{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OYRWKDGRTGHPKPMHRLTOJAB4KB","short_pith_number":"pith:OYRWKDGR","schema_version":"1.0","canonical_sha256":"7623650cd1998ef53d878ae6e4803c505c5e270eeb8c57f0351b4537fe285e7d","source":{"kind":"arxiv","id":"2509.22123","version":2},"attestation_state":"computed","paper":{"title":"Multilingual Vision-Language Models, A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrei-Alexandru Manea, Jind\\v{r}ich Libovick\\'y","submitted_at":"2025-09-26T09:46:13Z","abstract_excerpt":"This survey examines multilingual vision-language models that process text and images across languages. We review 33 models and 23 benchmarks, spanning encoder-only and generative architectures, and identify a key tension between language neutrality (consistent cross-lingual representations) and cultural awareness (adaptation to cultural contexts). Current training methods favor neutrality through contrastive learning, while cultural awareness depends on diverse data. Two-thirds of evaluation benchmarks use translation-based approaches prioritizing semantic consistency, though recent work inco"},"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":"2509.22123","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-26T09:46:13Z","cross_cats_sorted":[],"title_canon_sha256":"56b5667077c2738d00ce8428eac2de2092842934869e93120de2497f9f2d5c43","abstract_canon_sha256":"af00e92a587924175e6690b17675a305e75d89da34f0d1e8dcf888a17d927849"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:45:12.311812Z","signature_b64":"ku8xM7ecs2LYgido7advZ+AxQZs8qHyEfbDVMzexVIdxhmgZ1w3T380SZSzjWniyTpOlZwaiPVlrWpCWmZWMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7623650cd1998ef53d878ae6e4803c505c5e270eeb8c57f0351b4537fe285e7d","last_reissued_at":"2026-05-18T02:45:12.311104Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:45:12.311104Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multilingual Vision-Language Models, A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andrei-Alexandru Manea, Jind\\v{r}ich Libovick\\'y","submitted_at":"2025-09-26T09:46:13Z","abstract_excerpt":"This survey examines multilingual vision-language models that process text and images across languages. We review 33 models and 23 benchmarks, spanning encoder-only and generative architectures, and identify a key tension between language neutrality (consistent cross-lingual representations) and cultural awareness (adaptation to cultural contexts). Current training methods favor neutrality through contrastive learning, while cultural awareness depends on diverse data. Two-thirds of evaluation benchmarks use translation-based approaches prioritizing semantic consistency, though recent work inco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.22123","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2509.22123","created_at":"2026-05-18T02:45:12.311219+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.22123v2","created_at":"2026-05-18T02:45:12.311219+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.22123","created_at":"2026-05-18T02:45:12.311219+00:00"},{"alias_kind":"pith_short_12","alias_value":"OYRWKDGRTGHP","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"OYRWKDGRTGHPKPMH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"OYRWKDGR","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OYRWKDGRTGHPKPMHRLTOJAB4KB","json":"https://pith.science/pith/OYRWKDGRTGHPKPMHRLTOJAB4KB.json","graph_json":"https://pith.science/api/pith-number/OYRWKDGRTGHPKPMHRLTOJAB4KB/graph.json","events_json":"https://pith.science/api/pith-number/OYRWKDGRTGHPKPMHRLTOJAB4KB/events.json","paper":"https://pith.science/paper/OYRWKDGR"},"agent_actions":{"view_html":"https://pith.science/pith/OYRWKDGRTGHPKPMHRLTOJAB4KB","download_json":"https://pith.science/pith/OYRWKDGRTGHPKPMHRLTOJAB4KB.json","view_paper":"https://pith.science/paper/OYRWKDGR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.22123&json=true","fetch_graph":"https://pith.science/api/pith-number/OYRWKDGRTGHPKPMHRLTOJAB4KB/graph.json","fetch_events":"https://pith.science/api/pith-number/OYRWKDGRTGHPKPMHRLTOJAB4KB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OYRWKDGRTGHPKPMHRLTOJAB4KB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OYRWKDGRTGHPKPMHRLTOJAB4KB/action/storage_attestation","attest_author":"https://pith.science/pith/OYRWKDGRTGHPKPMHRLTOJAB4KB/action/author_attestation","sign_citation":"https://pith.science/pith/OYRWKDGRTGHPKPMHRLTOJAB4KB/action/citation_signature","submit_replication":"https://pith.science/pith/OYRWKDGRTGHPKPMHRLTOJAB4KB/action/replication_record"}},"created_at":"2026-05-18T02:45:12.311219+00:00","updated_at":"2026-05-18T02:45:12.311219+00:00"}