{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PJPTV7FHSR6GODV5KJGVMX7USD","short_pith_number":"pith:PJPTV7FH","canonical_record":{"source":{"id":"2403.10882","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-16T10:26:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68c62aa524ba342770f9863bfe3abf337414ce2cac493da0926000445f938420","abstract_canon_sha256":"471cdbd310a1faf938b5123e92fa10047c2cb2a1edc7da9c98abd89f53974cc6"},"schema_version":"1.0"},"canonical_sha256":"7a5f3afca7947c670ebd524d565ff490e6812662e4f6340c16ae508be9130139","source":{"kind":"arxiv","id":"2403.10882","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10882","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10882v2","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10882","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"pith_short_12","alias_value":"PJPTV7FHSR6G","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"pith_short_16","alias_value":"PJPTV7FHSR6GODV5","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"pith_short_8","alias_value":"PJPTV7FH","created_at":"2026-07-05T07:59:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PJPTV7FHSR6GODV5KJGVMX7USD","target":"record","payload":{"canonical_record":{"source":{"id":"2403.10882","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-16T10:26:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"68c62aa524ba342770f9863bfe3abf337414ce2cac493da0926000445f938420","abstract_canon_sha256":"471cdbd310a1faf938b5123e92fa10047c2cb2a1edc7da9c98abd89f53974cc6"},"schema_version":"1.0"},"canonical_sha256":"7a5f3afca7947c670ebd524d565ff490e6812662e4f6340c16ae508be9130139","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:05.870270Z","signature_b64":"9kTdxxVWfl1QTMV9Q3vwQXqtgbiPH35vb1xCZKywcZQDP7LNgFq2Grzkedpl8TCjJfTpTEMw7UaY0UAwYuyBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a5f3afca7947c670ebd524d565ff490e6812662e4f6340c16ae508be9130139","last_reissued_at":"2026-07-05T07:59:05.869854Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:05.869854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.10882","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":"2026-07-05T07:59:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iqPo+dp4CBHhZepb9bPeVMqBnTeUwqTmiwtOh7i0b/J3nlAvWEcLlnGeHYzEg1r0Kp41cc1fSJ9H0YihKwhkCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:46:18.009894Z"},"content_sha256":"a103bb9ea15b3f38e41a3077e096dbb5d59da655348dfb0f194dd39d12d26b47","schema_version":"1.0","event_id":"sha256:a103bb9ea15b3f38e41a3077e096dbb5d59da655348dfb0f194dd39d12d26b47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PJPTV7FHSR6GODV5KJGVMX7USD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Optimizing Language Augmentation for Multilingual Large Language Models: A Case Study on Korean","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Changsu Choi, Chanhyuk Yoon, Hansaem Kim, Hyejin Lee, HyeonSeok Lim, InHo Won, Jaewan Park, KyungTae Lim, Sangmin Kim, Seoyoon Park, Yejee Kang, Yiseul Lee, Yongbin Jeong, Younggyun Hahm","submitted_at":"2024-03-16T10:26:38Z","abstract_excerpt":"Large language models (LLMs) use pretraining to predict the subsequent word; however, their expansion requires significant computing resources. Numerous big tech companies and research institutes have developed multilingual LLMs (MLLMs) to meet current demands, overlooking less-resourced languages (LRLs). This study proposed three strategies to enhance the performance of LRLs based on the publicly available MLLMs. First, the MLLM vocabularies of LRLs were expanded to enhance expressiveness. Second, bilingual data were used for pretraining to align the high- and less-resourced languages. Third,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10882","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/2403.10882/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":"2026-07-05T07:59:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XmxquSPoTFAhtqcvCJd1Q4fjbhHpjpE2spMFDjdclNMDG46xzfigAcZi5dv/7iuN+Ex0JuFq1F/oLLuzgzGhBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T11:46:18.010510Z"},"content_sha256":"5304ad10b18c621071f2c814b26b15108b11f3cf74f7dfb3f1dde4bcfe0b624a","schema_version":"1.0","event_id":"sha256:5304ad10b18c621071f2c814b26b15108b11f3cf74f7dfb3f1dde4bcfe0b624a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PJPTV7FHSR6GODV5KJGVMX7USD/bundle.json","state