{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TVIZX3FRIYILQPUGK7D7HRTEZE","short_pith_number":"pith:TVIZX3FR","schema_version":"1.0","canonical_sha256":"9d519becb14610b83e8657c7f3c664c920d10927476fab5ebd9b28cdde3c46f1","source":{"kind":"arxiv","id":"2306.15221","version":1},"attestation_state":"computed","paper":{"title":"[Re] Double Sampling Randomized Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Abhay Kumar, Aryan Gupta, Harsh Dugar, Sarthak Gupta","submitted_at":"2023-06-27T05:46:18Z","abstract_excerpt":"This paper is a contribution to the reproducibility challenge in the field of machine learning, specifically addressing the issue of certifying the robustness of neural networks (NNs) against adversarial perturbations. The proposed Double Sampling Randomized Smoothing (DSRS) framework overcomes the limitations of existing methods by using an additional smoothing distribution to improve the robustness certification. The paper provides a clear manifestation of DSRS for a generalized family of Gaussian smoothing and a computationally efficient method for implementation. The experiments on MNIST a"},"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":"2306.15221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-27T05:46:18Z","cross_cats_sorted":["cs.CR","math.ST","stat.TH"],"title_canon_sha256":"3159ba4820ba9159e5c8631a1a54e6355f5070581e3f7283ba7da86fe5450304","abstract_canon_sha256":"5c8ee1b4cb99a98c3b6c99226e9fb272830524279cbade7412ba43078333b1c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:24:55.836588Z","signature_b64":"ZMKDsMNhFHzY7WN44nZYMIGhbsail7+t3Zygv8trzubY3xf7loh1nO19omT4Pd1HFNDPnaRs+IzdSnaFf5njDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d519becb14610b83e8657c7f3c664c920d10927476fab5ebd9b28cdde3c46f1","last_reissued_at":"2026-07-05T06:24:55.836078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:24:55.836078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"[Re] Double Sampling Randomized Smoothing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","math.ST","stat.TH"],"primary_cat":"cs.LG","authors_text":"Abhay Kumar, Aryan Gupta, Harsh Dugar, Sarthak Gupta","submitted_at":"2023-06-27T05:46:18Z","abstract_excerpt":"This paper is a contribution to the reproducibility challenge in the field of machine learning, specifically addressing the issue of certifying the robustness of neural networks (NNs) against adversarial perturbations. The proposed Double Sampling Randomized Smoothing (DSRS) framework overcomes the limitations of existing methods by using an additional smoothing distribution to improve the robustness certification. The paper provides a clear manifestation of DSRS for a generalized family of Gaussian smoothing and a computationally efficient method for implementation. The experiments on MNIST a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.15221","kind":"arxiv","version":1},"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/2306.15221/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":"2306.15221","created_at":"2026-07-05T06:24:55.836146+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.15221v1","created_at":"2026-07-05T06:24:55.836146+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.15221","created_at":"2026-07-05T06:24:55.836146+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVIZX3FRIYIL","created_at":"2026-07-05T06:24:55.836146+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVIZX3FRIYILQPUG","created_at":"2026-07-05T06:24:55.836146+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVIZX3FR","created_at":"2026-07-05T06:24:55.836146+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/TVIZX3FRIYILQPUGK7D7HRTEZE","json":"https://pith.science/pith/TVIZX3FRIYILQPUGK7D7HRTEZE.json","graph_json":"https://pith.science/api/pith-number/TVIZX3FRIYILQPUGK7D7HRTEZE/graph.json","events_json":"https://pith.science/api/pith-number/TVIZX3FRIYILQPUGK7D7HRTEZE/events.json","paper":"https://pith.science/paper/TVIZX3FR"},"agent_actions":{"view_html":"https://pith.science/pith/TVIZX3FRIYILQPUGK7D7HRTEZE","download_json":"https://pith.science/pith/TVIZX3FRIYILQPUGK7D7HRTEZE.json","view_paper":"https://pith.science/paper/TVIZX3FR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.15221&json=true","fetch_graph":"https://pith.science/api/pith-number/TVIZX3FRIYILQPUGK7D7HRTEZE/graph.json","fetch_events":"https://pith.science/api/pith-number/TVIZX3FRIYILQPUGK7D7HRTEZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVIZX3FRIYILQPUGK7D7HRTEZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVIZX3FRIYILQPUGK7D7HRTEZE/action/storage_attestation","attest_author":"https://pith.science/pith/TVIZX3FRIYILQPUGK7D7HRTEZE/action/author_attestation","sign_citation":"https://pith.science/pith/TVIZX3FRIYILQPUGK7D7HRTEZE/action/citation_signature","submit_replication":"https://pith.science/pith/TVIZX3FRIYILQPUGK7D7HRTEZE/action/replication_record"}},"created_at":"2026-07-05T06:24:55.836146+00:00","updated_at":"2026-07-05T06:24:55.836146+00:00"}