{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q2TC75C5Z4WKHOMFW2SD5ZC5KA","short_pith_number":"pith:Q2TC75C5","schema_version":"1.0","canonical_sha256":"86a62ff45dcf2ca3b985b6a43ee45d500498d17e97adb71601208a2fd48c762b","source":{"kind":"arxiv","id":"2303.14961","version":3},"attestation_state":"computed","paper":{"title":"Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Daniel Korth, Jeanette Miriam Lorenz, Karsten Roscher, Nicola Franco, Stephan Guennemann","submitted_at":"2023-03-27T07:52:58Z","abstract_excerpt":"As the use of machine learning continues to expand, the importance of ensuring its safety cannot be overstated. A key concern in this regard is the ability to identify whether a given sample is from the training distribution, or is an \"Out-Of-Distribution\" (OOD) sample. In addition, adversaries can manipulate OOD samples in ways that lead a classifier to make a confident prediction. In this study, we present a novel approach for certifying the robustness of OOD detection within a $\\ell_2$-norm around the input, regardless of network architecture and without the need for specific components or "},"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":"2303.14961","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-27T07:52:58Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"ce495bbfa75de5a038c115b546d6ce3277e683ef54bf09164be22eddbcb184c9","abstract_canon_sha256":"d9dee58aaeaca4e5426e27d940a49fc057f987cdff0dbe19d3e77176340d1b99"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:52.777566Z","signature_b64":"Hej48GZLGnAxSIhSZ2a80dj6cD9Gpg8H32CEb/f0GfFzFfN21ophDBC7sK94qRn+mv1eYr3gSfE++2uiXOoYAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86a62ff45dcf2ca3b985b6a43ee45d500498d17e97adb71601208a2fd48c762b","last_reissued_at":"2026-07-05T06:39:52.777097Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:52.777097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Denoised Smoothing for Certified and Adversarial Robust Out-Of-Distribution Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Daniel Korth, Jeanette Miriam Lorenz, Karsten Roscher, Nicola Franco, Stephan Guennemann","submitted_at":"2023-03-27T07:52:58Z","abstract_excerpt":"As the use of machine learning continues to expand, the importance of ensuring its safety cannot be overstated. A key concern in this regard is the ability to identify whether a given sample is from the training distribution, or is an \"Out-Of-Distribution\" (OOD) sample. In addition, adversaries can manipulate OOD samples in ways that lead a classifier to make a confident prediction. In this study, we present a novel approach for certifying the robustness of OOD detection within a $\\ell_2$-norm around the input, regardless of network architecture and without the need for specific components or "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14961","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/2303.14961/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":"2303.14961","created_at":"2026-07-05T06:39:52.777153+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.14961v3","created_at":"2026-07-05T06:39:52.777153+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14961","created_at":"2026-07-05T06:39:52.777153+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2TC75C5Z4WK","created_at":"2026-07-05T06:39:52.777153+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2TC75C5Z4WKHOMF","created_at":"2026-07-05T06:39:52.777153+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2TC75C5","created_at":"2026-07-05T06:39:52.777153+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.07690","citing_title":"Fortifying Time Series: DTW-Certified Robust Anomaly Detection","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q2TC75C5Z4WKHOMFW2SD5ZC5KA","json":"https://pith.science/pith/Q2TC75C5Z4WKHOMFW2SD5ZC5KA.json","graph_json":"https://pith.science/api/pith-number/Q2TC75C5Z4WKHOMFW2SD5ZC5KA/graph.json","events_json":"https://pith.science/api/pith-number/Q2TC75C5Z4WKHOMFW2SD5ZC5KA/events.json","paper":"https://pith.science/paper/Q2TC75C5"},"agent_actions":{"view_html":"https://pith.science/pith/Q2TC75C5Z4WKHOMFW2SD5ZC5KA","download_json":"https://pith.science/pith/Q2TC75C5Z4WKHOMFW2SD5ZC5KA.json","view_paper":"https://pith.science/paper/Q2TC75C5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.14961&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2TC75C5Z4WKHOMFW2SD5ZC5KA/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2TC75C5Z4WKHOMFW2SD5ZC5KA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2TC75C5Z4WKHOMFW2SD5ZC5KA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2TC75C5Z4WKHOMFW2SD5ZC5KA/action/storage_attestation","attest_author":"https://pith.science/pith/Q2TC75C5Z4WKHOMFW2SD5ZC5KA/action/author_attestation","sign_citation":"https://pith.science/pith/Q2TC75C5Z4WKHOMFW2SD5ZC5KA/action/citation_signature","submit_replication":"https://pith.science/pith/Q2TC75C5Z4WKHOMFW2SD5ZC5KA/action/replication_record"}},"created_at":"2026-07-05T06:39:52.777153+00:00","updated_at":"2026-07-05T06:39:52.777153+00:00"}