{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QYM3AL5XARUWN2AJ5VWIEG2ITX","short_pith_number":"pith:QYM3AL5X","schema_version":"1.0","canonical_sha256":"8619b02fb7046966e809ed6c821b489dfde14d82fc7e521ae8197112e458b454","source":{"kind":"arxiv","id":"2405.20556","version":1},"attestation_state":"computed","paper":{"title":"Certifying Global Robustness for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guannan Zhao, Hai Zhou, Shuyu Kong, You Li, Yunqi He","submitted_at":"2024-05-31T00:46:04Z","abstract_excerpt":"A globally robust deep neural network resists perturbations on all meaningful inputs. Current robustness certification methods emphasize local robustness, struggling to scale and generalize. This paper presents a systematic and efficient method to evaluate and verify global robustness for deep neural networks, leveraging the PAC verification framework for solid guarantees on verification results. We utilize probabilistic programs to characterize meaningful input regions, setting a realistic standard for global robustness. Additionally, we introduce the cumulative robustness curve as a criterio"},"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":"2405.20556","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T00:46:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f3aa5f3e816a614152e6469582ac6304757ad54a7c0d10aac2cbacc4ee1f4ed3","abstract_canon_sha256":"f70f6e347ee660652bce9cb6ce769f2078a4d1f0090b881a180b08bff771fef7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:25:38.986473Z","signature_b64":"vnkxxYPGkxUTzb3UAnSf4SVDlLtn2q/zBIuDSC0A9TBqEnYXw5HeirqazQI8ZwxEgcSDel7/VG1QJJ+UuPlCAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8619b02fb7046966e809ed6c821b489dfde14d82fc7e521ae8197112e458b454","last_reissued_at":"2026-07-05T08:25:38.986056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:25:38.986056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Certifying Global Robustness for Deep Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guannan Zhao, Hai Zhou, Shuyu Kong, You Li, Yunqi He","submitted_at":"2024-05-31T00:46:04Z","abstract_excerpt":"A globally robust deep neural network resists perturbations on all meaningful inputs. Current robustness certification methods emphasize local robustness, struggling to scale and generalize. This paper presents a systematic and efficient method to evaluate and verify global robustness for deep neural networks, leveraging the PAC verification framework for solid guarantees on verification results. We utilize probabilistic programs to characterize meaningful input regions, setting a realistic standard for global robustness. Additionally, we introduce the cumulative robustness curve as a criterio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20556","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/2405.20556/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":"2405.20556","created_at":"2026-07-05T08:25:38.986108+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20556v1","created_at":"2026-07-05T08:25:38.986108+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20556","created_at":"2026-07-05T08:25:38.986108+00:00"},{"alias_kind":"pith_short_12","alias_value":"QYM3AL5XARUW","created_at":"2026-07-05T08:25:38.986108+00:00"},{"alias_kind":"pith_short_16","alias_value":"QYM3AL5XARUWN2AJ","created_at":"2026-07-05T08:25:38.986108+00:00"},{"alias_kind":"pith_short_8","alias_value":"QYM3AL5X","created_at":"2026-07-05T08:25:38.986108+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/QYM3AL5XARUWN2AJ5VWIEG2ITX","json":"https://pith.science/pith/QYM3AL5XARUWN2AJ5VWIEG2ITX.json","graph_json":"https://pith.science/api/pith-number/QYM3AL5XARUWN2AJ5VWIEG2ITX/graph.json","events_json":"https://pith.science/api/pith-number/QYM3AL5XARUWN2AJ5VWIEG2ITX/events.json","paper":"https://pith.science/paper/QYM3AL5X"},"agent_actions":{"view_html":"https://pith.science/pith/QYM3AL5XARUWN2AJ5VWIEG2ITX","download_json":"https://pith.science/pith/QYM3AL5XARUWN2AJ5VWIEG2ITX.json","view_paper":"https://pith.science/paper/QYM3AL5X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20556&json=true","fetch_graph":"https://pith.science/api/pith-number/QYM3AL5XARUWN2AJ5VWIEG2ITX/graph.json","fetch_events":"https://pith.science/api/pith-number/QYM3AL5XARUWN2AJ5VWIEG2ITX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QYM3AL5XARUWN2AJ5VWIEG2ITX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QYM3AL5XARUWN2AJ5VWIEG2ITX/action/storage_attestation","attest_author":"https://pith.science/pith/QYM3AL5XARUWN2AJ5VWIEG2ITX/action/author_attestation","sign_citation":"https://pith.science/pith/QYM3AL5XARUWN2AJ5VWIEG2ITX/action/citation_signature","submit_replication":"https://pith.science/pith/QYM3AL5XARUWN2AJ5VWIEG2ITX/action/replication_record"}},"created_at":"2026-07-05T08:25:38.986108+00:00","updated_at":"2026-07-05T08:25:38.986108+00:00"}