{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:HBHUJLKA7XYWGNMFLTH7KTJPGL","short_pith_number":"pith:HBHUJLKA","schema_version":"1.0","canonical_sha256":"384f44ad40fdf16335855ccff54d2f32ca66f7a3f9f2c652522c828f7898ecc1","source":{"kind":"arxiv","id":"1602.05179","version":5},"attestation_state":"computed","paper":{"title":"Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Scellier, Yoshua Bengio","submitted_at":"2016-02-16T20:46:51Z","abstract_excerpt":"We introduce Equilibrium Propagation, a learning framework for energy-based models. It involves only one kind of neural computation, performed in both the first phase (when the prediction is made) and the second phase of training (after the target or prediction error is revealed). Although this algorithm computes the gradient of an objective function just like Backpropagation, it does not need a special computation or circuit for the second phase, where errors are implicitly propagated. Equilibrium Propagation shares similarities with Contrastive Hebbian Learning and Contrastive Divergence whi"},"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":"1602.05179","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2016-02-16T20:46:51Z","cross_cats_sorted":[],"title_canon_sha256":"86f217c16977a5e854556a53032db9047bbc3138743535f54520c4cba928d2fe","abstract_canon_sha256":"cca86efdd19daa129519fd0716ab8fb3a3bfa2dbaebb07efc603670d4f6b5f39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:47:43.087855Z","signature_b64":"fFHDUX9kF1gslwyYTEfY+S7V8hgJtU/LGS1xCLaJrlMJvCkEDkUFSb1VV5v8pRkD77lxxdULQGSl56UEGQ0dBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"384f44ad40fdf16335855ccff54d2f32ca66f7a3f9f2c652522c828f7898ecc1","last_reissued_at":"2026-05-18T00:47:43.087084Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:47:43.087084Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Equilibrium Propagation: Bridging the Gap Between Energy-Based Models and Backpropagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Benjamin Scellier, Yoshua Bengio","submitted_at":"2016-02-16T20:46:51Z","abstract_excerpt":"We introduce Equilibrium Propagation, a learning framework for energy-based models. It involves only one kind of neural computation, performed in both the first phase (when the prediction is made) and the second phase of training (after the target or prediction error is revealed). Although this algorithm computes the gradient of an objective function just like Backpropagation, it does not need a special computation or circuit for the second phase, where errors are implicitly propagated. Equilibrium Propagation shares similarities with Contrastive Hebbian Learning and Contrastive Divergence whi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.05179","kind":"arxiv","version":5},"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":"1602.05179","created_at":"2026-05-18T00:47:43.087211+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.05179v5","created_at":"2026-05-18T00:47:43.087211+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.05179","created_at":"2026-05-18T00:47:43.087211+00:00"},{"alias_kind":"pith_short_12","alias_value":"HBHUJLKA7XYW","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_16","alias_value":"HBHUJLKA7XYWGNMF","created_at":"2026-05-18T12:30:19.053100+00:00"},{"alias_kind":"pith_short_8","alias_value":"HBHUJLKA","created_at":"2026-05-18T12:30:19.053100+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.13081","citing_title":"Selectivity and Shape in the Design of Forward-Forward Goodness Functions","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08150","citing_title":"FlowEqProp: Training Flow Matching Generative Models with Gradient Equilibrium Propagation","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HBHUJLKA7XYWGNMFLTH7KTJPGL","json":"https://pith.science/pith/HBHUJLKA7XYWGNMFLTH7KTJPGL.json","graph_json":"https://pith.science/api/pith-number/HBHUJLKA7XYWGNMFLTH7KTJPGL/graph.json","events_json":"https://pith.science/api/pith-number/HBHUJLKA7XYWGNMFLTH7KTJPGL/events.json","paper":"https://pith.science/paper/HBHUJLKA"},"agent_actions":{"view_html":"https://pith.science/pith/HBHUJLKA7XYWGNMFLTH7KTJPGL","download_json":"https://pith.science/pith/HBHUJLKA7XYWGNMFLTH7KTJPGL.json","view_paper":"https://pith.science/paper/HBHUJLKA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.05179&json=true","fetch_graph":"https://pith.science/api/pith-number/HBHUJLKA7XYWGNMFLTH7KTJPGL/graph.json","fetch_events":"https://pith.science/api/pith-number/HBHUJLKA7XYWGNMFLTH7KTJPGL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HBHUJLKA7XYWGNMFLTH7KTJPGL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HBHUJLKA7XYWGNMFLTH7KTJPGL/action/storage_attestation","attest_author":"https://pith.science/pith/HBHUJLKA7XYWGNMFLTH7KTJPGL/action/author_attestation","sign_citation":"https://pith.science/pith/HBHUJLKA7XYWGNMFLTH7KTJPGL/action/citation_signature","submit_replication":"https://pith.science/pith/HBHUJLKA7XYWGNMFLTH7KTJPGL/action/replication_record"}},"created_at":"2026-05-18T00:47:43.087211+00:00","updated_at":"2026-05-18T00:47:43.087211+00:00"}