{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6HE77SWKPVF4YMIF5N46S6YNRQ","short_pith_number":"pith:6HE77SWK","schema_version":"1.0","canonical_sha256":"f1c9ffcaca7d4bcc3105eb79e97b0d8c3bb7c48a36ad31170e00e76ecfd06ccc","source":{"kind":"arxiv","id":"2506.06665","version":1},"attestation_state":"computed","paper":{"title":"SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hao Chen, Hong-Ming Chiu, Huan Zhang, Richard Y. Zhang","submitted_at":"2025-06-07T05:06:07Z","abstract_excerpt":"Neural network verifiers based on linear bound propagation scale impressively to massive models but can be surprisingly loose when neuron coupling is crucial. Conversely, semidefinite programming (SDP) verifiers capture inter-neuron coupling naturally, but their cubic complexity restricts them to only small models. In this paper, we propose SDP-CROWN, a novel hybrid verification framework that combines the tightness of SDP relaxations with the scalability of bound-propagation verifiers. At the core of SDP-CROWN is a new linear bound, derived via SDP principles, that explicitly captures $\\ell_{"},"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":"2506.06665","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-07T05:06:07Z","cross_cats_sorted":[],"title_canon_sha256":"c19c3ae2634a680b1005e9f71a0316ef568ea88c27bf2c625a3d47a82aea2838","abstract_canon_sha256":"b789ce4b77446eeb2c3cbe8779c72cc7c4049dc12ead3fab51b2a27a18e2ef65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:53.693407Z","signature_b64":"4fokgyH3wToZiJbyS4+W8LlPFl9SBIibWOXXadF2zIMzJFcCRugpBECBHufU4mFA9QLfpgePVvvBH19H3FNvDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1c9ffcaca7d4bcc3105eb79e97b0d8c3bb7c48a36ad31170e00e76ecfd06ccc","last_reissued_at":"2026-07-05T11:17:53.692855Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:53.692855Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SDP-CROWN: Efficient Bound Propagation for Neural Network Verification with Tightness of Semidefinite Programming","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hao Chen, Hong-Ming Chiu, Huan Zhang, Richard Y. Zhang","submitted_at":"2025-06-07T05:06:07Z","abstract_excerpt":"Neural network verifiers based on linear bound propagation scale impressively to massive models but can be surprisingly loose when neuron coupling is crucial. Conversely, semidefinite programming (SDP) verifiers capture inter-neuron coupling naturally, but their cubic complexity restricts them to only small models. In this paper, we propose SDP-CROWN, a novel hybrid verification framework that combines the tightness of SDP relaxations with the scalability of bound-propagation verifiers. At the core of SDP-CROWN is a new linear bound, derived via SDP principles, that explicitly captures $\\ell_{"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06665","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/2506.06665/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":"2506.06665","created_at":"2026-07-05T11:17:53.692914+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06665v1","created_at":"2026-07-05T11:17:53.692914+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06665","created_at":"2026-07-05T11:17:53.692914+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HE77SWKPVF4","created_at":"2026-07-05T11:17:53.692914+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HE77SWKPVF4YMIF","created_at":"2026-07-05T11:17:53.692914+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HE77SWK","created_at":"2026-07-05T11:17:53.692914+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/6HE77SWKPVF4YMIF5N46S6YNRQ","json":"https://pith.science/pith/6HE77SWKPVF4YMIF5N46S6YNRQ.json","graph_json":"https://pith.science/api/pith-number/6HE77SWKPVF4YMIF5N46S6YNRQ/graph.json","events_json":"https://pith.science/api/pith-number/6HE77SWKPVF4YMIF5N46S6YNRQ/events.json","paper":"https://pith.science/paper/6HE77SWK"},"agent_actions":{"view_html":"https://pith.science/pith/6HE77SWKPVF4YMIF5N46S6YNRQ","download_json":"https://pith.science/pith/6HE77SWKPVF4YMIF5N46S6YNRQ.json","view_paper":"https://pith.science/paper/6HE77SWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06665&json=true","fetch_graph":"https://pith.science/api/pith-number/6HE77SWKPVF4YMIF5N46S6YNRQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6HE77SWKPVF4YMIF5N46S6YNRQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HE77SWKPVF4YMIF5N46S6YNRQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HE77SWKPVF4YMIF5N46S6YNRQ/action/storage_attestation","attest_author":"https://pith.science/pith/6HE77SWKPVF4YMIF5N46S6YNRQ/action/author_attestation","sign_citation":"https://pith.science/pith/6HE77SWKPVF4YMIF5N46S6YNRQ/action/citation_signature","submit_replication":"https://pith.science/pith/6HE77SWKPVF4YMIF5N46S6YNRQ/action/replication_record"}},"created_at":"2026-07-05T11:17:53.692914+00:00","updated_at":"2026-07-05T11:17:53.692914+00:00"}