{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UB3YCPLLNMS6R45M7A5ZDMIHR7","short_pith_number":"pith:UB3YCPLL","schema_version":"1.0","canonical_sha256":"a077813d6b6b25e8f3acf83b91b1078fec9449a43b21b4330e35a0dbb1dbc6ef","source":{"kind":"arxiv","id":"2402.07498","version":2},"attestation_state":"computed","paper":{"title":"Accelerated Smoothing: A Scalable Approach to Randomized Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Devansh Bhardwaj, Kshitiz Kaushik, Sarthak Gupta","submitted_at":"2024-02-12T09:07:54Z","abstract_excerpt":"Randomized smoothing has emerged as a potent certifiable defense against adversarial attacks by employing smoothing noises from specific distributions to ensure the robustness of a smoothed classifier. However, the utilization of Monte Carlo sampling in this process introduces a compute-intensive element, which constrains the practicality of randomized smoothing on a larger scale. To address this limitation, we propose a novel approach that replaces Monte Carlo sampling with the training of a surrogate neural network. Through extensive experimentation in various settings, we demonstrate the ef"},"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":"2402.07498","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-02-12T09:07:54Z","cross_cats_sorted":[],"title_canon_sha256":"dd09dbe98917217d8647a087db33df77740dfa0f785022052f1452c40dd1eb41","abstract_canon_sha256":"a2cc31e39983dafb2af923482cbd4fc3213523912ad2f0648817ce53c622e6b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:45.498367Z","signature_b64":"3DLePLalnZjiZORgbuAC2bADIKxGB/OeFSTdpafDCrJ0es5yRCkYtHef4D6H00mzXYPPvMEyZOzjIzqOrEUdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a077813d6b6b25e8f3acf83b91b1078fec9449a43b21b4330e35a0dbb1dbc6ef","last_reissued_at":"2026-07-05T10:41:45.497857Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:45.497857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerated Smoothing: A Scalable Approach to Randomized Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Devansh Bhardwaj, Kshitiz Kaushik, Sarthak Gupta","submitted_at":"2024-02-12T09:07:54Z","abstract_excerpt":"Randomized smoothing has emerged as a potent certifiable defense against adversarial attacks by employing smoothing noises from specific distributions to ensure the robustness of a smoothed classifier. However, the utilization of Monte Carlo sampling in this process introduces a compute-intensive element, which constrains the practicality of randomized smoothing on a larger scale. To address this limitation, we propose a novel approach that replaces Monte Carlo sampling with the training of a surrogate neural network. Through extensive experimentation in various settings, we demonstrate the ef"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07498","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/2402.07498/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":"2402.07498","created_at":"2026-07-05T10:41:45.497915+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.07498v2","created_at":"2026-07-05T10:41:45.497915+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07498","created_at":"2026-07-05T10:41:45.497915+00:00"},{"alias_kind":"pith_short_12","alias_value":"UB3YCPLLNMS6","created_at":"2026-07-05T10:41:45.497915+00:00"},{"alias_kind":"pith_short_16","alias_value":"UB3YCPLLNMS6R45M","created_at":"2026-07-05T10:41:45.497915+00:00"},{"alias_kind":"pith_short_8","alias_value":"UB3YCPLL","created_at":"2026-07-05T10:41:45.497915+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02876","citing_title":"RRISE: Robust Radius Inference via a Surrogate Estimator","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UB3YCPLLNMS6R45M7A5ZDMIHR7","json":"https://pith.science/pith/UB3YCPLLNMS6R45M7A5ZDMIHR7.json","graph_json":"https://pith.science/api/pith-number/UB3YCPLLNMS6R45M7A5ZDMIHR7/graph.json","events_json":"https://pith.science/api/pith-number/UB3YCPLLNMS6R45M7A5ZDMIHR7/events.json","paper":"https://pith.science/paper/UB3YCPLL"},"agent_actions":{"view_html":"https://pith.science/pith/UB3YCPLLNMS6R45M7A5ZDMIHR7","download_json":"https://pith.science/pith/UB3YCPLLNMS6R45M7A5ZDMIHR7.json","view_paper":"https://pith.science/paper/UB3YCPLL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.07498&json=true","fetch_graph":"https://pith.science/api/pith-number/UB3YCPLLNMS6R45M7A5ZDMIHR7/graph.json","fetch_events":"https://pith.science/api/pith-number/UB3YCPLLNMS6R45M7A5ZDMIHR7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UB3YCPLLNMS6R45M7A5ZDMIHR7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UB3YCPLLNMS6R45M7A5ZDMIHR7/action/storage_attestation","attest_author":"https://pith.science/pith/UB3YCPLLNMS6R45M7A5ZDMIHR7/action/author_attestation","sign_citation":"https://pith.science/pith/UB3YCPLLNMS6R45M7A5ZDMIHR7/action/citation_signature","submit_replication":"https://pith.science/pith/UB3YCPLLNMS6R45M7A5ZDMIHR7/action/replication_record"}},"created_at":"2026-07-05T10:41:45.497915+00:00","updated_at":"2026-07-05T10:41:45.497915+00:00"}