{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:TSCMCEIAV4FQCFXR63R42K6IJI","short_pith_number":"pith:TSCMCEIA","schema_version":"1.0","canonical_sha256":"9c84c11100af0b0116f1f6e3cd2bc84a3d50bb833b07ea9b7737545c5325b70d","source":{"kind":"arxiv","id":"1812.06488","version":2},"attestation_state":"computed","paper":{"title":"Feedback alignment in deep convolutional networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Ashok Litwin-Kumar, L.F. Abbott, Theodore H. Moskovitz","submitted_at":"2018-12-12T22:12:53Z","abstract_excerpt":"Ongoing studies have identified similarities between neural representations in biological networks and in deep artificial neural networks. This has led to renewed interest in developing analogies between the backpropagation learning algorithm used to train artificial networks and the synaptic plasticity rules operative in the brain. These efforts are challenged by biologically implausible features of backpropagation, one of which is a reliance on symmetric forward and backward synaptic weights. A number of methods have been proposed that do not rely on weight symmetry but, thus far, these have"},"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":"1812.06488","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.NE","submitted_at":"2018-12-12T22:12:53Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"07cde85279c96aa5cae44f8f4c132e4a280aa2b75721ebc55913c15696ffc8a1","abstract_canon_sha256":"3f060b876c92d5cbf35a3d0061b3b9bc0e29f44dbe75f337740f833d43c7081c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:50.288434Z","signature_b64":"xDWClhTuMrXzIBI07mYCb5dNpHbBZpcdzupbCkp2F/WMH7b2BlbS41FuJNW9irMa3uht5TiD+ftmW+NN5vAXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9c84c11100af0b0116f1f6e3cd2bc84a3d50bb833b07ea9b7737545c5325b70d","last_reissued_at":"2026-05-17T23:43:50.287529Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:50.287529Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feedback alignment in deep convolutional networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Ashok Litwin-Kumar, L.F. Abbott, Theodore H. Moskovitz","submitted_at":"2018-12-12T22:12:53Z","abstract_excerpt":"Ongoing studies have identified similarities between neural representations in biological networks and in deep artificial neural networks. This has led to renewed interest in developing analogies between the backpropagation learning algorithm used to train artificial networks and the synaptic plasticity rules operative in the brain. These efforts are challenged by biologically implausible features of backpropagation, one of which is a reliance on symmetric forward and backward synaptic weights. A number of methods have been proposed that do not rely on weight symmetry but, thus far, these have"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.06488","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":""},"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":"1812.06488","created_at":"2026-05-17T23:43:50.287667+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.06488v2","created_at":"2026-05-17T23:43:50.287667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.06488","created_at":"2026-05-17T23:43:50.287667+00:00"},{"alias_kind":"pith_short_12","alias_value":"TSCMCEIAV4FQ","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_16","alias_value":"TSCMCEIAV4FQCFXR","created_at":"2026-05-18T12:32:56.356000+00:00"},{"alias_kind":"pith_short_8","alias_value":"TSCMCEIA","created_at":"2026-05-18T12:32:56.356000+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2503.02642","citing_title":"Spike-based alignment learning solves the weight transport problem","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2505.13741","citing_title":"Frozen Backpropagation: Relaxing Weight Symmetry in Deep Spiking Neural Networks","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08564","citing_title":"Biological Plausibility and Representational Alignment of Feedback Alignment in Convolutional Networks","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TSCMCEIAV4FQCFXR63R42K6IJI","json":"https://pith.science/pith/TSCMCEIAV4FQCFXR63R42K6IJI.json","graph_json":"https://pith.science/api/pith-number/TSCMCEIAV4FQCFXR63R42K6IJI/graph.json","events_json":"https://pith.science/api/pith-number/TSCMCEIAV4FQCFXR63R42K6IJI/events.json","paper":"https://pith.science/paper/TSCMCEIA"},"agent_actions":{"view_html":"https://pith.science/pith/TSCMCEIAV4FQCFXR63R42K6IJI","download_json":"https://pith.science/pith/TSCMCEIAV4FQCFXR63R42K6IJI.json","view_paper":"https://pith.science/paper/TSCMCEIA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.06488&json=true","fetch_graph":"https://pith.science/api/pith-number/TSCMCEIAV4FQCFXR63R42K6IJI/graph.json","fetch_events":"https://pith.science/api/pith-number/TSCMCEIAV4FQCFXR63R42K6IJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TSCMCEIAV4FQCFXR63R42K6IJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TSCMCEIAV4FQCFXR63R42K6IJI/action/storage_attestation","attest_author":"https://pith.science/pith/TSCMCEIAV4FQCFXR63R42K6IJI/action/author_attestation","sign_citation":"https://pith.science/pith/TSCMCEIAV4FQCFXR63R42K6IJI/action/citation_signature","submit_replication":"https://pith.science/pith/TSCMCEIAV4FQCFXR63R42K6IJI/action/replication_record"}},"created_at":"2026-05-17T23:43:50.287667+00:00","updated_at":"2026-05-17T23:43:50.287667+00:00"}