{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:C2QH2TGFFUFOAJVTHUNZY4IHVL","short_pith_number":"pith:C2QH2TGF","canonical_record":{"source":{"id":"2403.11399","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T01:14:47Z","cross_cats_sorted":[],"title_canon_sha256":"b9a9e28450f9f2fbf10248abada9029b0c73bac5213d1bf120ffcdd44d5b9d68","abstract_canon_sha256":"8374efb896931a4cd055b6a012e1d20acbdf3961b1b7ff56e2124d2b29e38ea1"},"schema_version":"1.0"},"canonical_sha256":"16a07d4cc52d0ae026b33d1b9c7107aad212ec3460f766ed52d556b8eed452a4","source":{"kind":"arxiv","id":"2403.11399","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11399","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11399v3","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11399","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"pith_short_12","alias_value":"C2QH2TGFFUFO","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"pith_short_16","alias_value":"C2QH2TGFFUFOAJVT","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"pith_short_8","alias_value":"C2QH2TGF","created_at":"2026-07-05T08:51:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:C2QH2TGFFUFOAJVTHUNZY4IHVL","target":"record","payload":{"canonical_record":{"source":{"id":"2403.11399","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T01:14:47Z","cross_cats_sorted":[],"title_canon_sha256":"b9a9e28450f9f2fbf10248abada9029b0c73bac5213d1bf120ffcdd44d5b9d68","abstract_canon_sha256":"8374efb896931a4cd055b6a012e1d20acbdf3961b1b7ff56e2124d2b29e38ea1"},"schema_version":"1.0"},"canonical_sha256":"16a07d4cc52d0ae026b33d1b9c7107aad212ec3460f766ed52d556b8eed452a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:51:37.197182Z","signature_b64":"EP9SLhE5qWHl1lvHD1vMgtqi9QWCKid2S/Kyn6wkz8DQCRDugMCSPItZt9TfIEdVjPW4OnPhHOBKyaHd/6bfDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16a07d4cc52d0ae026b33d1b9c7107aad212ec3460f766ed52d556b8eed452a4","last_reissued_at":"2026-07-05T08:51:37.196658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:51:37.196658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.11399","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:51:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v5prR0bVuSn+TnVRpr5lQ9KoGW4TBHnx/1zyPEqb7lwsZfoad+zqxO0v4RQgonvRoK6Z7tBTwPaDWmEv5CiQBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:24:48.078394Z"},"content_sha256":"b589d875f9777dc07aaff3ab66f8abb45b21e460010584efa8a1d9042b2f2519","schema_version":"1.0","event_id":"sha256:b589d875f9777dc07aaff3ab66f8abb45b21e460010584efa8a1d9042b2f2519"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:C2QH2TGFFUFOAJVTHUNZY4IHVL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"X-LLaVA: Optimizing Bilingual Large Vision-Language Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Changsu Choi, Dongjae Shin, Hangyeol Yoo, HyeonSeok Lim, InHo Won, KyungTae Lim, Minjun Kim, Sangmin Kim, Seungwoo Song","submitted_at":"2024-03-18T01:14:47Z","abstract_excerpt":"The impressive development of large language models (LLMs) is expanding into the realm of large multimodal models (LMMs), which incorporate multiple types of data beyond text. However, the nature of multimodal models leads to significant expenses in the creation of training data. Furthermore, constructing multilingual data for LMMs presents its own set of challenges due to language diversity and complexity. Therefore, in this study, we propose two cost-effective methods to solve this problem: (1) vocabulary expansion and pretraining of multilingual LLM for specific languages, and (2) automatic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11399","kind":"arxiv","version":3},"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/2403.11399/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":"2026-07-05T08:51:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jXbcznbfOBbY3aXP+8Sanp6FcvJ0tfKV4+PXF/tGZChJjvjbZ7xMxNDNkRpNew8iYjE4OfG9zEByiSyLeHoaDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T13:24:48.079457Z"},"content_sha256":"6d552a70df749190ee5f26afc304ffbaa0a1e436e91617f318ca59b4a9fe2fd7","schema_version":"1.0","event_id":"sha256:6d552a70df749190ee5f26afc304ffbaa0a1e436e91617f318ca59b4a9fe2fd7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/C2QH2TGFFUFOAJVTHUNZY4IHVL/bundle.json","state_url":"https://pith.science