{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:KMOP7GPZZZDED2HGH56BWDCSNH","short_pith_number":"pith:KMOP7GPZ","canonical_record":{"source":{"id":"1903.02083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-01-30T16:33:08Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"b5a6e1d0fdab0bc34a0ded406f3865421b91c16f0a43813d7e14115455698be7","abstract_canon_sha256":"7458ab7aa79a1272f2a2cb447f78e551cb6cf6b9dee91eada91fb2e283b6f3fb"},"schema_version":"1.0"},"canonical_sha256":"531cff99f9ce4641e8e63f7c1b0c5269f27b46ebbde92d19cab5a432aee7705b","source":{"kind":"arxiv","id":"1903.02083","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.02083","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.02083v2","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02083","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"KMOP7GPZZZDE","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KMOP7GPZZZDED2HG","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KMOP7GPZ","created_at":"2026-05-18T12:33:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:KMOP7GPZZZDED2HGH56BWDCSNH","target":"record","payload":{"canonical_record":{"source":{"id":"1903.02083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-01-30T16:33:08Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"b5a6e1d0fdab0bc34a0ded406f3865421b91c16f0a43813d7e14115455698be7","abstract_canon_sha256":"7458ab7aa79a1272f2a2cb447f78e551cb6cf6b9dee91eada91fb2e283b6f3fb"},"schema_version":"1.0"},"canonical_sha256":"531cff99f9ce4641e8e63f7c1b0c5269f27b46ebbde92d19cab5a432aee7705b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:46:40.982005Z","signature_b64":"xpvPOfJb+cQ8zMLx4BPLITF/O0I3dKDRIsBstu6MmS31AdEQF/aOUgTbbSyUKbQGW+o6DCNHrr2/0URW7NxtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"531cff99f9ce4641e8e63f7c1b0c5269f27b46ebbde92d19cab5a432aee7705b","last_reissued_at":"2026-05-17T23:46:40.981387Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:46:40.981387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.02083","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y3uaTigea8hjhB62nKF4XPLEXV+ymS5tnuJ+6oqcd5C6a+xxvaGHeXduyITxEAjb1btGXq+JpIQTvfrIsWK6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T13:16:42.204974Z"},"content_sha256":"045e78684d116aa575b39a61171347a47e60ab65e6699f3febe575809e1b9524","schema_version":"1.0","event_id":"sha256:045e78684d116aa575b39a61171347a47e60ab65e6699f3febe575809e1b9524"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:KMOP7GPZZZDED2HGH56BWDCSNH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Direct Feedback Alignment with Sparse Connections for Local Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Abhinav Parihar, Arijit Raychowdhury, Brian Crafton, Evan Gebhardt","submitted_at":"2019-01-30T16:33:08Z","abstract_excerpt":"Recent advances in deep neural networks (DNNs) owe their success to training algorithms that use backpropagation and gradient-descent. Backpropagation, while highly effective on von Neumann architectures, becomes inefficient when scaling to large networks. Commonly referred to as the weight transport problem, each neuron's dependence on the weights and errors located deeper in the network require exhaustive data movement which presents a key problem in enhancing the performance and energy-efficiency of machine-learning hardware. In this work, we propose a bio-plausible alternative to backpropa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02083","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:46:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PkDa0G9md30RNjl58OMmXrySN3uJUp+/Z6ADVPiA6XTUWMqsynRi+QuWEI7idZbt4t13mFDQhq4KJvhoQ/R7Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T13:16:42.205341Z"},"content_sha256":"e2afb19e1ff6bcb7c8fc3819da591bc78f660a421df5ac52f5e35da0fe0b48f9","schema_version":"1.0","event_id":"sha256:e2afb19e1ff6bcb7c8fc3819da591bc78f660a421df5ac52f5e35da0fe0b48f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KMOP7GPZZZDED2HGH56BWDCSNH/bundle.json","state_url":"https://pith.science/pith/KMOP7GPZZZDED2HGH56BWDCSNH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KMOP7GPZZZDED2HGH56BWDCSNH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-28T13:16:42Z","links":{"resolver":"https://pith.science/pith/KMOP7GPZZZDED2HGH56BWDCSNH","bundle":"https://pith.science/pith/KMOP7GPZZZDED2HGH56BWDCSNH/bundle.json","state":"https://pith.science/pith/KMOP7GPZZZDED2HGH56BWDCSNH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KMOP7GPZZZDED2HGH56BWDCSNH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:KMOP7GPZZZDED2HGH56BWDCSNH","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"7458ab7aa79a1272f2a2cb447f78e551cb6cf6b9dee91eada91fb2e283b6f3fb","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-01-30T16:33:08Z","title_canon_sha256":"b5a6e1d0fdab0bc34a0ded406f3865421b91c16f0a43813d7e14115455698be7"},"schema_version":"1.0","source":{"id":"1903.02083","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.02083","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"arxiv_version","alias_value":"1903.02083v2","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.02083","created_at":"2026-05-17T23:46:40Z"},{"alias_kind":"pith_short_12","alias_value":"KMOP7GPZZZDE","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_16","alias_value":"KMOP7GPZZZDED2HG","created_at":"2026-05-18T12:33:21Z"},{"alias_kind":"pith_short_8","alias_value":"KMOP7GPZ","created_at":"2026-05-18T12:33:21Z"}],"graph_snapshots":[{"event_id":"sha256:e2afb19e1ff6bcb7c8fc3819da591bc78f660a421df5ac52f5e35da0fe0b48f9","target":"graph","created_at":"2026-05-17T23:46:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"paper":{"abstract_excerpt":"Recent advances in deep neural networks (DNNs) owe their success to training algorithms that use backpropagation and gradient-descent. Backpropagation, while highly effective on von Neumann architectures, becomes inefficient when scaling to large networks. Commonly referred to as the weight transport problem, each neuron's dependence on the weights and errors located deeper in the network require exhaustive data movement which presents a key problem in enhancing the performance and energy-efficiency of machine-learning hardware. In this work, we propose a bio-plausible alternative to backpropa","authors_text":"Abhinav Parihar, Arijit Raychowdhury, Brian Crafton, Evan Gebhardt","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-01-30T16:33:08Z","title":"Direct Feedback Alignment with Sparse Connections for Local Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.02083","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:045e78684d116aa575b39a61171347a47e60ab65e6699f3febe575809e1b9524","target":"record","created_at":"2026-05-17T23:46:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"7458ab7aa79a1272f2a2cb447f78e551cb6cf6b9dee91eada91fb2e283b6f3fb","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2019-01-30T16:33:08Z","title_canon_sha256":"b5a6e1d0fdab0bc34a0ded406f3865421b91c16f0a43813d7e14115455698be7"},"schema_version":"1.0","source":{"id":"1903.02083","kind":"arxiv","version":2}},"canonical_sha256":"531cff99f9ce4641e8e63f7c1b0c5269f27b46ebbde92d19cab5a432aee7705b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"531cff99f9ce4641e8e63f7c1b0c5269f27b46ebbde92d19cab5a432aee7705b","first_computed_at":"2026-05-17T23:46:40.981387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:46:40.981387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xpvPOfJb+cQ8zMLx4BPLITF/O0I3dKDRIsBstu6MmS31AdEQF/aOUgTbbSyUKbQGW+o6DCNHrr2/0URW7NxtDA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:46:40.982005Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.02083","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:045e78684d116aa575b39a61171347a47e60ab65e6699f3febe575809e1b9524","sha256:e2afb19e1ff6bcb7c8fc3819da591bc78f660a421df5ac52f5e35da0fe0b48f9"],"state_sha256":"4437c31cca2e9a742c1557f4f9b04b671a3d5e39921b2de045fe9f16081c453d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qF3ijqI1IF2PDDl2o4ENmMH1i0GpMr07CoQTk28Yp1KLGA7CxZ5xpQ1D77QK5cuB18edR0a+rUti1WDcj8JTDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T13:16:42.207451Z","bundle_sha256":"fd0391c93c7f1a556e1a1b7d22011434922559ec29bf4d8afe3d515e0e6d52a0"}}