{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H6ARP625TUJKZ2GGIYXVUUTU47","short_pith_number":"pith:H6ARP625","schema_version":"1.0","canonical_sha256":"3f8117fb5d9d12ace8c6462f5a5274e7d64348412fa7edf790babcd139b29cf2","source":{"kind":"arxiv","id":"2409.01690","version":1},"attestation_state":"computed","paper":{"title":"Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ada-Astrid Balauca, Danda Pani Paudel, Kristina Toutanova, Luc Van Gool","submitted_at":"2024-09-03T08:13:06Z","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"},"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":"2409.01690","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-03T08:13:06Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a26bacc1b5d03625ff8f485d33a85621016c51f49aa5e92d91c49739697d422e","abstract_canon_sha256":"747167b4a7a898ff7a2378057886023df41d28a38c8bd5f75370115f1246c174"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:02:32.844743Z","signature_b64":"Yb/a/PQmX0HRpFiIifNId2NSRb//72vHPGOcWdgf6CURJTjnusXzMWMBZnzWAfkhhA5tC5gm1MJym9vY4GG3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f8117fb5d9d12ace8c6462f5a5274e7d64348412fa7edf790babcd139b29cf2","last_reissued_at":"2026-07-05T09:02:32.844181Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:02:32.844181Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Taming CLIP for Fine-grained and Structured Visual Understanding of Museum Exhibits","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Ada-Astrid Balauca, Danda Pani Paudel, Kristina Toutanova, Luc Van Gool","submitted_at":"2024-09-03T08:13:06Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.01690","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/2409.01690/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":"2409.01690","created_at":"2026-07-05T09:02:32.844255+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.01690v1","created_at":"2026-07-05T09:02:32.844255+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.01690","created_at":"2026-07-05T09:02:32.844255+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6ARP625TUJK","created_at":"2026-07-05T09:02:32.844255+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6ARP625TUJKZ2GG","created_at":"2026-07-05T09:02:32.844255+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6ARP625","created_at":"2026-07-05T09:02:32.844255+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.01370","citing_title":"Understanding Museum Exhibits using Vision-Language Reasoning","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6ARP625TUJKZ2GGIYXVUUTU47","json":"https://pith.science/pith/H6ARP625TUJKZ2GGIYXVUUTU47.json","graph_json":"https://pith.science/api/pith-number/H6ARP625TUJKZ2GGIYXVUUTU47/graph.json","events_json":"https://pith.science/api/pith-number/H6ARP625TUJKZ2GGIYXVUUTU47/events.json","paper":"https://pith.science/paper/H6ARP625"},"agent_actions":{"view_html":"https://pith.science/pith/H6ARP625TUJKZ2GGIYXVUUTU47","download_json":"https://pith.science/pith/H6ARP625TUJKZ2GGIYXVUUTU47.json","view_paper":"https://pith.science/paper/H6ARP625","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.01690&json=true","fetch_graph":"https://pith.science/api/pith-number/H6ARP625TUJKZ2GGIYXVUUTU47/graph.json","fetch_events":"https://pith.science/api/pith-number/H6ARP625TUJKZ2GGIYXVUUTU47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6ARP625TUJKZ2GGIYXVUUTU47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6ARP625TUJKZ2GGIYXVUUTU47/action/storage_attestation","attest_author":"https://pith.science/pith/H6ARP625TUJKZ2GGIYXVUUTU47/action/author_attestation","sign_citation":"https://pith.science/pith/H6ARP625TUJKZ2GGIYXVUUTU47/action/citation_signature","submit_replication":"https://pith.science/pith/H6ARP625TUJKZ2GGIYXVUUTU47/action/replication_record"}},"created_at":"2026-07-05T09:02:32.844255+00:00","updated_at":"2026-07-05T09:02:32.844255+00:00"}