{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:LUPN4EQA4LGKA2V45ZHVB6PQ6E","short_pith_number":"pith:LUPN4EQA","schema_version":"1.0","canonical_sha256":"5d1ede1200e2cca06abcee4f50f9f0f12f887e1379b6c0cc8a2dcaf6c6c76d33","source":{"kind":"arxiv","id":"1812.05979","version":1},"attestation_state":"computed","paper":{"title":"Scaling shared model governance via model splitting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.NE"],"primary_cat":"cs.LG","authors_text":"Andrew Trask, Jan Leike, Matteo Hessel, Miljan Martic, Pushmeet Kohli, Shane Legg","submitted_at":"2018-12-14T15:29:21Z","abstract_excerpt":"Currently the only techniques for sharing governance of a deep learning model are homomorphic encryption and secure multiparty computation. Unfortunately, neither of these techniques is applicable to the training of large neural networks due to their large computational and communication overheads. As a scalable technique for shared model governance, we propose splitting deep learning model between multiple parties. This paper empirically investigates the security guarantee of this technique, which is introduced as the problem of model completion: Given the entire training data set or an envir"},"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":"1812.05979","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2018-12-14T15:29:21Z","cross_cats_sorted":["cs.CR","cs.NE"],"title_canon_sha256":"fcd7105cb1be1522be83acbd41da5ba0412372f383841c93f67dae25da51976f","abstract_canon_sha256":"3c5f841fa0d50e8e81af0763c87e31739eda524c34c82daeb1a4fc4d5475d459"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:58:15.866416Z","signature_b64":"MDJihFA8MPLaVea48U3dneBqQWPYVfXSDfQpeA2sS8BLDHiLnnhbbBtCWsA9dhSeytxYb1U5skWRgNMDIbxtAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d1ede1200e2cca06abcee4f50f9f0f12f887e1379b6c0cc8a2dcaf6c6c76d33","last_reissued_at":"2026-05-17T23:58:15.865829Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:58:15.865829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling shared model governance via model splitting","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.NE"],"primary_cat":"cs.LG","authors_text":"Andrew Trask, Jan Leike, Matteo Hessel, Miljan Martic, Pushmeet Kohli, Shane Legg","submitted_at":"2018-12-14T15:29:21Z","abstract_excerpt":"Currently the only techniques for sharing governance of a deep learning model are homomorphic encryption and secure multiparty computation. Unfortunately, neither of these techniques is applicable to the training of large neural networks due to their large computational and communication overheads. As a scalable technique for shared model governance, we propose splitting deep learning model between multiple parties. This paper empirically investigates the security guarantee of this technique, which is introduced as the problem of model completion: Given the entire training data set or an envir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.05979","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":""},"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":"1812.05979","created_at":"2026-05-17T23:58:15.865935+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.05979v1","created_at":"2026-05-17T23:58:15.865935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.05979","created_at":"2026-05-17T23:58:15.865935+00:00"},{"alias_kind":"pith_short_12","alias_value":"LUPN4EQA4LGK","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_16","alias_value":"LUPN4EQA4LGKA2V4","created_at":"2026-05-18T12:32:37.024351+00:00"},{"alias_kind":"pith_short_8","alias_value":"LUPN4EQA","created_at":"2026-05-18T12:32:37.024351+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/LUPN4EQA4LGKA2V45ZHVB6PQ6E","json":"https://pith.science/pith/LUPN4EQA4LGKA2V45ZHVB6PQ6E.json","graph_json":"https://pith.science/api/pith-number/LUPN4EQA4LGKA2V45ZHVB6PQ6E/graph.json","events_json":"https://pith.science/api/pith-number/LUPN4EQA4LGKA2V45ZHVB6PQ6E/events.json","paper":"https://pith.science/paper/LUPN4EQA"},"agent_actions":{"view_html":"https://pith.science/pith/LUPN4EQA4LGKA2V45ZHVB6PQ6E","download_json":"https://pith.science/pith/LUPN4EQA4LGKA2V45ZHVB6PQ6E.json","view_paper":"https://pith.science/paper/LUPN4EQA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.05979&json=true","fetch_graph":"https://pith.science/api/pith-number/LUPN4EQA4LGKA2V45ZHVB6PQ6E/graph.json","fetch_events":"https://pith.science/api/pith-number/LUPN4EQA4LGKA2V45ZHVB6PQ6E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LUPN4EQA4LGKA2V45ZHVB6PQ6E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LUPN4EQA4LGKA2V45ZHVB6PQ6E/action/storage_attestation","attest_author":"https://pith.science/pith/LUPN4EQA4LGKA2V45ZHVB6PQ6E/action/author_attestation","sign_citation":"https://pith.science/pith/LUPN4EQA4LGKA2V45ZHVB6PQ6E/action/citation_signature","submit_replication":"https://pith.science/pith/LUPN4EQA4LGKA2V45ZHVB6PQ6E/action/replication_record"}},"created_at":"2026-05-17T23:58:15.865935+00:00","updated_at":"2026-05-17T23:58:15.865935+00:00"}