{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YBHWRO6TL6QPWLN3IVABHPZBDB","short_pith_number":"pith:YBHWRO6T","schema_version":"1.0","canonical_sha256":"c04f68bbd35fa0fb2dbb454013bf211845b21ca9f9f9d41157aed338550b1885","source":{"kind":"arxiv","id":"2311.03470","version":3},"attestation_state":"computed","paper":{"title":"Orion: A Fully Homomorphic Encryption Framework for Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Austin Ebel, Brandon Reagen, Karthik Garimella","submitted_at":"2023-11-06T19:14:17Z","abstract_excerpt":"Fully Homomorphic Encryption (FHE) has the potential to substantially improve privacy and security by enabling computation directly on encrypted data. This is especially true with deep learning, as today, many popular user services are powered by neural networks in the cloud. Beyond its well-known high computational costs, one of the major challenges facing wide-scale deployment of FHE-secured neural inference is effectively mapping these networks to FHE primitives. FHE poses many programming challenges including packing large vectors, managing accumulated noise, and translating arbitrary and "},"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":"2311.03470","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2023-11-06T19:14:17Z","cross_cats_sorted":[],"title_canon_sha256":"0f49c66e8921ac6d4567b7f4466bdc1af7cfdbdb199f555e265594deeff255dd","abstract_canon_sha256":"0b53e9be3046a932a05e9a5e6eb2ea83825a07481bc12359e305f176db515665"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:26.093912Z","signature_b64":"FUuYCBbgFb4BlyMBZ8Q+eu1I1IdrFssPrkg7ESt2nhxxD2a1zKZkEz4aJ13NdhaNSg0hXB8GM1EVccg/24gOCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c04f68bbd35fa0fb2dbb454013bf211845b21ca9f9f9d41157aed338550b1885","last_reissued_at":"2026-07-05T10:13:26.093429Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:26.093429Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Orion: A Fully Homomorphic Encryption Framework for Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Austin Ebel, Brandon Reagen, Karthik Garimella","submitted_at":"2023-11-06T19:14:17Z","abstract_excerpt":"Fully Homomorphic Encryption (FHE) has the potential to substantially improve privacy and security by enabling computation directly on encrypted data. This is especially true with deep learning, as today, many popular user services are powered by neural networks in the cloud. Beyond its well-known high computational costs, one of the major challenges facing wide-scale deployment of FHE-secured neural inference is effectively mapping these networks to FHE primitives. FHE poses many programming challenges including packing large vectors, managing accumulated noise, and translating arbitrary and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03470","kind":"arxiv","version":3},"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/2311.03470/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":"2311.03470","created_at":"2026-07-05T10:13:26.093493+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.03470v3","created_at":"2026-07-05T10:13:26.093493+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03470","created_at":"2026-07-05T10:13:26.093493+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBHWRO6TL6QP","created_at":"2026-07-05T10:13:26.093493+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBHWRO6TL6QPWLN3","created_at":"2026-07-05T10:13:26.093493+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBHWRO6T","created_at":"2026-07-05T10:13:26.093493+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14519","citing_title":"Towards Efficient Privacy-Preserving Machine Learning: A Systematic Review from Protocol, Model, and System Perspectives","ref_index":59,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YBHWRO6TL6QPWLN3IVABHPZBDB","json":"https://pith.science/pith/YBHWRO6TL6QPWLN3IVABHPZBDB.json","graph_json":"https://pith.science/api/pith-number/YBHWRO6TL6QPWLN3IVABHPZBDB/graph.json","events_json":"https://pith.science/api/pith-number/YBHWRO6TL6QPWLN3IVABHPZBDB/events.json","paper":"https://pith.science/paper/YBHWRO6T"},"agent_actions":{"view_html":"https://pith.science/pith/YBHWRO6TL6QPWLN3IVABHPZBDB","download_json":"https://pith.science/pith/YBHWRO6TL6QPWLN3IVABHPZBDB.json","view_paper":"https://pith.science/paper/YBHWRO6T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.03470&json=true","fetch_graph":"https://pith.science/api/pith-number/YBHWRO6TL6QPWLN3IVABHPZBDB/graph.json","fetch_events":"https://pith.science/api/pith-number/YBHWRO6TL6QPWLN3IVABHPZBDB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBHWRO6TL6QPWLN3IVABHPZBDB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBHWRO6TL6QPWLN3IVABHPZBDB/action/storage_attestation","attest_author":"https://pith.science/pith/YBHWRO6TL6QPWLN3IVABHPZBDB/action/author_attestation","sign_citation":"https://pith.science/pith/YBHWRO6TL6QPWLN3IVABHPZBDB/action/citation_signature","submit_replication":"https://pith.science/pith/YBHWRO6TL6QPWLN3IVABHPZBDB/action/replication_record"}},"created_at":"2026-07-05T10:13:26.093493+00:00","updated_at":"2026-07-05T10:13:26.093493+00:00"}