{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:I26MHBZCK4X2YLA3STMEERDAIM","short_pith_number":"pith:I26MHBZC","schema_version":"1.0","canonical_sha256":"46bcc38722572fac2c1b94d84244604339153b66b8d17d3d6e0d0c50a7f63566","source":{"kind":"arxiv","id":"2301.12549","version":3},"attestation_state":"computed","paper":{"title":"Unlocking Deterministic Robustness Certification on ImageNet","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andy Zou, Kai Hu, Klas Leino, Matt Fredrikson, Zifan Wang","submitted_at":"2023-01-29T21:40:04Z","abstract_excerpt":"Despite the promise of Lipschitz-based methods for provably-robust deep learning with deterministic guarantees, current state-of-the-art results are limited to feed-forward Convolutional Networks (ConvNets) on low-dimensional data, such as CIFAR-10. This paper investigates strategies for expanding certifiably robust training to larger, deeper models. A key challenge in certifying deep networks is efficient calculation of the Lipschitz bound for residual blocks found in ResNet and ViT architectures. We show that fast ways of bounding the Lipschitz constant for conventional ResNets are loose, an"},"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":"2301.12549","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-01-29T21:40:04Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"9cee9ff79e589e3693b7b29d023526bac66ff47fc25cd45703120dc337c0c12f","abstract_canon_sha256":"45cc314ae42fed18947db59d31052afacbfc1ae6d788081f433a46dfb2b49cd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:22.769875Z","signature_b64":"KfU6f6lcN/FR7/vzU+F0jMXXGoD3oqETZShikwnyMbLNfoL0sqPLzIG0fLHrpT9abe2HSsst5JPH8gxWh+RXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46bcc38722572fac2c1b94d84244604339153b66b8d17d3d6e0d0c50a7f63566","last_reissued_at":"2026-07-05T07:06:22.769477Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:22.769477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unlocking Deterministic Robustness Certification on ImageNet","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Andy Zou, Kai Hu, Klas Leino, Matt Fredrikson, Zifan Wang","submitted_at":"2023-01-29T21:40:04Z","abstract_excerpt":"Despite the promise of Lipschitz-based methods for provably-robust deep learning with deterministic guarantees, current state-of-the-art results are limited to feed-forward Convolutional Networks (ConvNets) on low-dimensional data, such as CIFAR-10. This paper investigates strategies for expanding certifiably robust training to larger, deeper models. A key challenge in certifying deep networks is efficient calculation of the Lipschitz bound for residual blocks found in ResNet and ViT architectures. We show that fast ways of bounding the Lipschitz constant for conventional ResNets are loose, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.12549","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/2301.12549/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":"2301.12549","created_at":"2026-07-05T07:06:22.769535+00:00"},{"alias_kind":"arxiv_version","alias_value":"2301.12549v3","created_at":"2026-07-05T07:06:22.769535+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.12549","created_at":"2026-07-05T07:06:22.769535+00:00"},{"alias_kind":"pith_short_12","alias_value":"I26MHBZCK4X2","created_at":"2026-07-05T07:06:22.769535+00:00"},{"alias_kind":"pith_short_16","alias_value":"I26MHBZCK4X2YLA3","created_at":"2026-07-05T07:06:22.769535+00:00"},{"alias_kind":"pith_short_8","alias_value":"I26MHBZC","created_at":"2026-07-05T07:06:22.769535+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/I26MHBZCK4X2YLA3STMEERDAIM","json":"https://pith.science/pith/I26MHBZCK4X2YLA3STMEERDAIM.json","graph_json":"https://pith.science/api/pith-number/I26MHBZCK4X2YLA3STMEERDAIM/graph.json","events_json":"https://pith.science/api/pith-number/I26MHBZCK4X2YLA3STMEERDAIM/events.json","paper":"https://pith.science/paper/I26MHBZC"},"agent_actions":{"view_html":"https://pith.science/pith/I26MHBZCK4X2YLA3STMEERDAIM","download_json":"https://pith.science/pith/I26MHBZCK4X2YLA3STMEERDAIM.json","view_paper":"https://pith.science/paper/I26MHBZC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2301.12549&json=true","fetch_graph":"https://pith.science/api/pith-number/I26MHBZCK4X2YLA3STMEERDAIM/graph.json","fetch_events":"https://pith.science/api/pith-number/I26MHBZCK4X2YLA3STMEERDAIM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I26MHBZCK4X2YLA3STMEERDAIM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I26MHBZCK4X2YLA3STMEERDAIM/action/storage_attestation","attest_author":"https://pith.science/pith/I26MHBZCK4X2YLA3STMEERDAIM/action/author_attestation","sign_citation":"https://pith.science/pith/I26MHBZCK4X2YLA3STMEERDAIM/action/citation_signature","submit_replication":"https://pith.science/pith/I26MHBZCK4X2YLA3STMEERDAIM/action/replication_record"}},"created_at":"2026-07-05T07:06:22.769535+00:00","updated_at":"2026-07-05T07:06:22.769535+00:00"}