{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LUX4A2LZFH7D6LWON5VQVHDBTB","short_pith_number":"pith:LUX4A2LZ","schema_version":"1.0","canonical_sha256":"5d2fc0697929fe3f2ece6f6b0a9c619861f1ad34268f4de97c31b3e385be1937","source":{"kind":"arxiv","id":"2103.05636","version":1},"attestation_state":"computed","paper":{"title":"A Gradient Estimator for Time-Varying Electrical Networks with Non-Linear Dissipation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jack Kendall","submitted_at":"2021-03-09T02:07:39Z","abstract_excerpt":"We propose a method for extending the technique of equilibrium propagation for estimating gradients in fixed-point neural networks to the more general setting of directed, time-varying neural networks by modeling them as electrical circuits. We use electrical circuit theory to construct a Lagrangian capable of describing deep, directed neural networks modeled using nonlinear capacitors and inductors, linear resistors and sources, and a special class of nonlinear dissipative elements called fractional memristors. We then derive an estimator for the gradient of the physical parameters of the net"},"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":"2103.05636","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-03-09T02:07:39Z","cross_cats_sorted":["cs.AI","cs.NE"],"title_canon_sha256":"db99f1eee024674cf455a89b02b4a355ff37278bbe9a0fe6bf87c53ac710a136","abstract_canon_sha256":"af10caa5f5ce2fc4e8073d29247326dc3b7198dd5d97bbf01149e60037394022"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:21:56.538995Z","signature_b64":"BkUXUWGGbMAObN0McJ5yQvbaZuHIQVRpd1VdOTZgsfVurarvO471k7L6Kt2U7GgzYvBzn5XeAW06o2+TSItEDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d2fc0697929fe3f2ece6f6b0a9c619861f1ad34268f4de97c31b3e385be1937","last_reissued_at":"2026-07-05T02:21:56.538465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:21:56.538465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Gradient Estimator for Time-Varying Electrical Networks with Non-Linear Dissipation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.NE"],"primary_cat":"cs.LG","authors_text":"Jack Kendall","submitted_at":"2021-03-09T02:07:39Z","abstract_excerpt":"We propose a method for extending the technique of equilibrium propagation for estimating gradients in fixed-point neural networks to the more general setting of directed, time-varying neural networks by modeling them as electrical circuits. We use electrical circuit theory to construct a Lagrangian capable of describing deep, directed neural networks modeled using nonlinear capacitors and inductors, linear resistors and sources, and a special class of nonlinear dissipative elements called fractional memristors. We then derive an estimator for the gradient of the physical parameters of the net"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.05636","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2103.05636/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":"2103.05636","created_at":"2026-07-05T02:21:56.538532+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.05636v1","created_at":"2026-07-05T02:21:56.538532+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.05636","created_at":"2026-07-05T02:21:56.538532+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUX4A2LZFH7D","created_at":"2026-07-05T02:21:56.538532+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUX4A2LZFH7D6LWO","created_at":"2026-07-05T02:21:56.538532+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUX4A2LZ","created_at":"2026-07-05T02:21:56.538532+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03584","citing_title":"Training a Predictive Coding Network on ImageNet using Equilibrium Propagation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LUX4A2LZFH7D6LWON5VQVHDBTB","json":"https://pith.science/pith/LUX4A2LZFH7D6LWON5VQVHDBTB.json","graph_json":"https://pith.science/api/pith-number/LUX4A2LZFH7D6LWON5VQVHDBTB/graph.json","events_json":"https://pith.science/api/pith-number/LUX4A2LZFH7D6LWON5VQVHDBTB/events.json","paper":"https://pith.science/paper/LUX4A2LZ"},"agent_actions":{"view_html":"https://pith.science/pith/LUX4A2LZFH7D6LWON5VQVHDBTB","download_json":"https://pith.science/pith/LUX4A2LZFH7D6LWON5VQVHDBTB.json","view_paper":"https://pith.science/paper/LUX4A2LZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.05636&json=true","fetch_graph":"https://pith.science/api/pith-number/LUX4A2LZFH7D6LWON5VQVHDBTB/graph.json","fetch_events":"https://pith.science/api/pith-number/LUX4A2LZFH7D6LWON5VQVHDBTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUX4A2LZFH7D6LWON5VQVHDBTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUX4A2LZFH7D6LWON5VQVHDBTB/action/storage_attestation","attest_author":"https://pith.science/pith/LUX4A2LZFH7D6LWON5VQVHDBTB/action/author_attestation","sign_citation":"https://pith.science/pith/LUX4A2LZFH7D6LWON5VQVHDBTB/action/citation_signature","submit_replication":"https://pith.science/pith/LUX4A2LZFH7D6LWON5VQVHDBTB/action/replication_record"}},"created_at":"2026-07-05T02:21:56.538532+00:00","updated_at":"2026-07-05T02:21:56.538532+00:00"}