{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:6HLP2KASHMXMGJJVWQAU2LNJ3N","short_pith_number":"pith:6HLP2KAS","schema_version":"1.0","canonical_sha256":"f1d6fd28123b2ec32535b4014d2da9db467fd5aae407126c5680bd588c75193e","source":{"kind":"arxiv","id":"2110.06850","version":4},"attestation_state":"computed","paper":{"title":"Boosting the Certified Robustness of L-infinity Distance Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bohang Zhang, Di He, Du Jiang, Liwei Wang","submitted_at":"2021-10-13T16:43:25Z","abstract_excerpt":"Recently, Zhang et al. (2021) developed a new neural network architecture based on $\\ell_\\infty$-distance functions, which naturally possesses certified $\\ell_\\infty$ robustness by its construction. Despite the novel design and theoretical foundation, so far the model only achieved comparable performance to conventional networks. In this paper, we make the following two contributions: $\\mathrm{(i)}$ We demonstrate that $\\ell_\\infty$-distance nets enjoy a fundamental advantage in certified robustness over conventional networks (under typical certification approaches); $\\mathrm{(ii)}$ With an im"},"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":"2110.06850","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-13T16:43:25Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"b3b2daecd1cfa6a5095aa9c9de1ca6bb0b045bde61d9af53c08b8b1c84348720","abstract_canon_sha256":"84a28dac73287fd4dc97b87c7233432e66998ed7ad406f71f0cf3132c5b4ac8f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:05:13.657126Z","signature_b64":"HhvNirlcageK++eRCy0G1HfJMI3TIWcCb7Z0XFBgof3bgHvYQMbvmck6PKdhHeP7CEXF+BSpdppKpb/aMQZlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f1d6fd28123b2ec32535b4014d2da9db467fd5aae407126c5680bd588c75193e","last_reissued_at":"2026-07-05T04:05:13.656694Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:05:13.656694Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Boosting the Certified Robustness of L-infinity Distance Nets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Bohang Zhang, Di He, Du Jiang, Liwei Wang","submitted_at":"2021-10-13T16:43:25Z","abstract_excerpt":"Recently, Zhang et al. (2021) developed a new neural network architecture based on $\\ell_\\infty$-distance functions, which naturally possesses certified $\\ell_\\infty$ robustness by its construction. Despite the novel design and theoretical foundation, so far the model only achieved comparable performance to conventional networks. In this paper, we make the following two contributions: $\\mathrm{(i)}$ We demonstrate that $\\ell_\\infty$-distance nets enjoy a fundamental advantage in certified robustness over conventional networks (under typical certification approaches); $\\mathrm{(ii)}$ With an im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06850","kind":"arxiv","version":4},"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/2110.06850/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":"2110.06850","created_at":"2026-07-05T04:05:13.656749+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.06850v4","created_at":"2026-07-05T04:05:13.656749+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06850","created_at":"2026-07-05T04:05:13.656749+00:00"},{"alias_kind":"pith_short_12","alias_value":"6HLP2KASHMXM","created_at":"2026-07-05T04:05:13.656749+00:00"},{"alias_kind":"pith_short_16","alias_value":"6HLP2KASHMXMGJJV","created_at":"2026-07-05T04:05:13.656749+00:00"},{"alias_kind":"pith_short_8","alias_value":"6HLP2KAS","created_at":"2026-07-05T04:05:13.656749+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.13303","citing_title":"On the Extreme Variance of Certified Local Robustness Across Model Seeds","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00747","citing_title":"Quantum Interval Bound Propagation for Certified Training of Quantum Neural Networks","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6HLP2KASHMXMGJJVWQAU2LNJ3N","json":"https://pith.science/pith/6HLP2KASHMXMGJJVWQAU2LNJ3N.json","graph_json":"https://pith.science/api/pith-number/6HLP2KASHMXMGJJVWQAU2LNJ3N/graph.json","events_json":"https://pith.science/api/pith-number/6HLP2KASHMXMGJJVWQAU2LNJ3N/events.json","paper":"https://pith.science/paper/6HLP2KAS"},"agent_actions":{"view_html":"https://pith.science/pith/6HLP2KASHMXMGJJVWQAU2LNJ3N","download_json":"https://pith.science/pith/6HLP2KASHMXMGJJVWQAU2LNJ3N.json","view_paper":"https://pith.science/paper/6HLP2KAS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.06850&json=true","fetch_graph":"https://pith.science/api/pith-number/6HLP2KASHMXMGJJVWQAU2LNJ3N/graph.json","fetch_events":"https://pith.science/api/pith-number/6HLP2KASHMXMGJJVWQAU2LNJ3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6HLP2KASHMXMGJJVWQAU2LNJ3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6HLP2KASHMXMGJJVWQAU2LNJ3N/action/storage_attestation","attest_author":"https://pith.science/pith/6HLP2KASHMXMGJJVWQAU2LNJ3N/action/author_attestation","sign_citation":"https://pith.science/pith/6HLP2KASHMXMGJJVWQAU2LNJ3N/action/citation_signature","submit_replication":"https://pith.science/pith/6HLP2KASHMXMGJJVWQAU2LNJ3N/action/replication_record"}},"created_at":"2026-07-05T04:05:13.656749+00:00","updated_at":"2026-07-05T04:05:13.656749+00:00"}