{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YWRY3MVQOSV6UTQC2MHOXAE3EW","short_pith_number":"pith:YWRY3MVQ","schema_version":"1.0","canonical_sha256":"c5a38db2b074abea4e02d30eeb809b259ee5e4228b8bda41c8b34849ecbbcd11","source":{"kind":"arxiv","id":"2508.05502","version":2},"attestation_state":"computed","paper":{"title":"MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Botian Shi, Guohang Yan, Jiaying Fei, Nuo Chen, Ruirui Chen, Yufei Gao, Yunshi Lan","submitted_at":"2025-08-07T15:36:24Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) perform strongly in high-resource languages, yet often produce fluent but culturally \"thin\" descriptions in low-resource settings. We argue that this failure is not merely a linguistic limitation: culture-specific visual knowledge depends on native visual-textual alignments that translation-centric pipelines rarely provide. We present MELLA, a multimodal dataset across eight low-resource languages, designed to support linguistic fluency and cultural groundedness. MELLA uses a dual-source strategy that combines native web image-alt-text pairs for culture"},"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":"2508.05502","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T15:36:24Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"506e13e520fade7bc4bc4609a1f56239f046aa571547f3363ecf0bf6169abd77","abstract_canon_sha256":"63e30ebbcbf0e3dbf28bb409cac8f9bdf7b355936f6f7a06cc3fa3a7ec64fc2e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T00:23:04.415409Z","signature_b64":"dnxuSfoZ5MvqAPd+Cbf66JTP6RJtaWYFIpun1L26LGrK0TayV7Ldqst30fQ0ZU7Al2O47/Epuid23x7BbbIGDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5a38db2b074abea4e02d30eeb809b259ee5e4228b8bda41c8b34849ecbbcd11","last_reissued_at":"2026-07-24T00:23:04.413622Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T00:23:04.413622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Botian Shi, Guohang Yan, Jiaying Fei, Nuo Chen, Ruirui Chen, Yufei Gao, Yunshi Lan","submitted_at":"2025-08-07T15:36:24Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) perform strongly in high-resource languages, yet often produce fluent but culturally \"thin\" descriptions in low-resource settings. We argue that this failure is not merely a linguistic limitation: culture-specific visual knowledge depends on native visual-textual alignments that translation-centric pipelines rarely provide. We present MELLA, a multimodal dataset across eight low-resource languages, designed to support linguistic fluency and cultural groundedness. MELLA uses a dual-source strategy that combines native web image-alt-text pairs for culture"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05502","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.05502/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":"2508.05502","created_at":"2026-07-24T00:23:04.414567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.05502v2","created_at":"2026-07-24T00:23:04.414567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05502","created_at":"2026-07-24T00:23:04.414567+00:00"},{"alias_kind":"pith_short_12","alias_value":"YWRY3MVQOSV6","created_at":"2026-07-24T00:23:04.414567+00:00"},{"alias_kind":"pith_short_16","alias_value":"YWRY3MVQOSV6UTQC","created_at":"2026-07-24T00:23:04.414567+00:00"},{"alias_kind":"pith_short_8","alias_value":"YWRY3MVQ","created_at":"2026-07-24T00:23:04.414567+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/YWRY3MVQOSV6UTQC2MHOXAE3EW","json":"https://pith.science/pith/YWRY3MVQOSV6UTQC2MHOXAE3EW.json","graph_json":"https://pith.science/api/pith-number/YWRY3MVQOSV6UTQC2MHOXAE3EW/graph.json","events_json":"https://pith.science/api/pith-number/YWRY3MVQOSV6UTQC2MHOXAE3EW/events.json","paper":"https://pith.science/paper/YWRY3MVQ"},"agent_actions":{"view_html":"https://pith.science/pith/YWRY3MVQOSV6UTQC2MHOXAE3EW","download_json":"https://pith.science/pith/YWRY3MVQOSV6UTQC2MHOXAE3EW.json","view_paper":"https://pith.science/paper/YWRY3MVQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.05502&json=true","fetch_graph":"https://pith.science/api/pith-number/YWRY3MVQOSV6UTQC2MHOXAE3EW/graph.json","fetch_events":"https://pith.science/api/pith-number/YWRY3MVQOSV6UTQC2MHOXAE3EW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YWRY3MVQOSV6UTQC2MHOXAE3EW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YWRY3MVQOSV6UTQC2MHOXAE3EW/action/storage_attestation","attest_author":"https://pith.science/pith/YWRY3MVQOSV6UTQC2MHOXAE3EW/action/author_attestation","sign_citation":"https://pith.science/pith/YWRY3MVQOSV6UTQC2MHOXAE3EW/action/citation_signature","submit_replication":"https://pith.science/pith/YWRY3MVQOSV6UTQC2MHOXAE3EW/action/replication_record"}},"created_at":"2026-07-24T00:23:04.414567+00:00","updated_at":"2026-07-24T00:23:04.414567+00:00"}