{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:424MQBJ4YE5CANJ3MB2VYM47O4","short_pith_number":"pith:424MQBJ4","schema_version":"1.0","canonical_sha256":"e6b8c8053cc13a20353b60755c339f772f8b9fbef83b01abeae0bbb3d7be4d11","source":{"kind":"arxiv","id":"2411.03769","version":1},"attestation_state":"computed","paper":{"title":"No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ibrahim Said Ahmad, Kenneth Ward Church, Kilichbek Haydarov, Mohamed Elhoseiny, Philip Torr, Runjia Li, Youssef Mohamed","submitted_at":"2024-11-06T09:05:17Z","abstract_excerpt":"Research in vision and language has made considerable progress thanks to benchmarks such as COCO. COCO captions focused on unambiguous facts in English; ArtEmis introduced subjective emotions and ArtELingo introduced some multilinguality (Chinese and Arabic). However we believe there should be more multilinguality. Hence, we present ArtELingo-28, a vision-language benchmark that spans $\\textbf{28}$ languages and encompasses approximately $\\textbf{200,000}$ annotations ($\\textbf{140}$ annotations per image). Traditionally, vision research focused on unambiguous class labels, whereas ArtELingo-2"},"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":"2411.03769","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-06T09:05:17Z","cross_cats_sorted":["cs.AI","cs.CY","cs.LG"],"title_canon_sha256":"2a162a181fbc39b16edf93b69b7258d49bf53f5c93f6ba94f610241869a3c34c","abstract_canon_sha256":"59d5459f9d8b305416612daa0ec24ff79e55321c5f9e23497060b13693a97017"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:31:55.739983Z","signature_b64":"j1YnYpCTwYKMjJeswWlubnLEUEqrRyxywCVCa3+YHCiZAQbcoYN4kWVzzalWS8yBbqrVaFjTU1hFC+ack1CKCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6b8c8053cc13a20353b60755c339f772f8b9fbef83b01abeae0bbb3d7be4d11","last_reissued_at":"2026-07-05T09:31:55.739490Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:31:55.739490Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"No Culture Left Behind: ArtELingo-28, a Benchmark of WikiArt with Captions in 28 Languages","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.LG"],"primary_cat":"cs.CL","authors_text":"Ibrahim Said Ahmad, Kenneth Ward Church, Kilichbek Haydarov, Mohamed Elhoseiny, Philip Torr, Runjia Li, Youssef Mohamed","submitted_at":"2024-11-06T09:05:17Z","abstract_excerpt":"Research in vision and language has made considerable progress thanks to benchmarks such as COCO. COCO captions focused on unambiguous facts in English; ArtEmis introduced subjective emotions and ArtELingo introduced some multilinguality (Chinese and Arabic). However we believe there should be more multilinguality. Hence, we present ArtELingo-28, a vision-language benchmark that spans $\\textbf{28}$ languages and encompasses approximately $\\textbf{200,000}$ annotations ($\\textbf{140}$ annotations per image). Traditionally, vision research focused on unambiguous class labels, whereas ArtELingo-2"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.03769","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/2411.03769/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":"2411.03769","created_at":"2026-07-05T09:31:55.739547+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.03769v1","created_at":"2026-07-05T09:31:55.739547+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.03769","created_at":"2026-07-05T09:31:55.739547+00:00"},{"alias_kind":"pith_short_12","alias_value":"424MQBJ4YE5C","created_at":"2026-07-05T09:31:55.739547+00:00"},{"alias_kind":"pith_short_16","alias_value":"424MQBJ4YE5CANJ3","created_at":"2026-07-05T09:31:55.739547+00:00"},{"alias_kind":"pith_short_8","alias_value":"424MQBJ4","created_at":"2026-07-05T09:31:55.739547+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22793","citing_title":"Evaluation of Cultural Competence of Vision-Language Models","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/424MQBJ4YE5CANJ3MB2VYM47O4","json":"https://pith.science/pith/424MQBJ4YE5CANJ3MB2VYM47O4.json","graph_json":"https://pith.science/api/pith-number/424MQBJ4YE5CANJ3MB2VYM47O4/graph.json","events_json":"https://pith.science/api/pith-number/424MQBJ4YE5CANJ3MB2VYM47O4/events.json","paper":"https://pith.science/paper/424MQBJ4"},"agent_actions":{"view_html":"https://pith.science/pith/424MQBJ4YE5CANJ3MB2VYM47O4","download_json":"https://pith.science/pith/424MQBJ4YE5CANJ3MB2VYM47O4.json","view_paper":"https://pith.science/paper/424MQBJ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.03769&json=true","fetch_graph":"https://pith.science/api/pith-number/424MQBJ4YE5CANJ3MB2VYM47O4/graph.json","fetch_events":"https://pith.science/api/pith-number/424MQBJ4YE5CANJ3MB2VYM47O4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/424MQBJ4YE5CANJ3MB2VYM47O4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/424MQBJ4YE5CANJ3MB2VYM47O4/action/storage_attestation","attest_author":"https://pith.science/pith/424MQBJ4YE5CANJ3MB2VYM47O4/action/author_attestation","sign_citation":"https://pith.science/pith/424MQBJ4YE5CANJ3MB2VYM47O4/action/citation_signature","submit_replication":"https://pith.science/pith/424MQBJ4YE5CANJ3MB2VYM47O4/action/replication_record"}},"created_at":"2026-07-05T09:31:55.739547+00:00","updated_at":"2026-07-05T09:31:55.739547+00:00"}