{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6ZZUHJ32X5PS3QQPXPH3X3XH6L","short_pith_number":"pith:6ZZUHJ32","schema_version":"1.0","canonical_sha256":"f67343a77abf5f2dc20fbbcfbbeee7f2cd1b80a5739d15f4f5d5dcec99cb6bc3","source":{"kind":"arxiv","id":"2409.16646","version":3},"attestation_state":"computed","paper":{"title":"Cross-Lingual and Cross-Cultural Variation in Image Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Edoardo M. Ponti, Uri Berger","submitted_at":"2024-09-25T05:57:09Z","abstract_excerpt":"Do speakers of different languages talk differently about what they see? Behavioural and cognitive studies report cultural effects on perception; however, these are mostly limited in scope and hard to replicate. In this work, we conduct the first large-scale empirical study of cross-lingual variation in image descriptions. Using a multimodal dataset with 31 languages and images from diverse locations, we develop a method to accurately identify entities mentioned in captions and present in the images, then measure how they vary across languages. Our analysis reveals that pairs of languages that"},"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":"2409.16646","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-09-25T05:57:09Z","cross_cats_sorted":[],"title_canon_sha256":"773e83ca33ccd7da57542a0d5c2ce5d3779b4cfb72c49825588f88ea7a56a703","abstract_canon_sha256":"a59e7eb8c10a27ca951a11ae415f34b35c4c7077ffe3c00439078f859d10ab00"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:32.020403Z","signature_b64":"dZEyhYJA7rFP32L2lbTSoVwwPK+gacE7j/o0Ij5jGol6GZDSOkk7uhXPg5JpzCMJ+YmGvI6I95Sy9e7l3KzRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f67343a77abf5f2dc20fbbcfbbeee7f2cd1b80a5739d15f4f5d5dcec99cb6bc3","last_reissued_at":"2026-07-05T09:19:32.019954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:32.019954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Lingual and Cross-Cultural Variation in Image Descriptions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Edoardo M. Ponti, Uri Berger","submitted_at":"2024-09-25T05:57:09Z","abstract_excerpt":"Do speakers of different languages talk differently about what they see? Behavioural and cognitive studies report cultural effects on perception; however, these are mostly limited in scope and hard to replicate. In this work, we conduct the first large-scale empirical study of cross-lingual variation in image descriptions. Using a multimodal dataset with 31 languages and images from diverse locations, we develop a method to accurately identify entities mentioned in captions and present in the images, then measure how they vary across languages. Our analysis reveals that pairs of languages that"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.16646","kind":"arxiv","version":3},"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/2409.16646/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":"2409.16646","created_at":"2026-07-05T09:19:32.020014+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.16646v3","created_at":"2026-07-05T09:19:32.020014+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.16646","created_at":"2026-07-05T09:19:32.020014+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZZUHJ32X5PS","created_at":"2026-07-05T09:19:32.020014+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZZUHJ32X5PS3QQP","created_at":"2026-07-05T09:19:32.020014+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZZUHJ32","created_at":"2026-07-05T09:19:32.020014+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.10369","citing_title":"A Grounded Typology of Word Classes","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ZZUHJ32X5PS3QQPXPH3X3XH6L","json":"https://pith.science/pith/6ZZUHJ32X5PS3QQPXPH3X3XH6L.json","graph_json":"https://pith.science/api/pith-number/6ZZUHJ32X5PS3QQPXPH3X3XH6L/graph.json","events_json":"https://pith.science/api/pith-number/6ZZUHJ32X5PS3QQPXPH3X3XH6L/events.json","paper":"https://pith.science/paper/6ZZUHJ32"},"agent_actions":{"view_html":"https://pith.science/pith/6ZZUHJ32X5PS3QQPXPH3X3XH6L","download_json":"https://pith.science/pith/6ZZUHJ32X5PS3QQPXPH3X3XH6L.json","view_paper":"https://pith.science/paper/6ZZUHJ32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.16646&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZZUHJ32X5PS3QQPXPH3X3XH6L/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZZUHJ32X5PS3QQPXPH3X3XH6L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZZUHJ32X5PS3QQPXPH3X3XH6L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZZUHJ32X5PS3QQPXPH3X3XH6L/action/storage_attestation","attest_author":"https://pith.science/pith/6ZZUHJ32X5PS3QQPXPH3X3XH6L/action/author_attestation","sign_citation":"https://pith.science/pith/6ZZUHJ32X5PS3QQPXPH3X3XH6L/action/citation_signature","submit_replication":"https://pith.science/pith/6ZZUHJ32X5PS3QQPXPH3X3XH6L/action/replication_record"}},"created_at":"2026-07-05T09:19:32.020014+00:00","updated_at":"2026-07-05T09:19:32.020014+00:00"}