{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5IICNYRC6AXQD6V25I2KWMIAXR","short_pith_number":"pith:5IICNYRC","schema_version":"1.0","canonical_sha256":"ea1026e222f02f01fabaea34ab3100bc6caa4682e59bb76ce8ab66554d87cbc2","source":{"kind":"arxiv","id":"2406.01078","version":4},"attestation_state":"computed","paper":{"title":"Unseen Visual Anomaly Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Sun, Hao Dong, Olga Fink, Yunkang Cao","submitted_at":"2024-06-03T07:58:09Z","abstract_excerpt":"Visual anomaly detection (AD) presents significant challenges due to the scarcity of anomalous data samples. While numerous works have been proposed to synthesize anomalous samples, these synthetic anomalies often lack authenticity or require extensive training data, limiting their applicability in real-world scenarios. In this work, we propose Anomaly Anything (AnomalyAny), a novel framework that leverages Stable Diffusion (SD)'s image generation capabilities to generate diverse and realistic unseen anomalies. By conditioning on a single normal sample during test time, AnomalyAny is able to g"},"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":"2406.01078","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-03T07:58:09Z","cross_cats_sorted":[],"title_canon_sha256":"1ae9d47e9db1cf316d275805319d397aaa1972609cb0994742d24566429f3faf","abstract_canon_sha256":"b00aea2b551ee7b11b0888c2f4f9863612fa1aed96e2f6298405308fd5c05de4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:48.890927Z","signature_b64":"4J+7OtRsNLwYJIwxmQlJT1DVAf80AoTpDalxXoVXeGgDzkvkUUXIc7ubnZRM3IH3h3UXoDMQCgIZlT5HvvDODA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea1026e222f02f01fabaea34ab3100bc6caa4682e59bb76ce8ab66554d87cbc2","last_reissued_at":"2026-07-05T11:19:48.890489Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:48.890489Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unseen Visual Anomaly Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Han Sun, Hao Dong, Olga Fink, Yunkang Cao","submitted_at":"2024-06-03T07:58:09Z","abstract_excerpt":"Visual anomaly detection (AD) presents significant challenges due to the scarcity of anomalous data samples. While numerous works have been proposed to synthesize anomalous samples, these synthetic anomalies often lack authenticity or require extensive training data, limiting their applicability in real-world scenarios. In this work, we propose Anomaly Anything (AnomalyAny), a novel framework that leverages Stable Diffusion (SD)'s image generation capabilities to generate diverse and realistic unseen anomalies. By conditioning on a single normal sample during test time, AnomalyAny is able to g"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01078","kind":"arxiv","version":4},"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/2406.01078/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":"2406.01078","created_at":"2026-07-05T11:19:48.890544+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01078v4","created_at":"2026-07-05T11:19:48.890544+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01078","created_at":"2026-07-05T11:19:48.890544+00:00"},{"alias_kind":"pith_short_12","alias_value":"5IICNYRC6AXQ","created_at":"2026-07-05T11:19:48.890544+00:00"},{"alias_kind":"pith_short_16","alias_value":"5IICNYRC6AXQD6V2","created_at":"2026-07-05T11:19:48.890544+00:00"},{"alias_kind":"pith_short_8","alias_value":"5IICNYRC","created_at":"2026-07-05T11:19:48.890544+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06693","citing_title":"STAGE: Segmentation-oriented Industrial Anomaly Synthesis via Graded Diffusion with Explicit Mask Alignment","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5IICNYRC6AXQD6V25I2KWMIAXR","json":"https://pith.science/pith/5IICNYRC6AXQD6V25I2KWMIAXR.json","graph_json":"https://pith.science/api/pith-number/5IICNYRC6AXQD6V25I2KWMIAXR/graph.json","events_json":"https://pith.science/api/pith-number/5IICNYRC6AXQD6V25I2KWMIAXR/events.json","paper":"https://pith.science/paper/5IICNYRC"},"agent_actions":{"view_html":"https://pith.science/pith/5IICNYRC6AXQD6V25I2KWMIAXR","download_json":"https://pith.science/pith/5IICNYRC6AXQD6V25I2KWMIAXR.json","view_paper":"https://pith.science/paper/5IICNYRC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01078&json=true","fetch_graph":"https://pith.science/api/pith-number/5IICNYRC6AXQD6V25I2KWMIAXR/graph.json","fetch_events":"https://pith.science/api/pith-number/5IICNYRC6AXQD6V25I2KWMIAXR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5IICNYRC6AXQD6V25I2KWMIAXR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5IICNYRC6AXQD6V25I2KWMIAXR/action/storage_attestation","attest_author":"https://pith.science/pith/5IICNYRC6AXQD6V25I2KWMIAXR/action/author_attestation","sign_citation":"https://pith.science/pith/5IICNYRC6AXQD6V25I2KWMIAXR/action/citation_signature","submit_replication":"https://pith.science/pith/5IICNYRC6AXQD6V25I2KWMIAXR/action/replication_record"}},"created_at":"2026-07-05T11:19:48.890544+00:00","updated_at":"2026-07-05T11:19:48.890544+00:00"}