{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:XXINXMSYG7QWH7FLF4IE3JHZQA","short_pith_number":"pith:XXINXMSY","schema_version":"1.0","canonical_sha256":"bdd0dbb25837e163fcab2f104da4f980336b1ebde4af8de631896b0d9c42bafb","source":{"kind":"arxiv","id":"2407.06635","version":1},"attestation_state":"computed","paper":{"title":"Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Bernhard Kainz, Christos Tzelepis, Giacomo Tarroni, Matthew Baugh, Sergio Naval Marimont, Vasilis Siomos","submitted_at":"2024-07-09T08:02:46Z","abstract_excerpt":"Unsupervised Anomaly Detection (UAD) methods aim to identify anomalies in test samples comparing them with a normative distribution learned from a dataset known to be anomaly-free. Approaches based on generative models offer interpretability by generating anomaly-free versions of test images, but are typically unable to identify subtle anomalies. Alternatively, approaches using feature modelling or self-supervised methods, such as the ones relying on synthetically generated anomalies, do not provide out-of-the-box interpretability. In this work, we present a novel method that combines the stre"},"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":"2407.06635","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-09T08:02:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"6a9d1773295add30bbdf9c9c3b877f6ff4df7eeed11ca3e0371d78e25fbee0ef","abstract_canon_sha256":"fce9b728e1e057b33e32bb4e1758bcfe32800bbf6fe6cf5d218a812eae4cb815"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:41:51.406264Z","signature_b64":"A7It/4+EQuzavEhYlvY5Fvh+QdoHkcdzs757Dj745eVvliymTRnRidbGZwyKrVD2yqGQD0y+uxl9wv1Ff4VHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bdd0dbb25837e163fcab2f104da4f980336b1ebde4af8de631896b0d9c42bafb","last_reissued_at":"2026-07-05T08:41:51.405856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:41:51.405856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Ensembled Cold-Diffusion Restorations for Unsupervised Anomaly Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CV","authors_text":"Bernhard Kainz, Christos Tzelepis, Giacomo Tarroni, Matthew Baugh, Sergio Naval Marimont, Vasilis Siomos","submitted_at":"2024-07-09T08:02:46Z","abstract_excerpt":"Unsupervised Anomaly Detection (UAD) methods aim to identify anomalies in test samples comparing them with a normative distribution learned from a dataset known to be anomaly-free. Approaches based on generative models offer interpretability by generating anomaly-free versions of test images, but are typically unable to identify subtle anomalies. Alternatively, approaches using feature modelling or self-supervised methods, such as the ones relying on synthetically generated anomalies, do not provide out-of-the-box interpretability. In this work, we present a novel method that combines the stre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06635","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/2407.06635/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":"2407.06635","created_at":"2026-07-05T08:41:51.405919+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06635v1","created_at":"2026-07-05T08:41:51.405919+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06635","created_at":"2026-07-05T08:41:51.405919+00:00"},{"alias_kind":"pith_short_12","alias_value":"XXINXMSYG7QW","created_at":"2026-07-05T08:41:51.405919+00:00"},{"alias_kind":"pith_short_16","alias_value":"XXINXMSYG7QWH7FL","created_at":"2026-07-05T08:41:51.405919+00:00"},{"alias_kind":"pith_short_8","alias_value":"XXINXMSY","created_at":"2026-07-05T08:41:51.405919+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/XXINXMSYG7QWH7FLF4IE3JHZQA","json":"https://pith.science/pith/XXINXMSYG7QWH7FLF4IE3JHZQA.json","graph_json":"https://pith.science/api/pith-number/XXINXMSYG7QWH7FLF4IE3JHZQA/graph.json","events_json":"https://pith.science/api/pith-number/XXINXMSYG7QWH7FLF4IE3JHZQA/events.json","paper":"https://pith.science/paper/XXINXMSY"},"agent_actions":{"view_html":"https://pith.science/pith/XXINXMSYG7QWH7FLF4IE3JHZQA","download_json":"https://pith.science/pith/XXINXMSYG7QWH7FLF4IE3JHZQA.json","view_paper":"https://pith.science/paper/XXINXMSY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.06635&json=true","fetch_graph":"https://pith.science/api/pith-number/XXINXMSYG7QWH7FLF4IE3JHZQA/graph.json","fetch_events":"https://pith.science/api/pith-number/XXINXMSYG7QWH7FLF4IE3JHZQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XXINXMSYG7QWH7FLF4IE3JHZQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XXINXMSYG7QWH7FLF4IE3JHZQA/action/storage_attestation","attest_author":"https://pith.science/pith/XXINXMSYG7QWH7FLF4IE3JHZQA/action/author_attestation","sign_citation":"https://pith.science/pith/XXINXMSYG7QWH7FLF4IE3JHZQA/action/citation_signature","submit_replication":"https://pith.science/pith/XXINXMSYG7QWH7FLF4IE3JHZQA/action/replication_record"}},"created_at":"2026-07-05T08:41:51.405919+00:00","updated_at":"2026-07-05T08:41:51.405919+00:00"}