{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DG5KLS75TKKCODKAMWW34BKAMW","short_pith_number":"pith:DG5KLS75","schema_version":"1.0","canonical_sha256":"19baa5cbfd9a94270d4065adbe054065af3034ce1ad216319eeb0a24e3c1f4a6","source":{"kind":"arxiv","id":"2501.15271","version":1},"attestation_state":"computed","paper":{"title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hamid Reza Dehbashi, Hossein Mirzaei, Mohammad Hossein Rohban, Mohammad Jafari, Mohammad Sabokrou, Zeinab Sadat Taghavi","submitted_at":"2025-01-25T16:44:47Z","abstract_excerpt":"Novelty Detection (ND) plays a crucial role in machine learning by identifying new or unseen data during model inference. This capability is especially important for the safe and reliable operation of automated systems. Despite advances in this field, existing techniques often fail to maintain their performance when subject to adversarial attacks. Our research addresses this gap by marrying the merits of nearest-neighbor algorithms with robust features obtained from models pretrained on ImageNet. We focus on enhancing the robustness and performance of ND algorithms. Experimental results demons"},"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":"2501.15271","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-25T16:44:47Z","cross_cats_sorted":[],"title_canon_sha256":"34b94913c34639d4760b0f08b1a854e73553b9b5134eabd037c2137416aa1d34","abstract_canon_sha256":"2f65f83b586328e51e9559a4eb24c23bfdb71d65b47134c2b40dc94d16b74148"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:26.622072Z","signature_b64":"vBuGDtCVr3ZT/YDEW4WmvAwun7B3kDsHQbpXP4SgzbFS7dspx4Gl4K6zUmXB3/BEgYbMnB8yeLuouZ6j1prLBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19baa5cbfd9a94270d4065adbe054065af3034ce1ad216319eeb0a24e3c1f4a6","last_reissued_at":"2026-07-05T10:05:26.621569Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:26.621569Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hamid Reza Dehbashi, Hossein Mirzaei, Mohammad Hossein Rohban, Mohammad Jafari, Mohammad Sabokrou, Zeinab Sadat Taghavi","submitted_at":"2025-01-25T16:44:47Z","abstract_excerpt":"Novelty Detection (ND) plays a crucial role in machine learning by identifying new or unseen data during model inference. This capability is especially important for the safe and reliable operation of automated systems. Despite advances in this field, existing techniques often fail to maintain their performance when subject to adversarial attacks. Our research addresses this gap by marrying the merits of nearest-neighbor algorithms with robust features obtained from models pretrained on ImageNet. We focus on enhancing the robustness and performance of ND algorithms. Experimental results demons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15271","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/2501.15271/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":"2501.15271","created_at":"2026-07-05T10:05:26.621634+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.15271v1","created_at":"2026-07-05T10:05:26.621634+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15271","created_at":"2026-07-05T10:05:26.621634+00:00"},{"alias_kind":"pith_short_12","alias_value":"DG5KLS75TKKC","created_at":"2026-07-05T10:05:26.621634+00:00"},{"alias_kind":"pith_short_16","alias_value":"DG5KLS75TKKCODKA","created_at":"2026-07-05T10:05:26.621634+00:00"},{"alias_kind":"pith_short_8","alias_value":"DG5KLS75","created_at":"2026-07-05T10:05:26.621634+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15271","citing_title":"Killing it with Zero-Shot: Adversarially Robust Novelty Detection","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DG5KLS75TKKCODKAMWW34BKAMW","json":"https://pith.science/pith/DG5KLS75TKKCODKAMWW34BKAMW.json","graph_json":"https://pith.science/api/pith-number/DG5KLS75TKKCODKAMWW34BKAMW/graph.json","events_json":"https://pith.science/api/pith-number/DG5KLS75TKKCODKAMWW34BKAMW/events.json","paper":"https://pith.science/paper/DG5KLS75"},"agent_actions":{"view_html":"https://pith.science/pith/DG5KLS75TKKCODKAMWW34BKAMW","download_json":"https://pith.science/pith/DG5KLS75TKKCODKAMWW34BKAMW.json","view_paper":"https://pith.science/paper/DG5KLS75","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.15271&json=true","fetch_graph":"https://pith.science/api/pith-number/DG5KLS75TKKCODKAMWW34BKAMW/graph.json","fetch_events":"https://pith.science/api/pith-number/DG5KLS75TKKCODKAMWW34BKAMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DG5KLS75TKKCODKAMWW34BKAMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DG5KLS75TKKCODKAMWW34BKAMW/action/storage_attestation","attest_author":"https://pith.science/pith/DG5KLS75TKKCODKAMWW34BKAMW/action/author_attestation","sign_citation":"https://pith.science/pith/DG5KLS75TKKCODKAMWW34BKAMW/action/citation_signature","submit_replication":"https://pith.science/pith/DG5KLS75TKKCODKAMWW34BKAMW/action/replication_record"}},"created_at":"2026-07-05T10:05:26.621634+00:00","updated_at":"2026-07-05T10:05:26.621634+00:00"}