{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y5FO4ENPTURF7MOKPIPH2OCDP6","short_pith_number":"pith:Y5FO4ENP","schema_version":"1.0","canonical_sha256":"c74aee11af9d225fb1ca7a1e7d38437f915c5e8345202d7e441cd822157047fb","source":{"kind":"arxiv","id":"2508.13560","version":2},"attestation_state":"computed","paper":{"title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Shen, Guiguang Ding, Mukesh Prasad, Shichen Qu, Xian Tao, Xiaopei Zhang, Xingang Wang, Xinyi Gong, Zhengtao Zhang, Zhen Qu","submitted_at":"2025-08-19T06:38:56Z","abstract_excerpt":"Recent vision-language models (e.g., CLIP) have demonstrated remarkable class-generalizable ability to unseen classes in few-shot anomaly segmentation (FSAS), leveraging supervised prompt learning or fine-tuning on seen classes. However, their cross-category generalization largely depends on prior knowledge of real seen anomaly samples. In this paper, we propose a novel framework, namely DictAS, which enables a unified model to detect visual anomalies in unseen object categories without any retraining on the target data, only employing a few normal reference images as visual prompts. The insig"},"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":"2508.13560","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-19T06:38:56Z","cross_cats_sorted":[],"title_canon_sha256":"9ff0747942c397e9f84ed62dacc46e30941807e4bf93eddb1c1efffceaa65f33","abstract_canon_sha256":"ca4d3b68b876c4c650f5fac551ce9e747ecf67ad6ace8096476680ba73e744b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:57:02.084696Z","signature_b64":"YIlAdQ7wiqeNtMPLltkeEXey2gfP6lIvk8dlR3o3twLKZmFbcVOb+5aR+R4tTOAk99GOVsr2fc4aHbZBNUxpDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c74aee11af9d225fb1ca7a1e7d38437f915c5e8345202d7e441cd822157047fb","last_reissued_at":"2026-07-05T11:57:02.084278Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:57:02.084278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DictAS: A Framework for Class-Generalizable Few-Shot Anomaly Segmentation via Dictionary Lookup","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fei Shen, Guiguang Ding, Mukesh Prasad, Shichen Qu, Xian Tao, Xiaopei Zhang, Xingang Wang, Xinyi Gong, Zhengtao Zhang, Zhen Qu","submitted_at":"2025-08-19T06:38:56Z","abstract_excerpt":"Recent vision-language models (e.g., CLIP) have demonstrated remarkable class-generalizable ability to unseen classes in few-shot anomaly segmentation (FSAS), leveraging supervised prompt learning or fine-tuning on seen classes. However, their cross-category generalization largely depends on prior knowledge of real seen anomaly samples. In this paper, we propose a novel framework, namely DictAS, which enables a unified model to detect visual anomalies in unseen object categories without any retraining on the target data, only employing a few normal reference images as visual prompts. The insig"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.13560","kind":"arxiv","version":2},"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/2508.13560/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":"2508.13560","created_at":"2026-07-05T11:57:02.084341+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.13560v2","created_at":"2026-07-05T11:57:02.084341+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.13560","created_at":"2026-07-05T11:57:02.084341+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y5FO4ENPTURF","created_at":"2026-07-05T11:57:02.084341+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y5FO4ENPTURF7MOK","created_at":"2026-07-05T11:57:02.084341+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y5FO4ENP","created_at":"2026-07-05T11:57:02.084341+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/Y5FO4ENPTURF7MOKPIPH2OCDP6","json":"https://pith.science/pith/Y5FO4ENPTURF7MOKPIPH2OCDP6.json","graph_json":"https://pith.science/api/pith-number/Y5FO4ENPTURF7MOKPIPH2OCDP6/graph.json","events_json":"https://pith.science/api/pith-number/Y5FO4ENPTURF7MOKPIPH2OCDP6/events.json","paper":"https://pith.science/paper/Y5FO4ENP"},"agent_actions":{"view_html":"https://pith.science/pith/Y5FO4ENPTURF7MOKPIPH2OCDP6","download_json":"https://pith.science/pith/Y5FO4ENPTURF7MOKPIPH2OCDP6.json","view_paper":"https://pith.science/paper/Y5FO4ENP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.13560&json=true","fetch_graph":"https://pith.science/api/pith-number/Y5FO4ENPTURF7MOKPIPH2OCDP6/graph.json","fetch_events":"https://pith.science/api/pith-number/Y5FO4ENPTURF7MOKPIPH2OCDP6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y5FO4ENPTURF7MOKPIPH2OCDP6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y5FO4ENPTURF7MOKPIPH2OCDP6/action/storage_attestation","attest_author":"https://pith.science/pith/Y5FO4ENPTURF7MOKPIPH2OCDP6/action/author_attestation","sign_citation":"https://pith.science/pith/Y5FO4ENPTURF7MOKPIPH2OCDP6/action/citation_signature","submit_replication":"https://pith.science/pith/Y5FO4ENPTURF7MOKPIPH2OCDP6/action/replication_record"}},"created_at":"2026-07-05T11:57:02.084341+00:00","updated_at":"2026-07-05T11:57:02.084341+00:00"}