{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JXIQUCRY3PXZAOME4F3F3ZTLXR","short_pith_number":"pith:JXIQUCRY","schema_version":"1.0","canonical_sha256":"4dd10a0a38dbef903984e1765de66bbc62f252a77649754aa4cec46fa75b169b","source":{"kind":"arxiv","id":"2401.05280","version":3},"attestation_state":"computed","paper":{"title":"Bound Tightening using Rolling-Horizon Decomposition for Neural Network Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Haoruo Zhao, Hassan Hijazi, Haydn Jones, Juston Moore, Mathieu Tanneau, Pascal Van Hentenryck","submitted_at":"2024-01-10T17:24:24Z","abstract_excerpt":"Neural network verification aims at providing formal guarantees on the output of trained neural networks, to ensure their robustness against adversarial examples and enable their deployment in safety-critical applications. This paper introduces a new approach to neural network verification using a novel mixed-integer programming rolling-horizon decomposition method. The algorithm leverages the layered structure of neural networks, by employing optimization-based bound-tightening on smaller sub-graphs of the original network in a rolling-horizon fashion. This strategy strikes a balance between "},"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":"2401.05280","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.OC","submitted_at":"2024-01-10T17:24:24Z","cross_cats_sorted":[],"title_canon_sha256":"ff2b96adf7d71ce773faf16ed226ec67f6d2fa6c20946f7a388ac9b8a96d5b1c","abstract_canon_sha256":"a960db78fc033d470a971859602f448610c8005cf7120f256b9c86e06f8f0429"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:23.939162Z","signature_b64":"AN1EQ2aRQJwuE05t3eFgj+9sM4YdA12okSGdDsBHnbRH3R0SeIUWXyxj0NEDsJ51GwrG7u/QWHd1/7l1L2ddBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4dd10a0a38dbef903984e1765de66bbc62f252a77649754aa4cec46fa75b169b","last_reissued_at":"2026-07-05T08:02:23.938655Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:23.938655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bound Tightening using Rolling-Horizon Decomposition for Neural Network Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"math.OC","authors_text":"Haoruo Zhao, Hassan Hijazi, Haydn Jones, Juston Moore, Mathieu Tanneau, Pascal Van Hentenryck","submitted_at":"2024-01-10T17:24:24Z","abstract_excerpt":"Neural network verification aims at providing formal guarantees on the output of trained neural networks, to ensure their robustness against adversarial examples and enable their deployment in safety-critical applications. This paper introduces a new approach to neural network verification using a novel mixed-integer programming rolling-horizon decomposition method. The algorithm leverages the layered structure of neural networks, by employing optimization-based bound-tightening on smaller sub-graphs of the original network in a rolling-horizon fashion. This strategy strikes a balance between "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.05280","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/2401.05280/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":"2401.05280","created_at":"2026-07-05T08:02:23.938705+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.05280v3","created_at":"2026-07-05T08:02:23.938705+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.05280","created_at":"2026-07-05T08:02:23.938705+00:00"},{"alias_kind":"pith_short_12","alias_value":"JXIQUCRY3PXZ","created_at":"2026-07-05T08:02:23.938705+00:00"},{"alias_kind":"pith_short_16","alias_value":"JXIQUCRY3PXZAOME","created_at":"2026-07-05T08:02:23.938705+00:00"},{"alias_kind":"pith_short_8","alias_value":"JXIQUCRY","created_at":"2026-07-05T08:02:23.938705+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/JXIQUCRY3PXZAOME4F3F3ZTLXR","json":"https://pith.science/pith/JXIQUCRY3PXZAOME4F3F3ZTLXR.json","graph_json":"https://pith.science/api/pith-number/JXIQUCRY3PXZAOME4F3F3ZTLXR/graph.json","events_json":"https://pith.science/api/pith-number/JXIQUCRY3PXZAOME4F3F3ZTLXR/events.json","paper":"https://pith.science/paper/JXIQUCRY"},"agent_actions":{"view_html":"https://pith.science/pith/JXIQUCRY3PXZAOME4F3F3ZTLXR","download_json":"https://pith.science/pith/JXIQUCRY3PXZAOME4F3F3ZTLXR.json","view_paper":"https://pith.science/paper/JXIQUCRY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.05280&json=true","fetch_graph":"https://pith.science/api/pith-number/JXIQUCRY3PXZAOME4F3F3ZTLXR/graph.json","fetch_events":"https://pith.science/api/pith-number/JXIQUCRY3PXZAOME4F3F3ZTLXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JXIQUCRY3PXZAOME4F3F3ZTLXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JXIQUCRY3PXZAOME4F3F3ZTLXR/action/storage_attestation","attest_author":"https://pith.science/pith/JXIQUCRY3PXZAOME4F3F3ZTLXR/action/author_attestation","sign_citation":"https://pith.science/pith/JXIQUCRY3PXZAOME4F3F3ZTLXR/action/citation_signature","submit_replication":"https://pith.science/pith/JXIQUCRY3PXZAOME4F3F3ZTLXR/action/replication_record"}},"created_at":"2026-07-05T08:02:23.938705+00:00","updated_at":"2026-07-05T08:02:23.938705+00:00"}