{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:LJMOFTKW233FLSRYK5X4DQ4AN6","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ddae22020101d31089d75503559ff3e646bd2d312e8cd5d423b31c28ba9708aa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-08T15:40:57Z","title_canon_sha256":"309cdca38c74fa0e013985a3e6254a89ce5deb3eb6c0ef8756c3769b9929ca32"},"schema_version":"1.0","source":{"id":"2606.09648","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.09648","created_at":"2026-06-09T02:09:01Z"},{"alias_kind":"arxiv_version","alias_value":"2606.09648v1","created_at":"2026-06-09T02:09:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09648","created_at":"2026-06-09T02:09:01Z"},{"alias_kind":"pith_short_12","alias_value":"LJMOFTKW233F","created_at":"2026-06-09T02:09:01Z"},{"alias_kind":"pith_short_16","alias_value":"LJMOFTKW233FLSRY","created_at":"2026-06-09T02:09:01Z"},{"alias_kind":"pith_short_8","alias_value":"LJMOFTKW","created_at":"2026-06-09T02:09:01Z"}],"graph_snapshots":[{"event_id":"sha256:bef12b9c1355ed08213f80b936045affd870dc6e51baa0b5ce5185fdc51a61e1","target":"graph","created_at":"2026-06-09T02:09:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.09648/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal data management has emerged as a central research topic in the database community, spanning data integration, semantic query processing, and data quality assessment. Despite this growing interest, the community lacks large-scale, real-world datasets combining tables, text, and images. We present ArtiFact, a multi-modal cultural heritage dataset of 651045 museum records collected from the Metropolitan Museum of Art, the Art Institute of Chicago, and the Rijksmuseum. We demonstrate the utility of ArtiFact through two downstream tasks. For cross-modal error detection, we introduce a c","authors_text":"Luciano Duarte, Olga Ovcharenko, Sebastian Schelter","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-08T15:40:57Z","title":"ArtiFact: A Large-Scale Multi-Modal Cultural Heritage Dataset"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09648","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8a063d9b09893cf75116c6754540865b7effc66dae5f00f9a3f01a37826b34a4","target":"record","created_at":"2026-06-09T02:09:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ddae22020101d31089d75503559ff3e646bd2d312e8cd5d423b31c28ba9708aa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DB","submitted_at":"2026-06-08T15:40:57Z","title_canon_sha256":"309cdca38c74fa0e013985a3e6254a89ce5deb3eb6c0ef8756c3769b9929ca32"},"schema_version":"1.0","source":{"id":"2606.09648","kind":"arxiv","version":1}},"canonical_sha256":"5a58e2cd56d6f655ca38576fc1c3806faa21a6e620416f9dd4059f72892c1609","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5a58e2cd56d6f655ca38576fc1c3806faa21a6e620416f9dd4059f72892c1609","first_computed_at":"2026-06-09T02:09:01.277077Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T02:09:01.277077Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8MO675fTNe5KTGys4qtC3B6xaDATDKKTLDRZMxf1y5w+OQFIX+2q5NxjATufnOReqrIb2ayjMMQuHmQO9hrDAQ==","signature_status":"signed_v1","signed_at":"2026-06-09T02:09:01.277687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.09648","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a063d9b09893cf75116c6754540865b7effc66dae5f00f9a3f01a37826b34a4","sha256:bef12b9c1355ed08213f80b936045affd870dc6e51baa0b5ce5185fdc51a61e1"],"state_sha256":"907298dd7fe4095ffcf46f5b34714ebb8ca13c50e972a5f591712b2951e8d716"}