{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R3CEMJGFQE6PPSDPT454JP34ZY","short_pith_number":"pith:R3CEMJGF","schema_version":"1.0","canonical_sha256":"8ec44624c5813cf7c86f9f3bc4bf7cce0daab1e70935981451eb96a9bff40bf1","source":{"kind":"arxiv","id":"2606.09117","version":1},"attestation_state":"computed","paper":{"title":"Optimizing Energy-based Neural Network Training with Coherent Ising Machine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Lu, Chen-Rui Fan, Chuan Wang, Jing-Wei Wen, Run-Qing Zhang, Zhi-Hong Zhang","submitted_at":"2026-06-08T07:11:37Z","abstract_excerpt":"While Ising machines serve as advanced physical solvers for the Ising model,enabling applications in combinatorial optimization and neural network training,their scalability for large-scale neural networks remains constrained by hardware connectivity limitations and suboptimal training methodologies. In this work,we leverage a Coherent Ising Machine (CIM) to train an energy-based neural network using Equilibrium Propagation, achieving performance comparable to existing software-based implementations. We further enhance the algorithm by integrating the Adam optimizer to solve for the ground sta"},"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":"2606.09117","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-08T07:11:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b1284e46694deeda219f7026d9ef6baac01795f7f46cc1d9b41d84e655db9aa3","abstract_canon_sha256":"aedc50030a778f8736f24397088136889ba015164bd6068f840aa403b792cf28"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:00.198731Z","signature_b64":"8PWQ9FVYxLphDE+/jrLAmip/h7w7w2Pepd6rRDJFPWsD9/dmF3yOYkkO5Rbl5V8f0XeDK/Zc+e+utuKXz6psCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ec44624c5813cf7c86f9f3bc4bf7cce0daab1e70935981451eb96a9bff40bf1","last_reissued_at":"2026-06-09T02:08:00.197721Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:00.197721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimizing Energy-based Neural Network Training with Coherent Ising Machine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bo Lu, Chen-Rui Fan, Chuan Wang, Jing-Wei Wen, Run-Qing Zhang, Zhi-Hong Zhang","submitted_at":"2026-06-08T07:11:37Z","abstract_excerpt":"While Ising machines serve as advanced physical solvers for the Ising model,enabling applications in combinatorial optimization and neural network training,their scalability for large-scale neural networks remains constrained by hardware connectivity limitations and suboptimal training methodologies. In this work,we leverage a Coherent Ising Machine (CIM) to train an energy-based neural network using Equilibrium Propagation, achieving performance comparable to existing software-based implementations. We further enhance the algorithm by integrating the Adam optimizer to solve for the ground sta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09117","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/2606.09117/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":"2606.09117","created_at":"2026-06-09T02:08:00.197884+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09117v1","created_at":"2026-06-09T02:08:00.197884+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09117","created_at":"2026-06-09T02:08:00.197884+00:00"},{"alias_kind":"pith_short_12","alias_value":"R3CEMJGFQE6P","created_at":"2026-06-09T02:08:00.197884+00:00"},{"alias_kind":"pith_short_16","alias_value":"R3CEMJGFQE6PPSDP","created_at":"2026-06-09T02:08:00.197884+00:00"},{"alias_kind":"pith_short_8","alias_value":"R3CEMJGF","created_at":"2026-06-09T02:08:00.197884+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/R3CEMJGFQE6PPSDPT454JP34ZY","json":"https://pith.science/pith/R3CEMJGFQE6PPSDPT454JP34ZY.json","graph_json":"https://pith.science/api/pith-number/R3CEMJGFQE6PPSDPT454JP34ZY/graph.json","events_json":"https://pith.science/api/pith-number/R3CEMJGFQE6PPSDPT454JP34ZY/events.json","paper":"https://pith.science/paper/R3CEMJGF"},"agent_actions":{"view_html":"https://pith.science/pith/R3CEMJGFQE6PPSDPT454JP34ZY","download_json":"https://pith.science/pith/R3CEMJGFQE6PPSDPT454JP34ZY.json","view_paper":"https://pith.science/paper/R3CEMJGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09117&json=true","fetch_graph":"https://pith.science/api/pith-number/R3CEMJGFQE6PPSDPT454JP34ZY/graph.json","fetch_events":"https://pith.science/api/pith-number/R3CEMJGFQE6PPSDPT454JP34ZY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R3CEMJGFQE6PPSDPT454JP34ZY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R3CEMJGFQE6PPSDPT454JP34ZY/action/storage_attestation","attest_author":"https://pith.science/pith/R3CEMJGFQE6PPSDPT454JP34ZY/action/author_attestation","sign_citation":"https://pith.science/pith/R3CEMJGFQE6PPSDPT454JP34ZY/action/citation_signature","submit_replication":"https://pith.science/pith/R3CEMJGFQE6PPSDPT454JP34ZY/action/replication_record"}},"created_at":"2026-06-09T02:08:00.197884+00:00","updated_at":"2026-06-09T02:08:00.197884+00:00"}