{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LV3BVZVGYI7IYNXRBI5ONPBB5V","short_pith_number":"pith:LV3BVZVG","schema_version":"1.0","canonical_sha256":"5d761ae6a6c23e8c36f10a3ae6bc21ed713dde99b36ba3e7d2c03b112179a11a","source":{"kind":"arxiv","id":"2507.22692","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Image Anomaly Detection Using Generative Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amaan Valiuddin, Christiaan Viviers, Fons van der Sommen, Francisco Caetano, Lemar Abdi","submitted_at":"2025-07-30T13:56:36Z","abstract_excerpt":"Detecting out-of-distribution (OOD) inputs is pivotal for deploying safe vision systems in open-world environments. We revisit diffusion models, not as generators, but as universal perceptual templates for OOD detection. This research explores the use of score-based generative models as foundational tools for semantic anomaly detection across unseen datasets. Specifically, we leverage the denoising trajectories of Denoising Diffusion Models (DDMs) as a rich source of texture and semantic information. By analyzing Stein score errors, amplified through the Structural Similarity Index Metric (SSI"},"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":"2507.22692","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-30T13:56:36Z","cross_cats_sorted":[],"title_canon_sha256":"4e747832081b05c9b3d67467d5e6bd9d488d3205c0e907b8e504aee6d5573fd5","abstract_canon_sha256":"f4e39713aa6c0c871774ba15e4c302d021bb87a2d0d4023d7c669906a1b8d0f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:47.219415Z","signature_b64":"2mbEE8zhyXE2F/xczzJOT2lWI0ALui99L91+5iKmfAR1YLO5eTE7i5yqvMS5TdD3Gm29LvbtjX/pgzA0Xg89Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d761ae6a6c23e8c36f10a3ae6bc21ed713dde99b36ba3e7d2c03b112179a11a","last_reissued_at":"2026-07-05T11:45:47.218944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:47.218944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Image Anomaly Detection Using Generative Foundation Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Amaan Valiuddin, Christiaan Viviers, Fons van der Sommen, Francisco Caetano, Lemar Abdi","submitted_at":"2025-07-30T13:56:36Z","abstract_excerpt":"Detecting out-of-distribution (OOD) inputs is pivotal for deploying safe vision systems in open-world environments. We revisit diffusion models, not as generators, but as universal perceptual templates for OOD detection. This research explores the use of score-based generative models as foundational tools for semantic anomaly detection across unseen datasets. Specifically, we leverage the denoising trajectories of Denoising Diffusion Models (DDMs) as a rich source of texture and semantic information. By analyzing Stein score errors, amplified through the Structural Similarity Index Metric (SSI"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22692","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/2507.22692/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":"2507.22692","created_at":"2026-07-05T11:45:47.218997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22692v1","created_at":"2026-07-05T11:45:47.218997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22692","created_at":"2026-07-05T11:45:47.218997+00:00"},{"alias_kind":"pith_short_12","alias_value":"LV3BVZVGYI7I","created_at":"2026-07-05T11:45:47.218997+00:00"},{"alias_kind":"pith_short_16","alias_value":"LV3BVZVGYI7IYNXR","created_at":"2026-07-05T11:45:47.218997+00:00"},{"alias_kind":"pith_short_8","alias_value":"LV3BVZVG","created_at":"2026-07-05T11:45:47.218997+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.21717","citing_title":"Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2603.21717","citing_title":"Uncertainty-Aware Distribution-to-Distribution Flow Matching for Scientific Imaging","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LV3BVZVGYI7IYNXRBI5ONPBB5V","json":"https://pith.science/pith/LV3BVZVGYI7IYNXRBI5ONPBB5V.json","graph_json":"https://pith.science/api/pith-number/LV3BVZVGYI7IYNXRBI5ONPBB5V/graph.json","events_json":"https://pith.science/api/pith-number/LV3BVZVGYI7IYNXRBI5ONPBB5V/events.json","paper":"https://pith.science/paper/LV3BVZVG"},"agent_actions":{"view_html":"https://pith.science/pith/LV3BVZVGYI7IYNXRBI5ONPBB5V","download_json":"https://pith.science/pith/LV3BVZVGYI7IYNXRBI5ONPBB5V.json","view_paper":"https://pith.science/paper/LV3BVZVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22692&json=true","fetch_graph":"https://pith.science/api/pith-number/LV3BVZVGYI7IYNXRBI5ONPBB5V/graph.json","fetch_events":"https://pith.science/api/pith-number/LV3BVZVGYI7IYNXRBI5ONPBB5V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LV3BVZVGYI7IYNXRBI5ONPBB5V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LV3BVZVGYI7IYNXRBI5ONPBB5V/action/storage_attestation","attest_author":"https://pith.science/pith/LV3BVZVGYI7IYNXRBI5ONPBB5V/action/author_attestation","sign_citation":"https://pith.science/pith/LV3BVZVGYI7IYNXRBI5ONPBB5V/action/citation_signature","submit_replication":"https://pith.science/pith/LV3BVZVGYI7IYNXRBI5ONPBB5V/action/replication_record"}},"created_at":"2026-07-05T11:45:47.218997+00:00","updated_at":"2026-07-05T11:45:47.218997+00:00"}