{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AKMJ5C5HTFD4BUIUWMMXY6JIBG","short_pith_number":"pith:AKMJ5C5H","schema_version":"1.0","canonical_sha256":"02989e8ba79947c0d114b3197c792809b28ee838686a7995a7e9163a530749d3","source":{"kind":"arxiv","id":"2508.10681","version":1},"attestation_state":"computed","paper":{"title":"IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Haiyang Yu, Ke Niu, Mengyang Zhao, Teng Fu","submitted_at":"2025-08-14T14:24:47Z","abstract_excerpt":"Few-Shot Industrial Anomaly Detection (FS-IAD) has important applications in automating industrial quality inspection. Recently, some FS-IAD methods based on Large Vision-Language Models (LVLMs) have been proposed with some achievements through prompt learning or fine-tuning. However, existing LVLMs focus on general tasks but lack basic industrial knowledge and reasoning capabilities related to FS-IAD, making these methods far from specialized human quality inspectors. To address these challenges, we propose a unified framework, IADGPT, designed to perform FS-IAD in a human-like manner, while "},"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":"2508.10681","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-08-14T14:24:47Z","cross_cats_sorted":[],"title_canon_sha256":"79d595148794478425d4bca6563ef5d72516ed8b6316d6dfd48859bc28be8b97","abstract_canon_sha256":"77d34abb0f3a6c871942ce20ddfd41447d4306e630884fdb0e80a13a766600ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:00.812069Z","signature_b64":"bf+reaUad6lXXMf59lIgL4B5OM+jiN3bzGHcRSGjV6QEbfITh1fO/tIgAmDp/cIRRWPq4CkVFGGJBun1SQVUBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"02989e8ba79947c0d114b3197c792809b28ee838686a7995a7e9163a530749d3","last_reissued_at":"2026-07-05T11:54:00.811615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:00.811615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Haiyang Yu, Ke Niu, Mengyang Zhao, Teng Fu","submitted_at":"2025-08-14T14:24:47Z","abstract_excerpt":"Few-Shot Industrial Anomaly Detection (FS-IAD) has important applications in automating industrial quality inspection. Recently, some FS-IAD methods based on Large Vision-Language Models (LVLMs) have been proposed with some achievements through prompt learning or fine-tuning. However, existing LVLMs focus on general tasks but lack basic industrial knowledge and reasoning capabilities related to FS-IAD, making these methods far from specialized human quality inspectors. To address these challenges, we propose a unified framework, IADGPT, designed to perform FS-IAD in a human-like manner, while "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10681","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/2508.10681/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":"2508.10681","created_at":"2026-07-05T11:54:00.811672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10681v1","created_at":"2026-07-05T11:54:00.811672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10681","created_at":"2026-07-05T11:54:00.811672+00:00"},{"alias_kind":"pith_short_12","alias_value":"AKMJ5C5HTFD4","created_at":"2026-07-05T11:54:00.811672+00:00"},{"alias_kind":"pith_short_16","alias_value":"AKMJ5C5HTFD4BUIU","created_at":"2026-07-05T11:54:00.811672+00:00"},{"alias_kind":"pith_short_8","alias_value":"AKMJ5C5H","created_at":"2026-07-05T11:54:00.811672+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/AKMJ5C5HTFD4BUIUWMMXY6JIBG","json":"https://pith.science/pith/AKMJ5C5HTFD4BUIUWMMXY6JIBG.json","graph_json":"https://pith.science/api/pith-number/AKMJ5C5HTFD4BUIUWMMXY6JIBG/graph.json","events_json":"https://pith.science/api/pith-number/AKMJ5C5HTFD4BUIUWMMXY6JIBG/events.json","paper":"https://pith.science/paper/AKMJ5C5H"},"agent_actions":{"view_html":"https://pith.science/pith/AKMJ5C5HTFD4BUIUWMMXY6JIBG","download_json":"https://pith.science/pith/AKMJ5C5HTFD4BUIUWMMXY6JIBG.json","view_paper":"https://pith.science/paper/AKMJ5C5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10681&json=true","fetch_graph":"https://pith.science/api/pith-number/AKMJ5C5HTFD4BUIUWMMXY6JIBG/graph.json","fetch_events":"https://pith.science/api/pith-number/AKMJ5C5HTFD4BUIUWMMXY6JIBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AKMJ5C5HTFD4BUIUWMMXY6JIBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AKMJ5C5HTFD4BUIUWMMXY6JIBG/action/storage_attestation","attest_author":"https://pith.science/pith/AKMJ5C5HTFD4BUIUWMMXY6JIBG/action/author_attestation","sign_citation":"https://pith.science/pith/AKMJ5C5HTFD4BUIUWMMXY6JIBG/action/citation_signature","submit_replication":"https://pith.science/pith/AKMJ5C5HTFD4BUIUWMMXY6JIBG/action/replication_record"}},"created_at":"2026-07-05T11:54:00.811672+00:00","updated_at":"2026-07-05T11:54:00.811672+00:00"}