_url":"https://pith.science/pith/PJPTV7FHSR6GODV5KJGVMX7USD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PJPTV7FHSR6GODV5KJGVMX7USD/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":"2026-08-11T11:46:18Z","links":{"resolver":"https://pith.science/pith/PJPTV7FHSR6GODV5KJGVMX7USD","bundle":"https://pith.science/pith/PJPTV7FHSR6GODV5KJGVMX7USD/bundle.json","state":"https://pith.science/pith/PJPTV7FHSR6GODV5KJGVMX7USD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PJPTV7FHSR6GODV5KJGVMX7USD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PJPTV7FHSR6GODV5KJGVMX7USD","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":"471cdbd310a1faf938b5123e92fa10047c2cb2a1edc7da9c98abd89f53974cc6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-16T10:26:38Z","title_canon_sha256":"68c62aa524ba342770f9863bfe3abf337414ce2cac493da0926000445f938420"},"schema_version":"1.0","source":{"id":"2403.10882","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10882","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10882v2","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10882","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"pith_short_12","alias_value":"PJPTV7FHSR6G","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"pith_short_16","alias_value":"PJPTV7FHSR6GODV5","created_at":"2026-07-05T07:59:05Z"},{"alias_kind":"pith_short_8","alias_value":"PJPTV7FH","created_at":"2026-07-05T07:59:05Z"}],"graph_snapshots":[{"event_id":"sha256:5304ad10b18c621071f2c814b26b15108b11f3cf74f7dfb3f1dde4bcfe0b624a","target":"graph","created_at":"2026-07-05T07:59:05Z","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/2403.10882/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) use pretraining to predict the subsequent word; however, their expansion requires significant computing resources. Numerous big tech companies and research institutes have developed multilingual LLMs (MLLMs) to meet current demands, overlooking less-resourced languages (LRLs). This study proposed three strategies to enhance the performance of LRLs based on the publicly available MLLMs. First, the MLLM vocabularies of LRLs were expanded to enhance expressiveness. Second, bilingual data were used for pretraining to align the high- and less-resourced languages. Third,","authors_text":"Changsu Choi, Chanhyuk Yoon, Hansaem Kim, Hyejin Lee, HyeonSeok Lim, InHo Won, Jaewan Park, KyungTae Lim, Sangmin Kim, Seoyoon Park, Yejee Kang, Yiseul Lee, Yongbin Jeong, Younggyun Hahm","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-16T10:26:38Z","title":"Optimizing Language Augmentation for Multilingual Large Language Models: A Case Study on Korean"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10882","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:a103bb9ea15b3f38e41a3077e096dbb5d59da655348dfb0f194dd39d12d26b47","target":"record","created_at":"2026-07-05T07:59:05Z","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":"471cdbd310a1faf938b5123e92fa10047c2cb2a1edc7da9c98abd89f53974cc6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-16T10:26:38Z","title_canon_sha256":"68c62aa524ba342770f9863bfe3abf337414ce2cac493da0926000445f938420"},"schema_version":"1.0","source":{"id":"2403.10882","kind":"arxiv","version":2}},"canonical_sha256":"7a5f3afca7947c670ebd524d565ff490e6812662e4f6340c16ae508be9130139","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a5f3afca7947c670ebd524d565ff490e6812662e4f6340c16ae508be9130139","first_computed_at":"2026-07-05T07:59:05.869854Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:05.869854Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9kTdxxVWfl1QTMV9Q3vwQXqtgbiPH35vb1xCZKywcZQDP7LNgFq2Grzkedpl8TCjJfTpTEMw7UaY0UAwYuyBDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:05.870270Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.10882","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a103bb9ea15b3f38e41a3077e096dbb5d59da655348dfb0f194dd39d12d26b47","sha256:5304ad10b18c621071f2c814b26b15108b11f3cf74f7dfb3f1dde4bcfe0b624a"],"state_sha256":"275b8ae4b9436dcefd33be3100579901ea1e8b589005e9c55b91390a09f63d30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/DJD+JI3a3DG0fDq3GMMWVMu5DOdT2KREUIgLiq1GAR52aA+WnU+IEyfupxWJYjxtMUq93yiiqb7Ese8OuVnDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T11:46:18.016908Z","bundle_sha256":"babbb3927ee12986153a88b595afb5a850dd365b21895538b02d5506dc7f0b0c"}}