{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WN5IWF6ROMGRLLAMCQA52MUC44","short_pith_number":"pith:WN5IWF6R","schema_version":"1.0","canonical_sha256":"b37a8b17d1730d15ac0c1401dd3282e73e2dbda454174797e6e8c0da500817cd","source":{"kind":"arxiv","id":"2502.12852","version":1},"attestation_state":"computed","paper":{"title":"MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Biemann, Fabian David Schmidt, Florian Schneider, Goran Glava\\v{s}","submitted_at":"2025-02-18T13:40:05Z","abstract_excerpt":"Existing multilingual vision-language (VL) benchmarks often only cover a handful of languages. Consequently, evaluations of large vision-language models (LVLMs) predominantly target high-resource languages, underscoring the need for evaluation data for low-resource languages. To address this limitation, we introduce MVL-SIB, a massively multilingual vision-language benchmark that evaluates both cross-modal and text-only topical matching across 205 languages -- over 100 more than the most multilingual existing VL benchmarks encompass. We then benchmark a range of of open-weight LVLMs together w"},"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":"2502.12852","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-18T13:40:05Z","cross_cats_sorted":[],"title_canon_sha256":"18caba9104fab78683282ae482aa70bf509bf55c195b4c7c53e35b3c2699331f","abstract_canon_sha256":"4d42a840d3ab22215bf50d1d25fb062f1a38f44e31ce588b0edd0e44e8959e39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:25.270063Z","signature_b64":"VdBbTC498+1R+HVDTjdT7nNpUFkeFyAhDUw3063OY41WcQVDIi+X8mcrNVn4hwKs9JIcdOkqtlKNVt2lFJTbAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b37a8b17d1730d15ac0c1401dd3282e73e2dbda454174797e6e8c0da500817cd","last_reissued_at":"2026-07-05T10:16:25.269540Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:25.269540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MVL-SIB: A Massively Multilingual Vision-Language Benchmark for Cross-Modal Topical Matching","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chris Biemann, Fabian David Schmidt, Florian Schneider, Goran Glava\\v{s}","submitted_at":"2025-02-18T13:40:05Z","abstract_excerpt":"Existing multilingual vision-language (VL) benchmarks often only cover a handful of languages. Consequently, evaluations of large vision-language models (LVLMs) predominantly target high-resource languages, underscoring the need for evaluation data for low-resource languages. To address this limitation, we introduce MVL-SIB, a massively multilingual vision-language benchmark that evaluates both cross-modal and text-only topical matching across 205 languages -- over 100 more than the most multilingual existing VL benchmarks encompass. We then benchmark a range of of open-weight LVLMs together w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12852","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/2502.12852/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":"2502.12852","created_at":"2026-07-05T10:16:25.269599+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12852v1","created_at":"2026-07-05T10:16:25.269599+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12852","created_at":"2026-07-05T10:16:25.269599+00:00"},{"alias_kind":"pith_short_12","alias_value":"WN5IWF6ROMGR","created_at":"2026-07-05T10:16:25.269599+00:00"},{"alias_kind":"pith_short_16","alias_value":"WN5IWF6ROMGRLLAM","created_at":"2026-07-05T10:16:25.269599+00:00"},{"alias_kind":"pith_short_8","alias_value":"WN5IWF6R","created_at":"2026-07-05T10:16:25.269599+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.22123","citing_title":"Multilingual Vision-Language Models, A Survey","ref_index":123,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WN5IWF6ROMGRLLAMCQA52MUC44","json":"https://pith.science/pith/WN5IWF6ROMGRLLAMCQA52MUC44.json","graph_json":"https://pith.science/api/pith-number/WN5IWF6ROMGRLLAMCQA52MUC44/graph.json","events_json":"https://pith.science/api/pith-number/WN5IWF6ROMGRLLAMCQA52MUC44/events.json","paper":"https://pith.science/paper/WN5IWF6R"},"agent_actions":{"view_html":"https://pith.science/pith/WN5IWF6ROMGRLLAMCQA52MUC44","download_json":"https://pith.science/pith/WN5IWF6ROMGRLLAMCQA52MUC44.json","view_paper":"https://pith.science/paper/WN5IWF6R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12852&json=true","fetch_graph":"https://pith.science/api/pith-number/WN5IWF6ROMGRLLAMCQA52MUC44/graph.json","fetch_events":"https://pith.science/api/pith-number/WN5IWF6ROMGRLLAMCQA52MUC44/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WN5IWF6ROMGRLLAMCQA52MUC44/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WN5IWF6ROMGRLLAMCQA52MUC44/action/storage_attestation","attest_author":"https://pith.science/pith/WN5IWF6ROMGRLLAMCQA52MUC44/action/author_attestation","sign_citation":"https://pith.science/pith/WN5IWF6ROMGRLLAMCQA52MUC44/action/citation_signature","submit_replication":"https://pith.science/pith/WN5IWF6ROMGRLLAMCQA52MUC44/action/replication_record"}},"created_at":"2026-07-05T10:16:25.269599+00:00","updated_at":"2026-07-05T10:16:25.269599+00:00"}