{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:CROECZPVM54SX4YDHIHI6HIVYX","short_pith_number":"pith:CROECZPV","canonical_record":{"source":{"id":"2508.07414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T16:24:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"45af3dd86c66a16babfea8e8b351c96913a564c5506d4776d8ed43e461200996","abstract_canon_sha256":"89d93ca6a5c53d52a9b5cf5443050f55ee24418a901239dce3b808a42f33bae1"},"schema_version":"1.0"},"canonical_sha256":"145c4165f567792bf3033a0e8f1d15c5d59a48044720cfbfee52f86989b33ef8","source":{"kind":"arxiv","id":"2508.07414","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07414","created_at":"2026-07-05T11:52:24Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07414v2","created_at":"2026-07-05T11:52:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07414","created_at":"2026-07-05T11:52:24Z"},{"alias_kind":"pith_short_12","alias_value":"CROECZPVM54S","created_at":"2026-07-05T11:52:24Z"},{"alias_kind":"pith_short_16","alias_value":"CROECZPVM54SX4YD","created_at":"2026-07-05T11:52:24Z"},{"alias_kind":"pith_short_8","alias_value":"CROECZPV","created_at":"2026-07-05T11:52:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:CROECZPVM54SX4YDHIHI6HIVYX","target":"record","payload":{"canonical_record":{"source":{"id":"2508.07414","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T16:24:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"45af3dd86c66a16babfea8e8b351c96913a564c5506d4776d8ed43e461200996","abstract_canon_sha256":"89d93ca6a5c53d52a9b5cf5443050f55ee24418a901239dce3b808a42f33bae1"},"schema_version":"1.0"},"canonical_sha256":"145c4165f567792bf3033a0e8f1d15c5d59a48044720cfbfee52f86989b33ef8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:24.321308Z","signature_b64":"xVGhrPjThTUYIjsy0QNHUGP3xryr6Rg2LpZsHXg3+PPoUO8NZrL2y1ru/vBVnXu5K2+jD8MZnZ+1zjyYlCP8Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"145c4165f567792bf3033a0e8f1d15c5d59a48044720cfbfee52f86989b33ef8","last_reissued_at":"2026-07-05T11:52:24.320883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:24.320883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.07414","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:52:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1U8v8Ygnk0m4IzdCBNWJkTBhbVXdsCY/413Fu6pTftUZvB6wMrDolGZVJ3718XfEdl8boM/bhjL2hj4w6R1GBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:19:15.029348Z"},"content_sha256":"d042869072a4ab0062240ebbd308d4535e76ecaafe32b263108148e5630cf14e","schema_version":"1.0","event_id":"sha256:d042869072a4ab0062240ebbd308d4535e76ecaafe32b263108148e5630cf14e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:CROECZPVM54SX4YDHIHI6HIVYX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grounding Multilingual Multimodal LLMs With Cultural Knowledge","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Jean de Dieu Nyandwi, Simran Khanuja, Yueqi Song","submitted_at":"2025-08-10T16:24:11Z","abstract_excerpt":"Multimodal Large Language Models excel in high-resource settings, but often misinterpret long-tail cultural entities and underperform in low-resource languages. To address this gap, we propose a data-centric approach that directly grounds MLLMs in cultural knowledge. Leveraging a large scale knowledge graph from Wikidata, we collect images that represent culturally significant entities, and generate synthetic multilingual visual question answering data. The resulting dataset, CulturalGround, comprises 22 million high-quality, culturally-rich VQA pairs spanning 42 countries and 39 languages. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07414","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/2508.07414/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:52:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EVwWp6fOLtzqNZaAJ+Y6uCifJpCdGTE3dL4kZdVC5iiGUlE9xJVcqE53VpbagWl3Z9H7EWnQDQUetz9dupfaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T17:19:15.029903Z"},"content_sha256":"1956b807fb30f0bf78965f8dca9b3b316166bf9f381cdcb60b5eec3d7caf63b2","schema_version":"1.0","event_id":"sha256:1956b807fb30f0bf78965f8dca9b3b316166bf9f381cdcb60b5eec3d7caf63b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CROECZPVM54SX4YDHIHI6HIVYX/bundle.json","state_url":"https://pith.science