{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EBNC5T5CEE2PG3IBIAF4K42K4A","short_pith_number":"pith:EBNC5T5C","schema_version":"1.0","canonical_sha256":"205a2ecfa22134f36d01400bc5734ae0134c081515e7b5251113fa1b4eabe5b1","source":{"kind":"arxiv","id":"2309.02214","version":2},"attestation_state":"computed","paper":{"title":"Improving equilibrium propagation without weight symmetry through Jacobian homeostasis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Axel Laborieux, Friedemann Zenke","submitted_at":"2023-09-05T13:20:43Z","abstract_excerpt":"Equilibrium propagation (EP) is a compelling alternative to the backpropagation of error algorithm (BP) for computing gradients of neural networks on biological or analog neuromorphic substrates. Still, the algorithm requires weight symmetry and infinitesimal equilibrium perturbations, i.e., nudges, to estimate unbiased gradients efficiently. Both requirements are challenging to implement in physical systems. Yet, whether and how weight asymmetry affects its applicability is unknown because, in practice, it may be masked by biases introduced through the finite nudge. To address this question, "},"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":"2309.02214","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-05T13:20:43Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"46de727a7d32a9f667596f64a2ddeab5f5982cb65b14274772e5a2d6f4f5b7ad","abstract_canon_sha256":"a4f7eb12f73b49bcc598544c1caf646f436f0a4a328a3ca056d2871fcec4a111"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:05:01.719967Z","signature_b64":"v/s28Wj61Xly8fx1NnB72ic3L1fqPI0+Tz1xAHJCtMol/3MMn8Nk/DJF6icLn9A1EB5eti4bnE6ZqF2VMvlcAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"205a2ecfa22134f36d01400bc5734ae0134c081515e7b5251113fa1b4eabe5b1","last_reissued_at":"2026-07-05T08:05:01.719503Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:05:01.719503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving equilibrium propagation without weight symmetry through Jacobian homeostasis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Axel Laborieux, Friedemann Zenke","submitted_at":"2023-09-05T13:20:43Z","abstract_excerpt":"Equilibrium propagation (EP) is a compelling alternative to the backpropagation of error algorithm (BP) for computing gradients of neural networks on biological or analog neuromorphic substrates. Still, the algorithm requires weight symmetry and infinitesimal equilibrium perturbations, i.e., nudges, to estimate unbiased gradients efficiently. Both requirements are challenging to implement in physical systems. Yet, whether and how weight asymmetry affects its applicability is unknown because, in practice, it may be masked by biases introduced through the finite nudge. To address this question, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02214","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2309.02214/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":"2309.02214","created_at":"2026-07-05T08:05:01.719557+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.02214v2","created_at":"2026-07-05T08:05:01.719557+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02214","created_at":"2026-07-05T08:05:01.719557+00:00"},{"alias_kind":"pith_short_12","alias_value":"EBNC5T5CEE2P","created_at":"2026-07-05T08:05:01.719557+00:00"},{"alias_kind":"pith_short_16","alias_value":"EBNC5T5CEE2PG3IB","created_at":"2026-07-05T08:05:01.719557+00:00"},{"alias_kind":"pith_short_8","alias_value":"EBNC5T5C","created_at":"2026-07-05T08:05:01.719557+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.09595","citing_title":"Neuromorphic Reinforcement Learning for Quadruped Locomotion Control on Uneven Terrain","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09595","citing_title":"Neuromorphic Reinforcement Learning for Quadruped Locomotion Control on Uneven Terrain","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/EBNC5T5CEE2PG3IBIAF4K42K4A","json":"https://pith.science/pith/EBNC5T5CEE2PG3IBIAF4K42K4A.json","graph_json":"https://pith.science/api/pith-number/EBNC5T5CEE2PG3IBIAF4K42K4A/graph.json","events_json":"https://pith.science/api/pith-number/EBNC5T5CEE2PG3IBIAF4K42K4A/events.json","paper":"https://pith.science/paper/EBNC5T5C"},"agent_actions":{"view_html":"https://pith.science/pith/EBNC5T5CEE2PG3IBIAF4K42K4A","download_json":"https://pith.science/pith/EBNC5T5CEE2PG3IBIAF4K42K4A.json","view_paper":"https://pith.science/paper/EBNC5T5C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.02214&json=true","fetch_graph":"https://pith.science/api/pith-number/EBNC5T5CEE2PG3IBIAF4K42K4A/graph.json","fetch_events":"https://pith.science/api/pith-number/EBNC5T5CEE2PG3IBIAF4K42K4A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EBNC5T5CEE2PG3IBIAF4K42K4A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EBNC5T5CEE2PG3IBIAF4K42K4A/action/storage_attestation","attest_author":"https://pith.science/pith/EBNC5T5CEE2PG3IBIAF4K42K4A/action/author_attestation","sign_citation":"https://pith.science/pith/EBNC5T5CEE2PG3IBIAF4K42K4A/action/citation_signature","submit_replication":"https://pith.science/pith/EBNC5T5CEE2PG3IBIAF4K42K4A/action/replication_record"}},"created_at":"2026-07-05T08:05:01.719557+00:00","updated_at":"2026-07-05T08:05:01.719557+00:00"}