{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:H6ARP625TUJKZ2GGIYXVUUTU47","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":"747167b4a7a898ff7a2378057886023df41d28a38c8bd5f75370115f1246c174","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T08:13:06Z","title_canon_sha256":"a26bacc1b5d03625ff8f485d33a85621016c51f49aa5e92d91c49739697d422e"},"schema_version":"1.0","source":{"id":"2409.01690","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.01690","created_at":"2026-07-05T09:02:32Z"},{"alias_kind":"arxiv_version","alias_value":"2409.01690v1","created_at":"2026-07-05T09:02:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01690","created_at":"2026-07-05T09:02:32Z"},{"alias_kind":"pith_short_12","alias_value":"H6ARP625TUJK","created_at":"2026-07-05T09:02:32Z"},{"alias_kind":"pith_short_16","alias_value":"H6ARP625TUJKZ2GG","created_at":"2026-07-05T09:02:32Z"},{"alias_kind":"pith_short_8","alias_value":"H6ARP625","created_at":"2026-07-05T09:02:32Z"}],"graph_snapshots":[{"event_id":"sha256:8fb087b87ace1676c837950bfd880e7bd9d2c42504a00aa7d9c039e7ee04a1ed","target":"graph","created_at":"2026-07-05T09:02:32Z","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/2409.01690/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"CLIP is a powerful and widely used tool for understanding images in the context of natural language descriptions to perform nuanced tasks. However, it does not offer application-specific fine-grained and structured understanding, due to its generic nature. In this work, we aim to adapt CLIP for fine-grained and structured -- in the form of tabular data -- visual understanding of museum exhibits. To facilitate such understanding we (a) collect, curate, and benchmark a dataset of 200K+ image-table pairs, and (b) develop a method that allows predicting tabular outputs for input images. Our datase","authors_text":"Ada-Astrid Balauca, Danda Pani Paudel, Kristina Toutanova, Luc Van Gool","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T08:13:06Z","title":"Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01690","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:bb7d76bacd9b7098abf8ee8fab95daa0f61362a50f350c9d24ea853b93d92a14","target":"record","created_at":"2026-07-05T09:02:32Z","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":"747167b4a7a898ff7a2378057886023df41d28a38c8bd5f75370115f1246c174","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T08:13:06Z","title_canon_sha256":"a26bacc1b5d03625ff8f485d33a85621016c51f49aa5e92d91c49739697d422e"},"schema_version":"1.0","source":{"id":"2409.01690","kind":"arxiv","version":1}},"canonical_sha256":"3f8117fb5d9d12ace8c6462f5a5274e7d64348412fa7edf790babcd139b29cf2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3f8117fb5d9d12ace8c6462f5a5274e7d64348412fa7edf790babcd139b29cf2","first_computed_at":"2026-07-05T09:02:32.844181Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:02:32.844181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Yb/a/PQmX0HRpFiIifNId2NSRb//72vHPGOcWdgf6CURJTjnusXzMWMBZnzWAfkhhA5tC5gm1MJym9vY4GG3Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:02:32.844743Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.01690","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb7d76bacd9b7098abf8ee8fab95daa0f61362a50f350c9d24ea853b93d92a14","sha256:8fb087b87ace1676c837950bfd880e7bd9d2c42504a00aa7d9c039e7ee04a1ed"],"state_sha256":"29c3eeadd7272f5d8fc5af7f83ec54f64d628b739ce15f8deed721d17e5ab50f"}