{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:XMCVKJQ6HMZIAV7WNDILWGGWA4","short_pith_number":"pith:XMCVKJQ6","schema_version":"1.0","canonical_sha256":"bb0555261e3b328057f668d0bb18d60710b7e929934ed9669426d82fbd7e4b0c","source":{"kind":"arxiv","id":"2005.04168","version":1},"attestation_state":"computed","paper":{"title":"Equilibrium Propagation with Continual Weight Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Benjamin Scellier, Damien Querlioz, Julie Grollier, Maxence Ernoult, Yoshua Bengio","submitted_at":"2020-04-29T14:54:30Z","abstract_excerpt":"Equilibrium Propagation (EP) is a learning algorithm that bridges Machine Learning and Neuroscience, by computing gradients closely matching those of Backpropagation Through Time (BPTT), but with a learning rule local in space. Given an input $x$ and associated target $y$, EP proceeds in two phases: in the first phase neurons evolve freely towards a first steady state; in the second phase output neurons are nudged towards $y$ until they reach a second steady state. However, in existing implementations of EP, the learning rule is not local in time: the weight update is performed after the dynam"},"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":"2005.04168","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2020-04-29T14:54:30Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"911c178467397588e7ac2db14d7598b381b15d78f6d78b063659133c84d7819a","abstract_canon_sha256":"56cf13798498ad86c4f3e5cfb3d74243527152e9cb4dd2bf371666edcfe85896"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:01:30.265178Z","signature_b64":"6F6hdtxgMe3zFdr2gfuiqQD4rfBJF48zM6WWAhd85DAscG3oEo0Jsijr1sofo1knBswq52TtwLqS4Bn06EvADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bb0555261e3b328057f668d0bb18d60710b7e929934ed9669426d82fbd7e4b0c","last_reissued_at":"2026-07-05T01:01:30.264810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:01:30.264810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Equilibrium Propagation with Continual Weight Updates","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.NE","authors_text":"Benjamin Scellier, Damien Querlioz, Julie Grollier, Maxence Ernoult, Yoshua Bengio","submitted_at":"2020-04-29T14:54:30Z","abstract_excerpt":"Equilibrium Propagation (EP) is a learning algorithm that bridges Machine Learning and Neuroscience, by computing gradients closely matching those of Backpropagation Through Time (BPTT), but with a learning rule local in space. Given an input $x$ and associated target $y$, EP proceeds in two phases: in the first phase neurons evolve freely towards a first steady state; in the second phase output neurons are nudged towards $y$ until they reach a second steady state. However, in existing implementations of EP, the learning rule is not local in time: the weight update is performed after the dynam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.04168","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/2005.04168/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":"2005.04168","created_at":"2026-07-05T01:01:30.264866+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.04168v1","created_at":"2026-07-05T01:01:30.264866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.04168","created_at":"2026-07-05T01:01:30.264866+00:00"},{"alias_kind":"pith_short_12","alias_value":"XMCVKJQ6HMZI","created_at":"2026-07-05T01:01:30.264866+00:00"},{"alias_kind":"pith_short_16","alias_value":"XMCVKJQ6HMZIAV7W","created_at":"2026-07-05T01:01:30.264866+00:00"},{"alias_kind":"pith_short_8","alias_value":"XMCVKJQ6","created_at":"2026-07-05T01:01:30.264866+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.13454","citing_title":"Optical Implementation of Equilibrium Propagation Using Spatial Photonic Ising Machines","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15985","citing_title":"Thermodynamic Networks: Harnessing Non-Equilibrium Steady States for Computation","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15989","citing_title":"Scalable Equilibrium Propagation via Intermediate Error Signals for Deep Convolutional CRNNs","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XMCVKJQ6HMZIAV7WNDILWGGWA4","json":"https://pith.science/pith/XMCVKJQ6HMZIAV7WNDILWGGWA4.json","graph_json":"https://pith.science/api/pith-number/XMCVKJQ6HMZIAV7WNDILWGGWA4/graph.json","events_json":"https://pith.science/api/pith-number/XMCVKJQ6HMZIAV7WNDILWGGWA4/events.json","paper":"https://pith.science/paper/XMCVKJQ6"},"agent_actions":{"view_html":"https://pith.science/pith/XMCVKJQ6HMZIAV7WNDILWGGWA4","download_json":"https://pith.science/pith/XMCVKJQ6HMZIAV7WNDILWGGWA4.json","view_paper":"https://pith.science/paper/XMCVKJQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.04168&json=true","fetch_graph":"https://pith.science/api/pith-number/XMCVKJQ6HMZIAV7WNDILWGGWA4/graph.json","fetch_events":"https://pith.science/api/pith-number/XMCVKJQ6HMZIAV7WNDILWGGWA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XMCVKJQ6HMZIAV7WNDILWGGWA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XMCVKJQ6HMZIAV7WNDILWGGWA4/action/storage_attestation","attest_author":"https://pith.science/pith/XMCVKJQ6HMZIAV7WNDILWGGWA4/action/author_attestation","sign_citation":"https://pith.science/pith/XMCVKJQ6HMZIAV7WNDILWGGWA4/action/citation_signature","submit_replication":"https://pith.science/pith/XMCVKJQ6HMZIAV7WNDILWGGWA4/action/replication_record"}},"created_at":"2026-07-05T01:01:30.264866+00:00","updated_at":"2026-07-05T01:01:30.264866+00:00"}