{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R4VCOUPLDKALLXWCGAY3NI5HOT","short_pith_number":"pith:R4VCOUPL","schema_version":"1.0","canonical_sha256":"8f2a2751eb1a80b5dec23031b6a3a774f1296d5a8c07313200015e1712a6b668","source":{"kind":"arxiv","id":"2606.03584","version":1},"attestation_state":"computed","paper":{"title":"Training a Predictive Coding Network on ImageNet using Equilibrium Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.NE"],"primary_cat":"cs.LG","authors_text":"Benjamin Scellier, Rasmus H{\\o}ier, Tugdual Kerjan","submitted_at":"2026-06-02T12:52:29Z","abstract_excerpt":"Equilibrium Propagation (EP) is a physics-based training framework that has primarily been employed in energy-based models, including continuous Hopfield networks, nonlinear resistive networks and coupled phase oscillators. However, EP's practical applications have so far remained limited to relatively small-scale problems. Predictive coding networks (PCNs), another class of energy-based models rooted in computational neuroscience, are typically trained with a specialized algorithm and have likewise not yet been demonstrated at large scale. In this work, we develop an EP-based training method "},"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":"2606.03584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-02T12:52:29Z","cross_cats_sorted":["cond-mat.dis-nn","cs.NE"],"title_canon_sha256":"ca60d3a909157e3decf17f06aee6c4c864974fd4bedd67bd2628dc73416a2e8f","abstract_canon_sha256":"1850d30dc688e4ad263c244aba8f42ebc72e8c6779cbf38708113bf3d7980256"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:06:01.461151Z","signature_b64":"GY2amKlisHwNyKkMpU+qF7XhlNuGbM4LqcJWuuI3zSRhz/o4vEUoZnGwvaS4LCN4SE9JpJ3ho7/9Qg7gGX4YBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f2a2751eb1a80b5dec23031b6a3a774f1296d5a8c07313200015e1712a6b668","last_reissued_at":"2026-06-03T01:06:01.460779Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:06:01.460779Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training a Predictive Coding Network on ImageNet using Equilibrium Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cs.NE"],"primary_cat":"cs.LG","authors_text":"Benjamin Scellier, Rasmus H{\\o}ier, Tugdual Kerjan","submitted_at":"2026-06-02T12:52:29Z","abstract_excerpt":"Equilibrium Propagation (EP) is a physics-based training framework that has primarily been employed in energy-based models, including continuous Hopfield networks, nonlinear resistive networks and coupled phase oscillators. However, EP's practical applications have so far remained limited to relatively small-scale problems. Predictive coding networks (PCNs), another class of energy-based models rooted in computational neuroscience, are typically trained with a specialized algorithm and have likewise not yet been demonstrated at large scale. In this work, we develop an EP-based training method "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03584","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/2606.03584/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":"2606.03584","created_at":"2026-06-03T01:06:01.460843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.03584v1","created_at":"2026-06-03T01:06:01.460843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.03584","created_at":"2026-06-03T01:06:01.460843+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4VCOUPLDKAL","created_at":"2026-06-03T01:06:01.460843+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4VCOUPLDKALLXWC","created_at":"2026-06-03T01:06:01.460843+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4VCOUPL","created_at":"2026-06-03T01:06:01.460843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4VCOUPLDKALLXWCGAY3NI5HOT","json":"https://pith.science/pith/R4VCOUPLDKALLXWCGAY3NI5HOT.json","graph_json":"https://pith.science/api/pith-number/R4VCOUPLDKALLXWCGAY3NI5HOT/graph.json","events_json":"https://pith.science/api/pith-number/R4VCOUPLDKALLXWCGAY3NI5HOT/events.json","paper":"https://pith.science/paper/R4VCOUPL"},"agent_actions":{"view_html":"https://pith.science/pith/R4VCOUPLDKALLXWCGAY3NI5HOT","download_json":"https://pith.science/pith/R4VCOUPLDKALLXWCGAY3NI5HOT.json","view_paper":"https://pith.science/paper/R4VCOUPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.03584&json=true","fetch_graph":"https://pith.science/api/pith-number/R4VCOUPLDKALLXWCGAY3NI5HOT/graph.json","fetch_events":"https://pith.science/api/pith-number/R4VCOUPLDKALLXWCGAY3NI5HOT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4VCOUPLDKALLXWCGAY3NI5HOT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4VCOUPLDKALLXWCGAY3NI5HOT/action/storage_attestation","attest_author":"https://pith.science/pith/R4VCOUPLDKALLXWCGAY3NI5HOT/action/author_attestation","sign_citation":"https://pith.science/pith/R4VCOUPLDKALLXWCGAY3NI5HOT/action/citation_signature","submit_replication":"https://pith.science/pith/R4VCOUPLDKALLXWCGAY3NI5HOT/action/replication_record"}},"created_at":"2026-06-03T01:06:01.460843+00:00","updated_at":"2026-06-03T01:06:01.460843+00:00"}