{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MRL6JZFVGNOW24SOSA333LQEMK","short_pith_number":"pith:MRL6JZFV","schema_version":"1.0","canonical_sha256":"6457e4e4b5335d6d724e9037bdae046281ba2dfa0bda977f74c8d886d8603d18","source":{"kind":"arxiv","id":"2106.06044","version":3},"attestation_state":"computed","paper":{"title":"Convergence and Alignment of Gradient Descent with Random Backpropagation Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ganlin Song, John Lafferty, Ruitu Xu","submitted_at":"2021-06-10T20:58:05Z","abstract_excerpt":"Stochastic gradient descent with backpropagation is the workhorse of artificial neural networks. It has long been recognized that backpropagation fails to be a biologically plausible algorithm. Fundamentally, it is a non-local procedure -- updating one neuron's synaptic weights requires knowledge of synaptic weights or receptive fields of downstream neurons. This limits the use of artificial neural networks as a tool for understanding the biological principles of information processing in the brain. Lillicrap et al. (2016) propose a more biologically plausible \"feedback alignment\" algorithm th"},"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":"2106.06044","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-06-10T20:58:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c8140997e8646a7843da068d9f5cbf78a25d974688eb9a1555838486e391077f","abstract_canon_sha256":"67de5b4f6068493b3db6d977d93dfc2bff73bc1c4cb17a9768cdc4773c52d5f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:43:16.638459Z","signature_b64":"QS9kZW5h0WXVEITBfwjJ5gM+wBOoYdla9jTUdvJbdZvZbjtMN0gLbVHtq6sxV0vF3vVZv0QXwpwWfzYfB9g/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6457e4e4b5335d6d724e9037bdae046281ba2dfa0bda977f74c8d886d8603d18","last_reissued_at":"2026-07-05T03:43:16.637983Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:43:16.637983Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence and Alignment of Gradient Descent with Random Backpropagation Weights","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Ganlin Song, John Lafferty, Ruitu Xu","submitted_at":"2021-06-10T20:58:05Z","abstract_excerpt":"Stochastic gradient descent with backpropagation is the workhorse of artificial neural networks. It has long been recognized that backpropagation fails to be a biologically plausible algorithm. Fundamentally, it is a non-local procedure -- updating one neuron's synaptic weights requires knowledge of synaptic weights or receptive fields of downstream neurons. This limits the use of artificial neural networks as a tool for understanding the biological principles of information processing in the brain. Lillicrap et al. (2016) propose a more biologically plausible \"feedback alignment\" algorithm th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.06044","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/2106.06044/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":"2106.06044","created_at":"2026-07-05T03:43:16.638054+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.06044v3","created_at":"2026-07-05T03:43:16.638054+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.06044","created_at":"2026-07-05T03:43:16.638054+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRL6JZFVGNOW","created_at":"2026-07-05T03:43:16.638054+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRL6JZFVGNOW24SO","created_at":"2026-07-05T03:43:16.638054+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRL6JZFV","created_at":"2026-07-05T03:43:16.638054+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.29528","citing_title":"Supervised Hebbian learning in Deep Counterstream Associative Networks","ref_index":92,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRL6JZFVGNOW24SOSA333LQEMK","json":"https://pith.science/pith/MRL6JZFVGNOW24SOSA333LQEMK.json","graph_json":"https://pith.science/api/pith-number/MRL6JZFVGNOW24SOSA333LQEMK/graph.json","events_json":"https://pith.science/api/pith-number/MRL6JZFVGNOW24SOSA333LQEMK/events.json","paper":"https://pith.science/paper/MRL6JZFV"},"agent_actions":{"view_html":"https://pith.science/pith/MRL6JZFVGNOW24SOSA333LQEMK","download_json":"https://pith.science/pith/MRL6JZFVGNOW24SOSA333LQEMK.json","view_paper":"https://pith.science/paper/MRL6JZFV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.06044&json=true","fetch_graph":"https://pith.science/api/pith-number/MRL6JZFVGNOW24SOSA333LQEMK/graph.json","fetch_events":"https://pith.science/api/pith-number/MRL6JZFVGNOW24SOSA333LQEMK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRL6JZFVGNOW24SOSA333LQEMK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRL6JZFVGNOW24SOSA333LQEMK/action/storage_attestation","attest_author":"https://pith.science/pith/MRL6JZFVGNOW24SOSA333LQEMK/action/author_attestation","sign_citation":"https://pith.science/pith/MRL6JZFVGNOW24SOSA333LQEMK/action/citation_signature","submit_replication":"https://pith.science/pith/MRL6JZFVGNOW24SOSA333LQEMK/action/replication_record"}},"created_at":"2026-07-05T03:43:16.638054+00:00","updated_at":"2026-07-05T03:43:16.638054+00:00"}