{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HZPLDSVEGPOWGQ34SLG2HPLFA4","short_pith_number":"pith:HZPLDSVE","schema_version":"1.0","canonical_sha256":"3e5eb1caa433dd63437c92cda3bd65071e7570dc12731020eda0f31fce3a4ff2","source":{"kind":"arxiv","id":"2309.16883","version":4},"attestation_state":"computed","paper":{"title":"The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre Allauzen, Alexandre Araujo, Blaise Delattre, Quentin Barth\\'elemy","submitted_at":"2023-09-28T22:41:47Z","abstract_excerpt":"Real-life applications of deep neural networks are hindered by their unsteady predictions when faced with noisy inputs and adversarial attacks. The certified radius in this context is a crucial indicator of the robustness of models. However how to design an efficient classifier with an associated certified radius? Randomized smoothing provides a promising framework by relying on noise injection into the inputs to obtain a smoothed and robust classifier. In this paper, we first show that the variance introduced by the Monte-Carlo sampling in the randomized smoothing procedure estimate closely i"},"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":"2309.16883","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-09-28T22:41:47Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"d5cda56d03026bfdda3eab41837a2e5d2b58ece2f78a61b70912838cd95a17ef","abstract_canon_sha256":"fe40a1126c81ba8b36f2b7ce8b9803d68e716ca879b9a536b914f35f8fc21150"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:56:52.840403Z","signature_b64":"njBKNrVzoRWVC7ioBUQ9e40a91LoAWPHKh0urlAZpaujR9eAf3GmccA57AW3pAyC3xsvJjy3U+F/FScZNV7XCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e5eb1caa433dd63437c92cda3bd65071e7570dc12731020eda0f31fce3a4ff2","last_reissued_at":"2026-07-05T07:56:52.839902Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:56:52.839902Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Alexandre Allauzen, Alexandre Araujo, Blaise Delattre, Quentin Barth\\'elemy","submitted_at":"2023-09-28T22:41:47Z","abstract_excerpt":"Real-life applications of deep neural networks are hindered by their unsteady predictions when faced with noisy inputs and adversarial attacks. The certified radius in this context is a crucial indicator of the robustness of models. However how to design an efficient classifier with an associated certified radius? Randomized smoothing provides a promising framework by relying on noise injection into the inputs to obtain a smoothed and robust classifier. In this paper, we first show that the variance introduced by the Monte-Carlo sampling in the randomized smoothing procedure estimate closely i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.16883","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/2309.16883/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":"2309.16883","created_at":"2026-07-05T07:56:52.839960+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.16883v4","created_at":"2026-07-05T07:56:52.839960+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.16883","created_at":"2026-07-05T07:56:52.839960+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZPLDSVEGPOW","created_at":"2026-07-05T07:56:52.839960+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZPLDSVEGPOWGQ34","created_at":"2026-07-05T07:56:52.839960+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZPLDSVE","created_at":"2026-07-05T07:56:52.839960+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/HZPLDSVEGPOWGQ34SLG2HPLFA4","json":"https://pith.science/pith/HZPLDSVEGPOWGQ34SLG2HPLFA4.json","graph_json":"https://pith.science/api/pith-number/HZPLDSVEGPOWGQ34SLG2HPLFA4/graph.json","events_json":"https://pith.science/api/pith-number/HZPLDSVEGPOWGQ34SLG2HPLFA4/events.json","paper":"https://pith.science/paper/HZPLDSVE"},"agent_actions":{"view_html":"https://pith.science/pith/HZPLDSVEGPOWGQ34SLG2HPLFA4","download_json":"https://pith.science/pith/HZPLDSVEGPOWGQ34SLG2HPLFA4.json","view_paper":"https://pith.science/paper/HZPLDSVE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.16883&json=true","fetch_graph":"https://pith.science/api/pith-number/HZPLDSVEGPOWGQ34SLG2HPLFA4/graph.json","fetch_events":"https://pith.science/api/pith-number/HZPLDSVEGPOWGQ34SLG2HPLFA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZPLDSVEGPOWGQ34SLG2HPLFA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZPLDSVEGPOWGQ34SLG2HPLFA4/action/storage_attestation","attest_author":"https://pith.science/pith/HZPLDSVEGPOWGQ34SLG2HPLFA4/action/author_attestation","sign_citation":"https://pith.science/pith/HZPLDSVEGPOWGQ34SLG2HPLFA4/action/citation_signature","submit_replication":"https://pith.science/pith/HZPLDSVEGPOWGQ34SLG2HPLFA4/action/replication_record"}},"created_at":"2026-07-05T07:56:52.839960+00:00","updated_at":"2026-07-05T07:56:52.839960+00:00"}