{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TKGR3QRNURVK4GJYPCNKD43K2D","short_pith_number":"pith:TKGR3QRN","schema_version":"1.0","canonical_sha256":"9a8d1dc22da46aae1938789aa1f36ad0dd452e62b96b63d4802c46847c55b202","source":{"kind":"arxiv","id":"2502.09057","version":1},"attestation_state":"computed","paper":{"title":"Vision-Language In-Context Learning Driven Few-Shot Visual Inspection Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hiroaki Aizawa, Kunihito Kato, Shiryu Ueno, Shunsuke Nakatsuka, Yoshikazu Hayashi, Yusei Yamada","submitted_at":"2025-02-13T08:11:10Z","abstract_excerpt":"We propose general visual inspection model using Vision-Language Model~(VLM) with few-shot images of non-defective or defective products, along with explanatory texts that serve as inspection criteria. Although existing VLM exhibit high performance across various tasks, they are not trained on specific tasks such as visual inspection. Thus, we construct a dataset consisting of diverse images of non-defective and defective products collected from the web, along with unified formatted output text, and fine-tune VLM. For new products, our method employs In-Context Learning, which allows the model"},"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":"2502.09057","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-13T08:11:10Z","cross_cats_sorted":[],"title_canon_sha256":"22964e3e200a4a4b660ef59a1cd91b6d9adb3d945f9092eb23800be65d4db757","abstract_canon_sha256":"5b78f0e8fb2197e5a3d2e0c62a3aa67984d45dbe5615c41caf297e06a15ae1ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:51.888561Z","signature_b64":"OWRcuJWw3TXJ2c1NhNcdkahcDzP/9G47vf1juxzXzxYd3sgdzWmjI9IXrP+GTHjP5A2Hz42VHKTvslU+OoKWCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a8d1dc22da46aae1938789aa1f36ad0dd452e62b96b63d4802c46847c55b202","last_reissued_at":"2026-07-05T10:13:51.888092Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:51.888092Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-Language In-Context Learning Driven Few-Shot Visual Inspection Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hiroaki Aizawa, Kunihito Kato, Shiryu Ueno, Shunsuke Nakatsuka, Yoshikazu Hayashi, Yusei Yamada","submitted_at":"2025-02-13T08:11:10Z","abstract_excerpt":"We propose general visual inspection model using Vision-Language Model~(VLM) with few-shot images of non-defective or defective products, along with explanatory texts that serve as inspection criteria. Although existing VLM exhibit high performance across various tasks, they are not trained on specific tasks such as visual inspection. Thus, we construct a dataset consisting of diverse images of non-defective and defective products collected from the web, along with unified formatted output text, and fine-tune VLM. For new products, our method employs In-Context Learning, which allows the model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.09057","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/2502.09057/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":"2502.09057","created_at":"2026-07-05T10:13:51.888149+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.09057v1","created_at":"2026-07-05T10:13:51.888149+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.09057","created_at":"2026-07-05T10:13:51.888149+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKGR3QRNURVK","created_at":"2026-07-05T10:13:51.888149+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKGR3QRNURVK4GJY","created_at":"2026-07-05T10:13:51.888149+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKGR3QRN","created_at":"2026-07-05T10:13:51.888149+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.03066","citing_title":"Redefining End-of-Life: Intelligent Automation for Electronics Remanufacturing Systems","ref_index":170,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TKGR3QRNURVK4GJYPCNKD43K2D","json":"https://pith.science/pith/TKGR3QRNURVK4GJYPCNKD43K2D.json","graph_json":"https://pith.science/api/pith-number/TKGR3QRNURVK4GJYPCNKD43K2D/graph.json","events_json":"https://pith.science/api/pith-number/TKGR3QRNURVK4GJYPCNKD43K2D/events.json","paper":"https://pith.science/paper/TKGR3QRN"},"agent_actions":{"view_html":"https://pith.science/pith/TKGR3QRNURVK4GJYPCNKD43K2D","download_json":"https://pith.science/pith/TKGR3QRNURVK4GJYPCNKD43K2D.json","view_paper":"https://pith.science/paper/TKGR3QRN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.09057&json=true","fetch_graph":"https://pith.science/api/pith-number/TKGR3QRNURVK4GJYPCNKD43K2D/graph.json","fetch_events":"https://pith.science/api/pith-number/TKGR3QRNURVK4GJYPCNKD43K2D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKGR3QRNURVK4GJYPCNKD43K2D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKGR3QRNURVK4GJYPCNKD43K2D/action/storage_attestation","attest_author":"https://pith.science/pith/TKGR3QRNURVK4GJYPCNKD43K2D/action/author_attestation","sign_citation":"https://pith.science/pith/TKGR3QRNURVK4GJYPCNKD43K2D/action/citation_signature","submit_replication":"https://pith.science/pith/TKGR3QRNURVK4GJYPCNKD43K2D/action/replication_record"}},"created_at":"2026-07-05T10:13:51.888149+00:00","updated_at":"2026-07-05T10:13:51.888149+00:00"}