/pith/C2QH2TGFFUFOAJVTHUNZY4IHVL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/C2QH2TGFFUFOAJVTHUNZY4IHVL/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":"2026-08-06T13:24:48Z","links":{"resolver":"https://pith.science/pith/C2QH2TGFFUFOAJVTHUNZY4IHVL","bundle":"https://pith.science/pith/C2QH2TGFFUFOAJVTHUNZY4IHVL/bundle.json","state":"https://pith.science/pith/C2QH2TGFFUFOAJVTHUNZY4IHVL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/C2QH2TGFFUFOAJVTHUNZY4IHVL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C2QH2TGFFUFOAJVTHUNZY4IHVL","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":"8374efb896931a4cd055b6a012e1d20acbdf3961b1b7ff56e2124d2b29e38ea1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T01:14:47Z","title_canon_sha256":"b9a9e28450f9f2fbf10248abada9029b0c73bac5213d1bf120ffcdd44d5b9d68"},"schema_version":"1.0","source":{"id":"2403.11399","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11399","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11399v3","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11399","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"pith_short_12","alias_value":"C2QH2TGFFUFO","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"pith_short_16","alias_value":"C2QH2TGFFUFOAJVT","created_at":"2026-07-05T08:51:37Z"},{"alias_kind":"pith_short_8","alias_value":"C2QH2TGF","created_at":"2026-07-05T08:51:37Z"}],"graph_snapshots":[{"event_id":"sha256:6d552a70df749190ee5f26afc304ffbaa0a1e436e91617f318ca59b4a9fe2fd7","target":"graph","created_at":"2026-07-05T08:51:37Z","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/2403.11399/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The impressive development of large language models (LLMs) is expanding into the realm of large multimodal models (LMMs), which incorporate multiple types of data beyond text. However, the nature of multimodal models leads to significant expenses in the creation of training data. Furthermore, constructing multilingual data for LMMs presents its own set of challenges due to language diversity and complexity. Therefore, in this study, we propose two cost-effective methods to solve this problem: (1) vocabulary expansion and pretraining of multilingual LLM for specific languages, and (2) automatic","authors_text":"Changsu Choi, Dongjae Shin, Hangyeol Yoo, HyeonSeok Lim, InHo Won, KyungTae Lim, Minjun Kim, Sangmin Kim, Seungwoo Song","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T01:14:47Z","title":"X-LLaVA: Optimizing Bilingual Large Vision-Language Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11399","kind":"arxiv","version":3},"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:b589d875f9777dc07aaff3ab66f8abb45b21e460010584efa8a1d9042b2f2519","target":"record","created_at":"2026-07-05T08:51:37Z","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":"8374efb896931a4cd055b6a012e1d20acbdf3961b1b7ff56e2124d2b29e38ea1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-18T01:14:47Z","title_canon_sha256":"b9a9e28450f9f2fbf10248abada9029b0c73bac5213d1bf120ffcdd44d5b9d68"},"schema_version":"1.0","source":{"id":"2403.11399","kind":"arxiv","version":3}},"canonical_sha256":"16a07d4cc52d0ae026b33d1b9c7107aad212ec3460f766ed52d556b8eed452a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16a07d4cc52d0ae026b33d1b9c7107aad212ec3460f766ed52d556b8eed452a4","first_computed_at":"2026-07-05T08:51:37.196658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:51:37.196658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EP9SLhE5qWHl1lvHD1vMgtqi9QWCKid2S/Kyn6wkz8DQCRDugMCSPItZt9TfIEdVjPW4OnPhHOBKyaHd/6bfDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:51:37.197182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11399","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b589d875f9777dc07aaff3ab66f8abb45b21e460010584efa8a1d9042b2f2519","sha256:6d552a70df749190ee5f26afc304ffbaa0a1e436e91617f318ca59b4a9fe2fd7"],"state_sha256":"6abb7f057f911c66785b32c883fc1237e268a743f4d5ade05daa7c29f227dafb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lf8/eNo+L7WqPtSzjZyvLlJZ5SZLDs26O6p2rtuX6ORkzu7ymLsvpusZXh9jXWHfiUW6QlWT56x2lbMbLz/lDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T13:24:48.087419Z","bundle_sha256":"cfb9419b39304c0a2ab616dd8a6847560ffa636d546220044c790a0e132a89c6"}}