{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:4SJDUTWUA6X4L4N45MWLRLL3T7","short_pith_number":"pith:4SJDUTWU","schema_version":"1.0","canonical_sha256":"e4923a4ed407afc5f1bceb2cb8ad7b9ffe4cf80a3e9e10fcb2df59060b3474e5","source":{"kind":"arxiv","id":"2007.10868","version":2},"attestation_state":"computed","paper":{"title":"Scaling Polyhedral Neural Network Verification on GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christoph M\\\"uller, Fran\\c{c}ois Serre, Gagandeep Singh, Markus P\\\"uschel, Martin Vechev","submitted_at":"2020-07-20T16:09:07Z","abstract_excerpt":"Certifying the robustness of neural networks against adversarial attacks is essential to their reliable adoption in safety-critical systems such as autonomous driving and medical diagnosis. Unfortunately, state-of-the-art verifiers either do not scale to bigger networks or are too imprecise to prove robustness, limiting their practical adoption. In this work, we introduce GPUPoly, a scalable verifier that can prove the robustness of significantly larger deep neural networks than previously possible. The key technical insight behind GPUPoly is the design of custom, sound polyhedra algorithms fo"},"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":"2007.10868","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-20T16:09:07Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"bd13d21a97d7cdb19685688d86ebe8d891d6396964577d8bf959b162d39784c1","abstract_canon_sha256":"10d844bc8ea5417091b73397a0f6b2a0d088a461ac0074589e92dd9a62c468e4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:41:28.224780Z","signature_b64":"7HfbJ80adWM1rPjEotAOjOwv+JEn7OaMc8jWR493g6s4JLj8iuP1JgsNyPbDbsVkf/os1ZBcYi9V5b+aFLOrAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4923a4ed407afc5f1bceb2cb8ad7b9ffe4cf80a3e9e10fcb2df59060b3474e5","last_reissued_at":"2026-07-05T02:41:28.224363Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:41:28.224363Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Polyhedral Neural Network Verification on GPUs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Christoph M\\\"uller, Fran\\c{c}ois Serre, Gagandeep Singh, Markus P\\\"uschel, Martin Vechev","submitted_at":"2020-07-20T16:09:07Z","abstract_excerpt":"Certifying the robustness of neural networks against adversarial attacks is essential to their reliable adoption in safety-critical systems such as autonomous driving and medical diagnosis. Unfortunately, state-of-the-art verifiers either do not scale to bigger networks or are too imprecise to prove robustness, limiting their practical adoption. In this work, we introduce GPUPoly, a scalable verifier that can prove the robustness of significantly larger deep neural networks than previously possible. The key technical insight behind GPUPoly is the design of custom, sound polyhedra algorithms fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.10868","kind":"arxiv","version":2},"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/2007.10868/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":"2007.10868","created_at":"2026-07-05T02:41:28.224422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2007.10868v2","created_at":"2026-07-05T02:41:28.224422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.10868","created_at":"2026-07-05T02:41:28.224422+00:00"},{"alias_kind":"pith_short_12","alias_value":"4SJDUTWUA6X4","created_at":"2026-07-05T02:41:28.224422+00:00"},{"alias_kind":"pith_short_16","alias_value":"4SJDUTWUA6X4L4N4","created_at":"2026-07-05T02:41:28.224422+00:00"},{"alias_kind":"pith_short_8","alias_value":"4SJDUTWU","created_at":"2026-07-05T02:41:28.224422+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.17453","citing_title":"Efficient Neural Network Verification via Order Leading Exploration of Branch-and-Bound Trees","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4SJDUTWUA6X4L4N45MWLRLL3T7","json":"https://pith.science/pith/4SJDUTWUA6X4L4N45MWLRLL3T7.json","graph_json":"https://pith.science/api/pith-number/4SJDUTWUA6X4L4N45MWLRLL3T7/graph.json","events_json":"https://pith.science/api/pith-number/4SJDUTWUA6X4L4N45MWLRLL3T7/events.json","paper":"https://pith.science/paper/4SJDUTWU"},"agent_actions":{"view_html":"https://pith.science/pith/4SJDUTWUA6X4L4N45MWLRLL3T7","download_json":"https://pith.science/pith/4SJDUTWUA6X4L4N45MWLRLL3T7.json","view_paper":"https://pith.science/paper/4SJDUTWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2007.10868&json=true","fetch_graph":"https://pith.science/api/pith-number/4SJDUTWUA6X4L4N45MWLRLL3T7/graph.json","fetch_events":"https://pith.science/api/pith-number/4SJDUTWUA6X4L4N45MWLRLL3T7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4SJDUTWUA6X4L4N45MWLRLL3T7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4SJDUTWUA6X4L4N45MWLRLL3T7/action/storage_attestation","attest_author":"https://pith.science/pith/4SJDUTWUA6X4L4N45MWLRLL3T7/action/author_attestation","sign_citation":"https://pith.science/pith/4SJDUTWUA6X4L4N45MWLRLL3T7/action/citation_signature","submit_replication":"https://pith.science/pith/4SJDUTWUA6X4L4N45MWLRLL3T7/action/replication_record"}},"created_at":"2026-07-05T02:41:28.224422+00:00","updated_at":"2026-07-05T02:41:28.224422+00:00"}