{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZQ55W3AD7MIPNYMPWPQGODELD4","short_pith_number":"pith:ZQ55W3AD","schema_version":"1.0","canonical_sha256":"cc3bdb6c03fb10f6e18fb3e0670c8b1f10f32479e4e44f0378201a1d3c9b37b5","source":{"kind":"arxiv","id":"2508.11750","version":1},"attestation_state":"computed","paper":{"title":"Training nonlinear optical neural networks with Scattering Backpropagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.mes-hall","cs.ET"],"primary_cat":"physics.optics","authors_text":"Clara C. Wanjura, Florian Marquardt, Nicola Dal Cin","submitted_at":"2025-08-15T18:00:05Z","abstract_excerpt":"As deep learning applications continue to deploy increasingly large artificial neural networks, the associated high energy demands are creating a need for alternative neuromorphic approaches. Optics and photonics are particularly compelling platforms as they offer high speeds and energy efficiency. Neuromorphic systems based on nonlinear optics promise high expressivity with a minimal number of parameters. However, so far, there is no efficient and generic physics-based training method allowing us to extract gradients for the most general class of nonlinear optical systems. In this work, we pr"},"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":"2508.11750","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"physics.optics","submitted_at":"2025-08-15T18:00:05Z","cross_cats_sorted":["cond-mat.dis-nn","cond-mat.mes-hall","cs.ET"],"title_canon_sha256":"b3a24ca5195e54e6c2a26bc91cfb66b67d27ab1a51d8afd63264d6d062634a65","abstract_canon_sha256":"d2cf288489d889a7b1f6f530307a4ec3a778288c8ba6d821c6195bf0ce5879ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:53.747260Z","signature_b64":"4G+1l7phC3yhhJGohJlvN8EAfqUYwJDB35AXZNyfws4AC66ujeFS1mccdzOaMWQFH100DwJb1apMgCPp0QFoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc3bdb6c03fb10f6e18fb3e0670c8b1f10f32479e4e44f0378201a1d3c9b37b5","last_reissued_at":"2026-07-05T11:54:53.746797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:53.746797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Training nonlinear optical neural networks with Scattering Backpropagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cond-mat.dis-nn","cond-mat.mes-hall","cs.ET"],"primary_cat":"physics.optics","authors_text":"Clara C. Wanjura, Florian Marquardt, Nicola Dal Cin","submitted_at":"2025-08-15T18:00:05Z","abstract_excerpt":"As deep learning applications continue to deploy increasingly large artificial neural networks, the associated high energy demands are creating a need for alternative neuromorphic approaches. Optics and photonics are particularly compelling platforms as they offer high speeds and energy efficiency. Neuromorphic systems based on nonlinear optics promise high expressivity with a minimal number of parameters. However, so far, there is no efficient and generic physics-based training method allowing us to extract gradients for the most general class of nonlinear optical systems. In this work, we pr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11750","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/2508.11750/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":"2508.11750","created_at":"2026-07-05T11:54:53.746854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11750v1","created_at":"2026-07-05T11:54:53.746854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11750","created_at":"2026-07-05T11:54:53.746854+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQ55W3AD7MIP","created_at":"2026-07-05T11:54:53.746854+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQ55W3AD7MIPNYMP","created_at":"2026-07-05T11:54:53.746854+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQ55W3AD","created_at":"2026-07-05T11:54:53.746854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.02734","citing_title":"Non-Volatile Vortex MTJs with Opto-Electrical and Spin-Diode Nonlinearities as Multifunctional Neuromorphic Platforms","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11658","citing_title":"Neuromorphic computing with optomechanical oscillators","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZQ55W3AD7MIPNYMPWPQGODELD4","json":"https://pith.science/pith/ZQ55W3AD7MIPNYMPWPQGODELD4.json","graph_json":"https://pith.science/api/pith-number/ZQ55W3AD7MIPNYMPWPQGODELD4/graph.json","events_json":"https://pith.science/api/pith-number/ZQ55W3AD7MIPNYMPWPQGODELD4/events.json","paper":"https://pith.science/paper/ZQ55W3AD"},"agent_actions":{"view_html":"https://pith.science/pith/ZQ55W3AD7MIPNYMPWPQGODELD4","download_json":"https://pith.science/pith/ZQ55W3AD7MIPNYMPWPQGODELD4.json","view_paper":"https://pith.science/paper/ZQ55W3AD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11750&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQ55W3AD7MIPNYMPWPQGODELD4/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQ55W3AD7MIPNYMPWPQGODELD4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQ55W3AD7MIPNYMPWPQGODELD4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQ55W3AD7MIPNYMPWPQGODELD4/action/storage_attestation","attest_author":"https://pith.science/pith/ZQ55W3AD7MIPNYMPWPQGODELD4/action/author_attestation","sign_citation":"https://pith.science/pith/ZQ55W3AD7MIPNYMPWPQGODELD4/action/citation_signature","submit_replication":"https://pith.science/pith/ZQ55W3AD7MIPNYMPWPQGODELD4/action/replication_record"}},"created_at":"2026-07-05T11:54:53.746854+00:00","updated_at":"2026-07-05T11:54:53.746854+00:00"}