{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7ALYVULCGF6S2XWS6HH2F6OVMV","short_pith_number":"pith:7ALYVULC","schema_version":"1.0","canonical_sha256":"f8178ad162317d2d5ed2f1cfa2f9d565592488021aad2fb5f0636ad8b98c44d7","source":{"kind":"arxiv","id":"2505.02103","version":5},"attestation_state":"computed","paper":{"title":"How to Train an Oscillator Ising Machine using Equilibrium Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.dis-nn","authors_text":"Alex Gower","submitted_at":"2025-05-04T13:17:15Z","abstract_excerpt":"We show that Oscillator Ising Machines (OIMs) are prime candidates for use as neuromorphic machine learning processors with Equilibrium Propagation (EP) based on-chip learning. The inherent energy gradient descent dynamics of OIMs, combined with their standard CMOS implementation using existing fabrication processes, provide a natural substrate for EP learning. Our simulations confirm that OIMs satisfy the gradient-descending update property necessary for a scalable Equilibrium Propagation implementation and achieve $\\sim 97.2\\pm0.1\\%$ test accuracy on MNIST and $\\sim 88.0\\pm0.1\\%$ on Fashion-"},"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":"2505.02103","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.dis-nn","submitted_at":"2025-05-04T13:17:15Z","cross_cats_sorted":[],"title_canon_sha256":"eea6951826fb102c30d89328c35463ed9e4cfae6dd2e3da7201e68384e07b509","abstract_canon_sha256":"ba5538bb8b15ed73fbc369b2da91cde7a487dbf459a662d4b2272e2afe402615"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:46.586978Z","signature_b64":"w4euf/eWstFIJdjIpr9HkNvftjSGgCcnggrLj4HwVWLHZEzHyYWAPU/VpV3c+4pICUm3puIitDv68IL6ATo6DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8178ad162317d2d5ed2f1cfa2f9d565592488021aad2fb5f0636ad8b98c44d7","last_reissued_at":"2026-07-05T11:54:46.586488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:46.586488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How to Train an Oscillator Ising Machine using Equilibrium Propagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cond-mat.dis-nn","authors_text":"Alex Gower","submitted_at":"2025-05-04T13:17:15Z","abstract_excerpt":"We show that Oscillator Ising Machines (OIMs) are prime candidates for use as neuromorphic machine learning processors with Equilibrium Propagation (EP) based on-chip learning. The inherent energy gradient descent dynamics of OIMs, combined with their standard CMOS implementation using existing fabrication processes, provide a natural substrate for EP learning. Our simulations confirm that OIMs satisfy the gradient-descending update property necessary for a scalable Equilibrium Propagation implementation and achieve $\\sim 97.2\\pm0.1\\%$ test accuracy on MNIST and $\\sim 88.0\\pm0.1\\%$ on Fashion-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02103","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.02103/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":"2505.02103","created_at":"2026-07-05T11:54:46.586551+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.02103v5","created_at":"2026-07-05T11:54:46.586551+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02103","created_at":"2026-07-05T11:54:46.586551+00:00"},{"alias_kind":"pith_short_12","alias_value":"7ALYVULCGF6S","created_at":"2026-07-05T11:54:46.586551+00:00"},{"alias_kind":"pith_short_16","alias_value":"7ALYVULCGF6S2XWS","created_at":"2026-07-05T11:54:46.586551+00:00"},{"alias_kind":"pith_short_8","alias_value":"7ALYVULC","created_at":"2026-07-05T11:54:46.586551+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.10272","citing_title":"The Phase Is the Gradient: Equilibrium Propagation for Frequency Learning in Kuramoto Networks","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7ALYVULCGF6S2XWS6HH2F6OVMV","json":"https://pith.science/pith/7ALYVULCGF6S2XWS6HH2F6OVMV.json","graph_json":"https://pith.science/api/pith-number/7ALYVULCGF6S2XWS6HH2F6OVMV/graph.json","events_json":"https://pith.science/api/pith-number/7ALYVULCGF6S2XWS6HH2F6OVMV/events.json","paper":"https://pith.science/paper/7ALYVULC"},"agent_actions":{"view_html":"https://pith.science/pith/7ALYVULCGF6S2XWS6HH2F6OVMV","download_json":"https://pith.science/pith/7ALYVULCGF6S2XWS6HH2F6OVMV.json","view_paper":"https://pith.science/paper/7ALYVULC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.02103&json=true","fetch_graph":"https://pith.science/api/pith-number/7ALYVULCGF6S2XWS6HH2F6OVMV/graph.json","fetch_events":"https://pith.science/api/pith-number/7ALYVULCGF6S2XWS6HH2F6OVMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7ALYVULCGF6S2XWS6HH2F6OVMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7ALYVULCGF6S2XWS6HH2F6OVMV/action/storage_attestation","attest_author":"https://pith.science/pith/7ALYVULCGF6S2XWS6HH2F6OVMV/action/author_attestation","sign_citation":"https://pith.science/pith/7ALYVULCGF6S2XWS6HH2F6OVMV/action/citation_signature","submit_replication":"https://pith.science/pith/7ALYVULCGF6S2XWS6HH2F6OVMV/action/replication_record"}},"created_at":"2026-07-05T11:54:46.586551+00:00","updated_at":"2026-07-05T11:54:46.586551+00:00"}