{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QYGSMWBXSHQYGIMN55GI6QAT3I","short_pith_number":"pith:QYGSMWBX","schema_version":"1.0","canonical_sha256":"860d26583791e183218def4c8f4013da114f11c4b98ac95bab8a28aa6659ad91","source":{"kind":"arxiv","id":"2411.04663","version":1},"attestation_state":"computed","paper":{"title":"Explainable Search and Discovery of Visual Cultural Heritage Collections with Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lauren Tilton, Taylor Arnold","submitted_at":"2024-11-07T12:48:39Z","abstract_excerpt":"Many cultural institutions have made large digitized visual collections available online, often under permissible re-use licences. Creating interfaces for exploring and searching these collections is difficult, particularly in the absence of granular metadata. In this paper, we introduce a method for using state-of-the-art multimodal large language models (LLMs) to enable an open-ended, explainable search and discovery interface for visual collections. We show how our approach can create novel clustering and recommendation systems that avoid common pitfalls of methods based directly on visual "},"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":"2411.04663","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-07T12:48:39Z","cross_cats_sorted":[],"title_canon_sha256":"bc64b9f5441f602c409044a418c660db0c667f8aacb5f0cac9f0fafef170e607","abstract_canon_sha256":"9e4c9c72e6b3bf20caab5e048eb3590d260d2e541d51e25c724dbba4bf964985"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:23.643826Z","signature_b64":"MX8n+UNvt9BOodxocSunZsjNm0W4uZEK8j3Jec57atNVgL9vO6292kYjW8kjZneJnzkQ1434OrsQ7f0w7C7hAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"860d26583791e183218def4c8f4013da114f11c4b98ac95bab8a28aa6659ad91","last_reissued_at":"2026-07-05T09:32:23.643383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:23.643383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Explainable Search and Discovery of Visual Cultural Heritage Collections with Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Lauren Tilton, Taylor Arnold","submitted_at":"2024-11-07T12:48:39Z","abstract_excerpt":"Many cultural institutions have made large digitized visual collections available online, often under permissible re-use licences. Creating interfaces for exploring and searching these collections is difficult, particularly in the absence of granular metadata. In this paper, we introduce a method for using state-of-the-art multimodal large language models (LLMs) to enable an open-ended, explainable search and discovery interface for visual collections. We show how our approach can create novel clustering and recommendation systems that avoid common pitfalls of methods based directly on visual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.04663","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/2411.04663/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":"2411.04663","created_at":"2026-07-05T09:32:23.643442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.04663v1","created_at":"2026-07-05T09:32:23.643442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.04663","created_at":"2026-07-05T09:32:23.643442+00:00"},{"alias_kind":"pith_short_12","alias_value":"QYGSMWBXSHQY","created_at":"2026-07-05T09:32:23.643442+00:00"},{"alias_kind":"pith_short_16","alias_value":"QYGSMWBXSHQYGIMN","created_at":"2026-07-05T09:32:23.643442+00:00"},{"alias_kind":"pith_short_8","alias_value":"QYGSMWBX","created_at":"2026-07-05T09:32:23.643442+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06044","citing_title":"A Unified Framework for Cultural Heritage Data Historicity and Migration: The ARGUS Approach","ref_index":15,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QYGSMWBXSHQYGIMN55GI6QAT3I","json":"https://pith.science/pith/QYGSMWBXSHQYGIMN55GI6QAT3I.json","graph_json":"https://pith.science/api/pith-number/QYGSMWBXSHQYGIMN55GI6QAT3I/graph.json","events_json":"https://pith.science/api/pith-number/QYGSMWBXSHQYGIMN55GI6QAT3I/events.json","paper":"https://pith.science/paper/QYGSMWBX"},"agent_actions":{"view_html":"https://pith.science/pith/QYGSMWBXSHQYGIMN55GI6QAT3I","download_json":"https://pith.science/pith/QYGSMWBXSHQYGIMN55GI6QAT3I.json","view_paper":"https://pith.science/paper/QYGSMWBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.04663&json=true","fetch_graph":"https://pith.science/api/pith-number/QYGSMWBXSHQYGIMN55GI6QAT3I/graph.json","fetch_events":"https://pith.science/api/pith-number/QYGSMWBXSHQYGIMN55GI6QAT3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QYGSMWBXSHQYGIMN55GI6QAT3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QYGSMWBXSHQYGIMN55GI6QAT3I/action/storage_attestation","attest_author":"https://pith.science/pith/QYGSMWBXSHQYGIMN55GI6QAT3I/action/author_attestation","sign_citation":"https://pith.science/pith/QYGSMWBXSHQYGIMN55GI6QAT3I/action/citation_signature","submit_replication":"https://pith.science/pith/QYGSMWBXSHQYGIMN55GI6QAT3I/action/replication_record"}},"created_at":"2026-07-05T09:32:23.643442+00:00","updated_at":"2026-07-05T09:32:23.643442+00:00"}