{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YWRY3MVQOSV6UTQC2MHOXAE3EW","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"63e30ebbcbf0e3dbf28bb409cac8f9bdf7b355936f6f7a06cc3fa3a7ec64fc2e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T15:36:24Z","title_canon_sha256":"506e13e520fade7bc4bc4609a1f56239f046aa571547f3363ecf0bf6169abd77"},"schema_version":"1.0","source":{"id":"2508.05502","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.05502","created_at":"2026-07-24T00:23:04Z"},{"alias_kind":"arxiv_version","alias_value":"2508.05502v2","created_at":"2026-07-24T00:23:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.05502","created_at":"2026-07-24T00:23:04Z"},{"alias_kind":"pith_short_12","alias_value":"YWRY3MVQOSV6","created_at":"2026-07-24T00:23:04Z"},{"alias_kind":"pith_short_16","alias_value":"YWRY3MVQOSV6UTQC","created_at":"2026-07-24T00:23:04Z"},{"alias_kind":"pith_short_8","alias_value":"YWRY3MVQ","created_at":"2026-07-24T00:23:04Z"}],"graph_snapshots":[{"event_id":"sha256:9e1752a3b067890bb9527f4e14f857cd2f07bdf17208c515d38bba2a66da376d","target":"graph","created_at":"2026-07-24T00:23:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2508.05502/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Botian Shi, Guohang Yan, Jiaying Fei, Nuo Chen, Ruirui Chen, Yufei Gao, Yunshi Lan","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T15:36:24Z","title":"MELLA: Bridging Linguistic Capability and Cultural Groundedness for Low-Resource Language MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.05502","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:994535d344df51c3c4eb22f011b4ba5270b47c30ffcf9a63b36beb0abaa642b7","target":"record","created_at":"2026-07-24T00:23:04Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"63e30ebbcbf0e3dbf28bb409cac8f9bdf7b355936f6f7a06cc3fa3a7ec64fc2e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-07T15:36:24Z","title_canon_sha256":"506e13e520fade7bc4bc4609a1f56239f046aa571547f3363ecf0bf6169abd77"},"schema_version":"1.0","source":{"id":"2508.05502","kind":"arxiv","version":2}},"canonical_sha256":"c5a38db2b074abea4e02d30eeb809b259ee5e4228b8bda41c8b34849ecbbcd11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5a38db2b074abea4e02d30eeb809b259ee5e4228b8bda41c8b34849ecbbcd11","first_computed_at":"2026-07-24T00:23:04.413622Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T00:23:04.413622Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dnxuSfoZ5MvqAPd+Cbf66JTP6RJtaWYFIpun1L26LGrK0TayV7Ldqst30fQ0ZU7Al2O47/Epuid23x7BbbIGDQ==","signature_status":"signed_v1","signed_at":"2026-07-24T00:23:04.415409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.05502","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:994535d344df51c3c4eb22f011b4ba5270b47c30ffcf9a63b36beb0abaa642b7","sha256:9e1752a3b067890bb9527f4e14f857cd2f07bdf17208c515d38bba2a66da376d"],"state_sha256":"ce1b915fd0667049011a7d30c466e3e51f2520fb9f8a8290842dc8033f6946ec"}