{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PCY2NESDW3VWD5UKOSN6MZ3JJ4","short_pith_number":"pith:PCY2NESD","schema_version":"1.0","canonical_sha256":"78b1a69243b6eb61f68a749be667694f26cd352863224978e63a1f066a5b7610","source":{"kind":"arxiv","id":"2505.09263","version":1},"attestation_state":"computed","paper":{"title":"Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin-Bin Gao, Chengjie Wang, Guan Gui, Jun Liu, Yunsheng Wu","submitted_at":"2025-05-14T10:25:06Z","abstract_excerpt":"Anomaly detection is a practical and challenging task due to the scarcity of anomaly samples in industrial inspection. Some existing anomaly detection methods address this issue by synthesizing anomalies with noise or external data. However, there is always a large semantic gap between synthetic and real-world anomalies, resulting in weak performance in anomaly detection. To solve the problem, we propose a few-shot Anomaly-driven Generation (AnoGen) method, which guides the diffusion model to generate realistic and diverse anomalies with only a few real anomalies, thereby benefiting training a"},"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":"2505.09263","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-14T10:25:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3dc043355137a3c53f1b409a155140dedc901aab6707b809b553fc9ea13f568c","abstract_canon_sha256":"a2e7faf2bcad11c4878670f77ac05874a0634da92d40eee88453a84b71ae2603"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:05.239205Z","signature_b64":"dc+l0AA61tw55W21JCjHe+YdPpPImXe0mUq51tQ9eB6R54oj6MbHhbgI8Ub9Wh4zdOA+HPH4wjZySNSfOXx/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78b1a69243b6eb61f68a749be667694f26cd352863224978e63a1f066a5b7610","last_reissued_at":"2026-07-05T11:03:05.238624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:05.238624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Few-Shot Anomaly-Driven Generation for Anomaly Classification and Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bin-Bin Gao, Chengjie Wang, Guan Gui, Jun Liu, Yunsheng Wu","submitted_at":"2025-05-14T10:25:06Z","abstract_excerpt":"Anomaly detection is a practical and challenging task due to the scarcity of anomaly samples in industrial inspection. Some existing anomaly detection methods address this issue by synthesizing anomalies with noise or external data. However, there is always a large semantic gap between synthetic and real-world anomalies, resulting in weak performance in anomaly detection. To solve the problem, we propose a few-shot Anomaly-driven Generation (AnoGen) method, which guides the diffusion model to generate realistic and diverse anomalies with only a few real anomalies, thereby benefiting training a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09263","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/2505.09263/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":"2505.09263","created_at":"2026-07-05T11:03:05.238687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09263v1","created_at":"2026-07-05T11:03:05.238687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09263","created_at":"2026-07-05T11:03:05.238687+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCY2NESDW3VW","created_at":"2026-07-05T11:03:05.238687+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCY2NESDW3VWD5UK","created_at":"2026-07-05T11:03:05.238687+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCY2NESD","created_at":"2026-07-05T11:03:05.238687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.23766","citing_title":"Semantic Iterative Reconstruction: One-Shot Universal Anomaly Detection","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCY2NESDW3VWD5UKOSN6MZ3JJ4","json":"https://pith.science/pith/PCY2NESDW3VWD5UKOSN6MZ3JJ4.json","graph_json":"https://pith.science/api/pith-number/PCY2NESDW3VWD5UKOSN6MZ3JJ4/graph.json","events_json":"https://pith.science/api/pith-number/PCY2NESDW3VWD5UKOSN6MZ3JJ4/events.json","paper":"https://pith.science/paper/PCY2NESD"},"agent_actions":{"view_html":"https://pith.science/pith/PCY2NESDW3VWD5UKOSN6MZ3JJ4","download_json":"https://pith.science/pith/PCY2NESDW3VWD5UKOSN6MZ3JJ4.json","view_paper":"https://pith.science/paper/PCY2NESD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09263&json=true","fetch_graph":"https://pith.science/api/pith-number/PCY2NESDW3VWD5UKOSN6MZ3JJ4/graph.json","fetch_events":"https://pith.science/api/pith-number/PCY2NESDW3VWD5UKOSN6MZ3JJ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCY2NESDW3VWD5UKOSN6MZ3JJ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCY2NESDW3VWD5UKOSN6MZ3JJ4/action/storage_attestation","attest_author":"https://pith.science/pith/PCY2NESDW3VWD5UKOSN6MZ3JJ4/action/author_attestation","sign_citation":"https://pith.science/pith/PCY2NESDW3VWD5UKOSN6MZ3JJ4/action/citation_signature","submit_replication":"https://pith.science/pith/PCY2NESDW3VWD5UKOSN6MZ3JJ4/action/replication_record"}},"created_at":"2026-07-05T11:03:05.238687+00:00","updated_at":"2026-07-05T11:03:05.238687+00:00"}