{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:37M4G6KU5KFQY4NWO5Y22XLB5E","short_pith_number":"pith:37M4G6KU","schema_version":"1.0","canonical_sha256":"dfd9c37954ea8b0c71b67771ad5d61e926b084a68ba57503fd892076313bbe07","source":{"kind":"arxiv","id":"2304.03294","version":3},"attestation_state":"computed","paper":{"title":"What makes a good data augmentation for few-shot unsupervised image anomaly detection?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zheng, Guoyang Xie, Hua Yan, Jiaqi Liu, Jinbao Wang, Lingrui Zhang, Shuheng Zhang, Yaochu Jin","submitted_at":"2023-04-06T07:05:59Z","abstract_excerpt":"Data augmentation is a promising technique for unsupervised anomaly detection in industrial applications, where the availability of positive samples is often limited due to factors such as commercial competition and sample collection difficulties. In this paper, how to effectively select and apply data augmentation methods for unsupervised anomaly detection is studied. The impact of various data augmentation methods on different anomaly detection algorithms is systematically investigated through experiments. The experimental results show that the performance of different industrial image anoma"},"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":"2304.03294","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T07:05:59Z","cross_cats_sorted":[],"title_canon_sha256":"cbf998c6017c06554d96cd630962062411c96a33fc7506b843444a0fb3980478","abstract_canon_sha256":"a3f331c6e66769db08c0aabbbc1c1e5922409e814227fa5ab67b2e0144d2bbfe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:46.731465Z","signature_b64":"Up7nY7IP6kUSCHkhPeFbyYotD3LtQ5g1aXbI2xZevgI0xNcT6exTYczvR0XQ0/uPQhJ3EGGEkkSJVfDGjjK3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfd9c37954ea8b0c71b67771ad5d61e926b084a68ba57503fd892076313bbe07","last_reissued_at":"2026-07-05T06:03:46.731057Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:46.731057Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What makes a good data augmentation for few-shot unsupervised image anomaly detection?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Feng Zheng, Guoyang Xie, Hua Yan, Jiaqi Liu, Jinbao Wang, Lingrui Zhang, Shuheng Zhang, Yaochu Jin","submitted_at":"2023-04-06T07:05:59Z","abstract_excerpt":"Data augmentation is a promising technique for unsupervised anomaly detection in industrial applications, where the availability of positive samples is often limited due to factors such as commercial competition and sample collection difficulties. In this paper, how to effectively select and apply data augmentation methods for unsupervised anomaly detection is studied. The impact of various data augmentation methods on different anomaly detection algorithms is systematically investigated through experiments. The experimental results show that the performance of different industrial image anoma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03294","kind":"arxiv","version":3},"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/2304.03294/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":"2304.03294","created_at":"2026-07-05T06:03:46.731116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03294v3","created_at":"2026-07-05T06:03:46.731116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03294","created_at":"2026-07-05T06:03:46.731116+00:00"},{"alias_kind":"pith_short_12","alias_value":"37M4G6KU5KFQ","created_at":"2026-07-05T06:03:46.731116+00:00"},{"alias_kind":"pith_short_16","alias_value":"37M4G6KU5KFQY4NW","created_at":"2026-07-05T06:03:46.731116+00:00"},{"alias_kind":"pith_short_8","alias_value":"37M4G6KU","created_at":"2026-07-05T06:03:46.731116+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.07770","citing_title":"From Benchmark Performance to Tool Deployment: Human-in-the-Loop Anomaly Detection","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/37M4G6KU5KFQY4NWO5Y22XLB5E","json":"https://pith.science/pith/37M4G6KU5KFQY4NWO5Y22XLB5E.json","graph_json":"https://pith.science/api/pith-number/37M4G6KU5KFQY4NWO5Y22XLB5E/graph.json","events_json":"https://pith.science/api/pith-number/37M4G6KU5KFQY4NWO5Y22XLB5E/events.json","paper":"https://pith.science/paper/37M4G6KU"},"agent_actions":{"view_html":"https://pith.science/pith/37M4G6KU5KFQY4NWO5Y22XLB5E","download_json":"https://pith.science/pith/37M4G6KU5KFQY4NWO5Y22XLB5E.json","view_paper":"https://pith.science/paper/37M4G6KU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03294&json=true","fetch_graph":"https://pith.science/api/pith-number/37M4G6KU5KFQY4NWO5Y22XLB5E/graph.json","fetch_events":"https://pith.science/api/pith-number/37M4G6KU5KFQY4NWO5Y22XLB5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/37M4G6KU5KFQY4NWO5Y22XLB5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/37M4G6KU5KFQY4NWO5Y22XLB5E/action/storage_attestation","attest_author":"https://pith.science/pith/37M4G6KU5KFQY4NWO5Y22XLB5E/action/author_attestation","sign_citation":"https://pith.science/pith/37M4G6KU5KFQY4NWO5Y22XLB5E/action/citation_signature","submit_replication":"https://pith.science/pith/37M4G6KU5KFQY4NWO5Y22XLB5E/action/replication_record"}},"created_at":"2026-07-05T06:03:46.731116+00:00","updated_at":"2026-07-05T06:03:46.731116+00:00"}