alias_value":"JZ43ZQMXXKFM","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"JZ43ZQMXXKFMIGYH","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"JZ43ZQMX","created_at":"2026-05-18T12:33:21.387695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.09238","citing_title":"Mono-Forward: Revisiting Forward-Forward through Objective-Locality Decomposition","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JZ43ZQMXXKFMIGYHE43TY2WLB4","json":"https://pith.science/pith/JZ43ZQMXXKFMIGYHE43TY2WLB4.json","graph_json":"https://pith.science/api/pith-number/JZ43ZQMXXKFMIGYHE43TY2WLB4/graph.json","events_json":"https://pith.science/api/pith-number/JZ43ZQMXXKFMIGYHE43TY2WLB4/events.json","paper":"https://pith.science/paper/JZ43ZQMX"},"agent_actions":{"view_html":"https://pith.science/pith/JZ43ZQMXXKFMIGYHE43TY2WLB4","download_json":"https://pith.science/pith/JZ43ZQMXXKFMIGYHE43TY2WLB4.json","view_paper":"https://pith.science/paper/JZ43ZQMX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.04554&json=true","fetch_graph":"https://pith.science/api/pith-number/JZ43ZQMXXKFMIGYHE43TY2WLB4/graph.json","fetch_events":"https://pith.science/api/pith-number/JZ43ZQMXXKFMIGYHE43TY2WLB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JZ43ZQMXXKFMIGYHE43TY2WLB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JZ43ZQMXXKFMIGYHE43TY2WLB4/action/storage_attestation","attest_author":"https://pith.science/pith/JZ43ZQMXXKFMIGYHE43TY2WLB4/action/author_attestation","sign_citation":"https://pith.science/pith/JZ43ZQMXXKFMIGYHE43TY2WLB4/action/citation_signature","submit_replication":"https://pith.science/pith/JZ43ZQMXXKFMIGYHE43TY2WLB4/action/replication_record"}},"created_at":"2026-05-17T23:43:38.914851+00:00","updated_at":"2026-05-17T23:43:38.914851+00:00"}