/pith/CROECZPVM54SX4YDHIHI6HIVYX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CROECZPVM54SX4YDHIHI6HIVYX/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-15T17:19:15Z","links":{"resolver":"https://pith.science/pith/CROECZPVM54SX4YDHIHI6HIVYX","bundle":"https://pith.science/pith/CROECZPVM54SX4YDHIHI6HIVYX/bundle.json","state":"https://pith.science/pith/CROECZPVM54SX4YDHIHI6HIVYX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CROECZPVM54SX4YDHIHI6HIVYX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CROECZPVM54SX4YDHIHI6HIVYX","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":"89d93ca6a5c53d52a9b5cf5443050f55ee24418a901239dce3b808a42f33bae1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T16:24:11Z","title_canon_sha256":"45af3dd86c66a16babfea8e8b351c96913a564c5506d4776d8ed43e461200996"},"schema_version":"1.0","source":{"id":"2508.07414","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.07414","created_at":"2026-07-05T11:52:24Z"},{"alias_kind":"arxiv_version","alias_value":"2508.07414v2","created_at":"2026-07-05T11:52:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.07414","created_at":"2026-07-05T11:52:24Z"},{"alias_kind":"pith_short_12","alias_value":"CROECZPVM54S","created_at":"2026-07-05T11:52:24Z"},{"alias_kind":"pith_short_16","alias_value":"CROECZPVM54SX4YD","created_at":"2026-07-05T11:52:24Z"},{"alias_kind":"pith_short_8","alias_value":"CROECZPV","created_at":"2026-07-05T11:52:24Z"}],"graph_snapshots":[{"event_id":"sha256:1956b807fb30f0bf78965f8dca9b3b316166bf9f381cdcb60b5eec3d7caf63b2","target":"graph","created_at":"2026-07-05T11:52:24Z","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/2508.07414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models excel in high-resource settings, but often misinterpret long-tail cultural entities and underperform in low-resource languages. To address this gap, we propose a data-centric approach that directly grounds MLLMs in cultural knowledge. Leveraging a large scale knowledge graph from Wikidata, we collect images that represent culturally significant entities, and generate synthetic multilingual visual question answering data. The resulting dataset, CulturalGround, comprises 22 million high-quality, culturally-rich VQA pairs spanning 42 countries and 39 languages. We","authors_text":"Graham Neubig, Jean de Dieu Nyandwi, Simran Khanuja, Yueqi Song","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T16:24:11Z","title":"Grounding Multilingual Multimodal LLMs With Cultural Knowledge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.07414","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:d042869072a4ab0062240ebbd308d4535e76ecaafe32b263108148e5630cf14e","target":"record","created_at":"2026-07-05T11:52:24Z","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":"89d93ca6a5c53d52a9b5cf5443050f55ee24418a901239dce3b808a42f33bae1","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-10T16:24:11Z","title_canon_sha256":"45af3dd86c66a16babfea8e8b351c96913a564c5506d4776d8ed43e461200996"},"schema_version":"1.0","source":{"id":"2508.07414","kind":"arxiv","version":2}},"canonical_sha256":"145c4165f567792bf3033a0e8f1d15c5d59a48044720cfbfee52f86989b33ef8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"145c4165f567792bf3033a0e8f1d15c5d59a48044720cfbfee52f86989b33ef8","first_computed_at":"2026-07-05T11:52:24.320883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:24.320883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xVGhrPjThTUYIjsy0QNHUGP3xryr6Rg2LpZsHXg3+PPoUO8NZrL2y1ru/vBVnXu5K2+jD8MZnZ+1zjyYlCP8Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:24.321308Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.07414","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d042869072a4ab0062240ebbd308d4535e76ecaafe32b263108148e5630cf14e","sha256:1956b807fb30f0bf78965f8dca9b3b316166bf9f381cdcb60b5eec3d7caf63b2"],"state_sha256":"e7f788cdd253a92bb394642babfb3b562e285fcc189e15513d7a72b91b33341c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C44lGpw6B0JrhYTYn5aUvpov056awW8iGmxOJ33wP6g875FVM0HcNJS2orDkXzp0eDrqCGoehIwph0tBsJdkCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T17:19:15.033439Z","bundle_sha256":"569972e582da5860d291a0b766bfd0d834275b0f11e97b4d8ed4a4ac373fb49a"}}