{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KEPSVN4ILROVQWA5ATBZHFVKZL","short_pith_number":"pith:KEPSVN4I","schema_version":"1.0","canonical_sha256":"511f2ab7885c5d58581d04c39396aacadf686a13840022feed5558465b86590f","source":{"kind":"arxiv","id":"2607.03817","version":1},"attestation_state":"computed","paper":{"title":"Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caifeng Shan, Fang Zhao, Hongsong Wang, Runzhi Deng, Xixi Liu, Yiming Zhong, Yundi Hu, Zhao Wang","submitted_at":"2026-07-04T11:05:57Z","abstract_excerpt":"Large Multimodal Models (LMMs) show strong few-shot generalization, but industrial anomaly detection remains difficult because defects are small, input resolution is limited, and textual standards are not always grounded in visual evidence. Recent optimization-based methods improve alignment through fine-tuning, but they often require many defective samples, which are unavailable in early deployment. We present Global Logic and Local Search (GLLS), a training-free framework for reference-guided multimodal in-context verification. GLLS uses a Part-Aware Visual-Logical Atlas to organize normal r"},"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":"2607.03817","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-04T11:05:57Z","cross_cats_sorted":[],"title_canon_sha256":"73620d9397dc87c56b7b33502e60d73beebc3f2275fa7a01a251928370b946c4","abstract_canon_sha256":"442728a6506f346feb660517e0d89130c24fc01dae5d599f1a7b8433cc332a6d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:08.949064Z","signature_b64":"IjofuLKrL4z8Xv3E6nVZXGQVbhCjwynhj7AiHKrMAs1MnsdgXdklsAkDYfhInAKKSXWkHKQ8viSZXVUFG4aODQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"511f2ab7885c5d58581d04c39396aacadf686a13840022feed5558465b86590f","last_reissued_at":"2026-07-07T02:18:08.948365Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:08.948365Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Global Logic and Local Search: Dual-Stream Multimodal In-Context Learning for Verifiable Industrial Anomaly Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Caifeng Shan, Fang Zhao, Hongsong Wang, Runzhi Deng, Xixi Liu, Yiming Zhong, Yundi Hu, Zhao Wang","submitted_at":"2026-07-04T11:05:57Z","abstract_excerpt":"Large Multimodal Models (LMMs) show strong few-shot generalization, but industrial anomaly detection remains difficult because defects are small, input resolution is limited, and textual standards are not always grounded in visual evidence. Recent optimization-based methods improve alignment through fine-tuning, but they often require many defective samples, which are unavailable in early deployment. We present Global Logic and Local Search (GLLS), a training-free framework for reference-guided multimodal in-context verification. GLLS uses a Part-Aware Visual-Logical Atlas to organize normal r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03817","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/2607.03817/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":"2607.03817","created_at":"2026-07-07T02:18:08.948499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.03817v1","created_at":"2026-07-07T02:18:08.948499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03817","created_at":"2026-07-07T02:18:08.948499+00:00"},{"alias_kind":"pith_short_12","alias_value":"KEPSVN4ILROV","created_at":"2026-07-07T02:18:08.948499+00:00"},{"alias_kind":"pith_short_16","alias_value":"KEPSVN4ILROVQWA5","created_at":"2026-07-07T02:18:08.948499+00:00"},{"alias_kind":"pith_short_8","alias_value":"KEPSVN4I","created_at":"2026-07-07T02:18:08.948499+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/KEPSVN4ILROVQWA5ATBZHFVKZL","json":"https://pith.science/pith/KEPSVN4ILROVQWA5ATBZHFVKZL.json","graph_json":"https://pith.science/api/pith-number/KEPSVN4ILROVQWA5ATBZHFVKZL/graph.json","events_json":"https://pith.science/api/pith-number/KEPSVN4ILROVQWA5ATBZHFVKZL/events.json","paper":"https://pith.science/paper/KEPSVN4I"},"agent_actions":{"view_html":"https://pith.science/pith/KEPSVN4ILROVQWA5ATBZHFVKZL","download_json":"https://pith.science/pith/KEPSVN4ILROVQWA5ATBZHFVKZL.json","view_paper":"https://pith.science/paper/KEPSVN4I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.03817&json=true","fetch_graph":"https://pith.science/api/pith-number/KEPSVN4ILROVQWA5ATBZHFVKZL/graph.json","fetch_events":"https://pith.science/api/pith-number/KEPSVN4ILROVQWA5ATBZHFVKZL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KEPSVN4ILROVQWA5ATBZHFVKZL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KEPSVN4ILROVQWA5ATBZHFVKZL/action/storage_attestation","attest_author":"https://pith.science/pith/KEPSVN4ILROVQWA5ATBZHFVKZL/action/author_attestation","sign_citation":"https://pith.science/pith/KEPSVN4ILROVQWA5ATBZHFVKZL/action/citation_signature","submit_replication":"https://pith.science/pith/KEPSVN4ILROVQWA5ATBZHFVKZL/action/replication_record"}},"created_at":"2026-07-07T02:18:08.948499+00:00","updated_at":"2026-07-07T02:18:08.948499+00:00"}