{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:KKLEMNIPPWDETZ7KGNDBXT7DXQ","short_pith_number":"pith:KKLEMNIP","schema_version":"1.0","canonical_sha256":"529646350f7d8649e7ea33461bcfe3bc099976b2aa60dd62920c30bdc06a6100","source":{"kind":"arxiv","id":"2102.08452","version":2},"attestation_state":"computed","paper":{"title":"Globally-Robust Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Klas Leino, Matt Fredrikson, Zifan Wang","submitted_at":"2021-02-16T21:10:52Z","abstract_excerpt":"The threat of adversarial examples has motivated work on training certifiably robust neural networks to facilitate efficient verification of local robustness at inference time. We formalize a notion of global robustness, which captures the operational properties of on-line local robustness certification while yielding a natural learning objective for robust training. We show that widely-used architectures can be easily adapted to this objective by incorporating efficient global Lipschitz bounds into the network, yielding certifiably-robust models by construction that achieve state-of-the-art v"},"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":"2102.08452","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-02-16T21:10:52Z","cross_cats_sorted":["cs.CR","stat.ML"],"title_canon_sha256":"b9f1447901bfbc92a927528ff6750d40937e78c3de8ded9d0f5eda615ad45383","abstract_canon_sha256":"810345a98f6f00ad1432d96b210b2a10994f22103539d2beea0db6125a9381f6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:48:36.084556Z","signature_b64":"oXaBDiAks4HxylLUCWJ5kRwqNCjpbGlwH8Z1hx4JuWPsHDjbY/8RkUFkndxDn2NUWMKEjkPe+868FlgyftUtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"529646350f7d8649e7ea33461bcfe3bc099976b2aa60dd62920c30bdc06a6100","last_reissued_at":"2026-07-05T02:48:36.084115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:48:36.084115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Globally-Robust Neural Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Klas Leino, Matt Fredrikson, Zifan Wang","submitted_at":"2021-02-16T21:10:52Z","abstract_excerpt":"The threat of adversarial examples has motivated work on training certifiably robust neural networks to facilitate efficient verification of local robustness at inference time. We formalize a notion of global robustness, which captures the operational properties of on-line local robustness certification while yielding a natural learning objective for robust training. We show that widely-used architectures can be easily adapted to this objective by incorporating efficient global Lipschitz bounds into the network, yielding certifiably-robust models by construction that achieve state-of-the-art v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.08452","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/2102.08452/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":"2102.08452","created_at":"2026-07-05T02:48:36.084179+00:00"},{"alias_kind":"arxiv_version","alias_value":"2102.08452v2","created_at":"2026-07-05T02:48:36.084179+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.08452","created_at":"2026-07-05T02:48:36.084179+00:00"},{"alias_kind":"pith_short_12","alias_value":"KKLEMNIPPWDE","created_at":"2026-07-05T02:48:36.084179+00:00"},{"alias_kind":"pith_short_16","alias_value":"KKLEMNIPPWDETZ7K","created_at":"2026-07-05T02:48:36.084179+00:00"},{"alias_kind":"pith_short_8","alias_value":"KKLEMNIP","created_at":"2026-07-05T02:48:36.084179+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/KKLEMNIPPWDETZ7KGNDBXT7DXQ","json":"https://pith.science/pith/KKLEMNIPPWDETZ7KGNDBXT7DXQ.json","graph_json":"https://pith.science/api/pith-number/KKLEMNIPPWDETZ7KGNDBXT7DXQ/graph.json","events_json":"https://pith.science/api/pith-number/KKLEMNIPPWDETZ7KGNDBXT7DXQ/events.json","paper":"https://pith.science/paper/KKLEMNIP"},"agent_actions":{"view_html":"https://pith.science/pith/KKLEMNIPPWDETZ7KGNDBXT7DXQ","download_json":"https://pith.science/pith/KKLEMNIPPWDETZ7KGNDBXT7DXQ.json","view_paper":"https://pith.science/paper/KKLEMNIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2102.08452&json=true","fetch_graph":"https://pith.science/api/pith-number/KKLEMNIPPWDETZ7KGNDBXT7DXQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KKLEMNIPPWDETZ7KGNDBXT7DXQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KKLEMNIPPWDETZ7KGNDBXT7DXQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KKLEMNIPPWDETZ7KGNDBXT7DXQ/action/storage_attestation","attest_author":"https://pith.science/pith/KKLEMNIPPWDETZ7KGNDBXT7DXQ/action/author_attestation","sign_citation":"https://pith.science/pith/KKLEMNIPPWDETZ7KGNDBXT7DXQ/action/citation_signature","submit_replication":"https://pith.science/pith/KKLEMNIPPWDETZ7KGNDBXT7DXQ/action/replication_record"}},"created_at":"2026-07-05T02:48:36.084179+00:00","updated_at":"2026-07-05T02:48:36.084179+00:00"}