{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GO7M6OFSFWMXMLLTDQ2W7WS7LH","short_pith_number":"pith:GO7M6OFS","schema_version":"1.0","canonical_sha256":"33becf38b22d99762d731c356fda5f59f97f0f5b5159190d86957e8d59aa3fd2","source":{"kind":"arxiv","id":"2508.08421","version":1},"attestation_state":"computed","paper":{"title":"Neural Tangent Knowledge Distillation for Optical Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Arka Majumdar, Eli Shlizerman, Jinlin Xiang, Minho Choi, Yubo Zhang, Zhihao Zhou","submitted_at":"2025-08-11T19:15:06Z","abstract_excerpt":"Hybrid Optical Neural Networks (ONNs, typically consisting of an optical frontend and a digital backend) offer an energy-efficient alternative to fully digital deep networks for real-time, power-constrained systems. However, their adoption is limited by two main challenges: the accuracy gap compared to large-scale networks during training, and discrepancies between simulated and fabricated systems that further degrade accuracy. While previous work has proposed end-to-end optimizations for specific datasets (e.g., MNIST) and optical systems, these approaches typically lack generalization across"},"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":"2508.08421","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-11T19:15:06Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"95524fe2e15d3cd112f1b85980bc86acebd2c9b3168451174fc0a29c6a467857","abstract_canon_sha256":"1f47c21d9a83a633a5c97ac5374eb2f81a9222219b92d995fa174b96de2611f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:27.938647Z","signature_b64":"RKd1MMvzPSaG6gz1o6tEVc0kFu9mYzucY60iYDLBiRWB+QrQKvDx64JpsxtnSRTLL33UKY0bZ4O7UM39rzOnAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"33becf38b22d99762d731c356fda5f59f97f0f5b5159190d86957e8d59aa3fd2","last_reissued_at":"2026-07-05T11:52:27.938113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:27.938113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Tangent Knowledge Distillation for Optical Convolutional Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Arka Majumdar, Eli Shlizerman, Jinlin Xiang, Minho Choi, Yubo Zhang, Zhihao Zhou","submitted_at":"2025-08-11T19:15:06Z","abstract_excerpt":"Hybrid Optical Neural Networks (ONNs, typically consisting of an optical frontend and a digital backend) offer an energy-efficient alternative to fully digital deep networks for real-time, power-constrained systems. However, their adoption is limited by two main challenges: the accuracy gap compared to large-scale networks during training, and discrepancies between simulated and fabricated systems that further degrade accuracy. While previous work has proposed end-to-end optimizations for specific datasets (e.g., MNIST) and optical systems, these approaches typically lack generalization across"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.08421","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/2508.08421/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":"2508.08421","created_at":"2026-07-05T11:52:27.938175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.08421v1","created_at":"2026-07-05T11:52:27.938175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.08421","created_at":"2026-07-05T11:52:27.938175+00:00"},{"alias_kind":"pith_short_12","alias_value":"GO7M6OFSFWMX","created_at":"2026-07-05T11:52:27.938175+00:00"},{"alias_kind":"pith_short_16","alias_value":"GO7M6OFSFWMXMLLT","created_at":"2026-07-05T11:52:27.938175+00:00"},{"alias_kind":"pith_short_8","alias_value":"GO7M6OFS","created_at":"2026-07-05T11:52:27.938175+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.08109","citing_title":"Advantages of Broadband Metalenses for Generalizable Image Classification","ref_index":30,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GO7M6OFSFWMXMLLTDQ2W7WS7LH","json":"https://pith.science/pith/GO7M6OFSFWMXMLLTDQ2W7WS7LH.json","graph_json":"https://pith.science/api/pith-number/GO7M6OFSFWMXMLLTDQ2W7WS7LH/graph.json","events_json":"https://pith.science/api/pith-number/GO7M6OFSFWMXMLLTDQ2W7WS7LH/events.json","paper":"https://pith.science/paper/GO7M6OFS"},"agent_actions":{"view_html":"https://pith.science/pith/GO7M6OFSFWMXMLLTDQ2W7WS7LH","download_json":"https://pith.science/pith/GO7M6OFSFWMXMLLTDQ2W7WS7LH.json","view_paper":"https://pith.science/paper/GO7M6OFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.08421&json=true","fetch_graph":"https://pith.science/api/pith-number/GO7M6OFSFWMXMLLTDQ2W7WS7LH/graph.json","fetch_events":"https://pith.science/api/pith-number/GO7M6OFSFWMXMLLTDQ2W7WS7LH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GO7M6OFSFWMXMLLTDQ2W7WS7LH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GO7M6OFSFWMXMLLTDQ2W7WS7LH/action/storage_attestation","attest_author":"https://pith.science/pith/GO7M6OFSFWMXMLLTDQ2W7WS7LH/action/author_attestation","sign_citation":"https://pith.science/pith/GO7M6OFSFWMXMLLTDQ2W7WS7LH/action/citation_signature","submit_replication":"https://pith.science/pith/GO7M6OFSFWMXMLLTDQ2W7WS7LH/action/replication_record"}},"created_at":"2026-07-05T11:52:27.938175+00:00","updated_at":"2026-07-05T11:52:27.938175+00:00"}