{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:PL3G327SQJQJXWCL22EBLLESWS","short_pith_number":"pith:PL3G327S","schema_version":"1.0","canonical_sha256":"7af66debf282609bd84bd68815ac92b492db4ab958a7a655589e94e8b997dd0d","source":{"kind":"arxiv","id":"1905.13633","version":1},"attestation_state":"computed","paper":{"title":"Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Scellier, Damien Querlioz, Julie Grollier, Maxence Ernoult, Yoshua Bengio","submitted_at":"2019-05-31T14:26:39Z","abstract_excerpt":"Equilibrium Propagation (EP) is a biologically inspired learning algorithm for convergent recurrent neural networks, i.e. RNNs that are fed by a static input x and settle to a steady state. Training convergent RNNs consists in adjusting the weights until the steady state of output neurons coincides with a target y. Convergent RNNs can also be trained with the more conventional Backpropagation Through Time (BPTT) algorithm. In its original formulation EP was described in the case of real-time neuronal dynamics, which is computationally costly. In this work, we introduce a discrete-time version "},"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":"1905.13633","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-31T14:26:39Z","cross_cats_sorted":["cs.NE","stat.ML"],"title_canon_sha256":"a06fa9e0fe95a53b243e00cf1f431d774a897498fd062ec62a33322ea4010d5e","abstract_canon_sha256":"fc2d84d79227de9b9911fb10451043e17e4f9689fe437398696dcef5a758dead"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:44:34.360408Z","signature_b64":"VFsWmrxnt44TGSGT4gX8gVlPv0y6DJbdRhu6zoRZs08streFdfzv79jucPU1kJyDQHgVmBjkoqwc1QlnvNcrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7af66debf282609bd84bd68815ac92b492db4ab958a7a655589e94e8b997dd0d","last_reissued_at":"2026-05-17T23:44:34.359652Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:44:34.359652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Updates of Equilibrium Prop Match Gradients of Backprop Through Time in an RNN with Static Input","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.NE","stat.ML"],"primary_cat":"cs.LG","authors_text":"Benjamin Scellier, Damien Querlioz, Julie Grollier, Maxence Ernoult, Yoshua Bengio","submitted_at":"2019-05-31T14:26:39Z","abstract_excerpt":"Equilibrium Propagation (EP) is a biologically inspired learning algorithm for convergent recurrent neural networks, i.e. RNNs that are fed by a static input x and settle to a steady state. Training convergent RNNs consists in adjusting the weights until the steady state of output neurons coincides with a target y. Convergent RNNs can also be trained with the more conventional Backpropagation Through Time (BPTT) algorithm. In its original formulation EP was described in the case of real-time neuronal dynamics, which is computationally costly. In this work, we introduce a discrete-time version "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.13633","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":""},"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":"1905.13633","created_at":"2026-05-17T23:44:34.359778+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.13633v1","created_at":"2026-05-17T23:44:34.359778+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.13633","created_at":"2026-05-17T23:44:34.359778+00:00"},{"alias_kind":"pith_short_12","alias_value":"PL3G327SQJQJ","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_16","alias_value":"PL3G327SQJQJXWCL","created_at":"2026-05-18T12:33:24.271573+00:00"},{"alias_kind":"pith_short_8","alias_value":"PL3G327S","created_at":"2026-05-18T12:33:24.271573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.08150","citing_title":"FlowEqProp: Training Flow Matching Generative Models with Gradient Equilibrium Propagation","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PL3G327SQJQJXWCL22EBLLESWS","json":"https://pith.science/pith/PL3G327SQJQJXWCL22EBLLESWS.json","graph_json":"https://pith.science/api/pith-number/PL3G327SQJQJXWCL22EBLLESWS/graph.json","events_json":"https://pith.science/api/pith-number/PL3G327SQJQJXWCL22EBLLESWS/events.json","paper":"https://pith.science/paper/PL3G327S"},"agent_actions":{"view_html":"https://pith.science/pith/PL3G327SQJQJXWCL22EBLLESWS","download_json":"https://pith.science/pith/PL3G327SQJQJXWCL22EBLLESWS.json","view_paper":"https://pith.science/paper/PL3G327S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.13633&json=true","fetch_graph":"https://pith.science/api/pith-number/PL3G327SQJQJXWCL22EBLLESWS/graph.json","fetch_events":"https://pith.science/api/pith-number/PL3G327SQJQJXWCL22EBLLESWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PL3G327SQJQJXWCL22EBLLESWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PL3G327SQJQJXWCL22EBLLESWS/action/storage_attestation","attest_author":"https://pith.science/pith/PL3G327SQJQJXWCL22EBLLESWS/action/author_attestation","sign_citation":"https://pith.science/pith/PL3G327SQJQJXWCL22EBLLESWS/action/citation_signature","submit_replication":"https://pith.science/pith/PL3G327SQJQJXWCL22EBLLESWS/action/replication_record"}},"created_at":"2026-05-17T23:44:34.359778+00:00","updated_at":"2026-05-17T23:44:34.359778+00:00"}