{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3I2ZD355SQ6V3UKTKU5YOKLLDJ","short_pith_number":"pith:3I2ZD355","canonical_record":{"source":{"id":"2407.05975","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T14:18:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c272b623b2c68d214b81f5d67cb24ac08cb98edac575d883281ab411a5dc547","abstract_canon_sha256":"2a95f2806b03581191dbcf9004083fb320537ca4455d13ed0c6e19f3a30da6e1"},"schema_version":"1.0"},"canonical_sha256":"da3591efbd943d5dd153553b87296b1a524faba6dcfea890dda5add3c301db36","source":{"kind":"arxiv","id":"2407.05975","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05975","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05975v2","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05975","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"pith_short_12","alias_value":"3I2ZD355SQ6V","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"pith_short_16","alias_value":"3I2ZD355SQ6V3UKT","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"pith_short_8","alias_value":"3I2ZD355","created_at":"2026-07-05T09:19:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3I2ZD355SQ6V3UKTKU5YOKLLDJ","target":"record","payload":{"canonical_record":{"source":{"id":"2407.05975","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T14:18:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"8c272b623b2c68d214b81f5d67cb24ac08cb98edac575d883281ab411a5dc547","abstract_canon_sha256":"2a95f2806b03581191dbcf9004083fb320537ca4455d13ed0c6e19f3a30da6e1"},"schema_version":"1.0"},"canonical_sha256":"da3591efbd943d5dd153553b87296b1a524faba6dcfea890dda5add3c301db36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:29.900930Z","signature_b64":"qS/8mk996qoYlS/f35O7a/Lkj3eZB3qKLVydk+GyOGZYFrEzQus5hhajzTE0jjklUcbduqKa0TXW6FXJKL4oCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"da3591efbd943d5dd153553b87296b1a524faba6dcfea890dda5add3c301db36","last_reissued_at":"2026-07-05T09:19:29.900499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:29.900499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.05975","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":"2026-07-05T09:19:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fWlsOOwrZMi5oN0u9IYaOQy6rQTpIYy8l4Y9/GiyWfBIKSuS/82VPlxM6WF2780Gxi58YofpSZWQYYc/ZRfsDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:28:23.162487Z"},"content_sha256":"51785b930f7e99f58bbdf4c9e616c1f91d28ee47b855899dd0937c13f5ca40b6","schema_version":"1.0","event_id":"sha256:51785b930f7e99f58bbdf4c9e616c1f91d28ee47b855899dd0937c13f5ca40b6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3I2ZD355SQ6V3UKTKU5YOKLLDJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fei Yuan, Lei Li, Wenhao Zhu, Yinquan Lu, Yu Qiao","submitted_at":"2024-07-08T14:18:28Z","abstract_excerpt":"Large Language Models (LLMs) demonstrate remarkable translation capabilities in high-resource language tasks, yet their performance in low-resource languages is hindered by insufficient multilingual data during pre-training. To address this, we conduct extensive multilingual continual pre-training on the LLaMA series models, enabling translation support across more than 100 languages. Through a comprehensive analysis of training strategies, such as vocabulary expansion and data augmentation, we develop LLaMAX. Remarkably, without sacrificing its generalization ability, LLaMAX achieves signific"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05975","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/2407.05975/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":"2026-07-05T09:19:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yLClE55CuLrJN6y/YSGnPE/mx7HpgZsXt6+EXC9orQ8I6BSfiePer8iP4YQ/byNQDCzTmumTH4iQoj2OE30OAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:28:23.163081Z"},"content_sha256":"cf5bb8c1c825d26bce47ae70c8d25808704e28be03b94d556abcd05eefd86c8c","schema_version":"1.0","event_id":"sha256:cf5bb8c1c825d26bce47ae70c8d25808704e28be03b94d556abcd05eefd86c8c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3I2ZD355SQ6V3UKTKU5YOKLLDJ/bundle.json","state_url":"https://pith.science/pith/3I2ZD355SQ6V3UKTKU5YOKLLDJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3I2ZD355SQ6V3UKTKU5YOKLLDJ/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":"2026-08-06T05:28:23Z","links":{"resolver":"https://pith.science/pith/3I2ZD355SQ6V3UKTKU5YOKLLDJ","bundle":"https://pith.science/pith/3I2ZD355SQ6V3UKTKU5YOKLLDJ/bundle.json","state":"https://pith.science/pith/3I2ZD355SQ6V3UKTKU5YOKLLDJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3I2ZD355SQ6V3UKTKU5YOKLLDJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3I2ZD355SQ6V3UKTKU5YOKLLDJ","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":"2a95f2806b03581191dbcf9004083fb320537ca4455d13ed0c6e19f3a30da6e1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T14:18:28Z","title_canon_sha256":"8c272b623b2c68d214b81f5d67cb24ac08cb98edac575d883281ab411a5dc547"},"schema_version":"1.0","source":{"id":"2407.05975","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.05975","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"arxiv_version","alias_value":"2407.05975v2","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05975","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"pith_short_12","alias_value":"3I2ZD355SQ6V","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"pith_short_16","alias_value":"3I2ZD355SQ6V3UKT","created_at":"2026-07-05T09:19:29Z"},{"alias_kind":"pith_short_8","alias_value":"3I2ZD355","created_at":"2026-07-05T09:19:29Z"}],"graph_snapshots":[{"event_id":"sha256:cf5bb8c1c825d26bce47ae70c8d25808704e28be03b94d556abcd05eefd86c8c","target":"graph","created_at":"2026-07-05T09:19:29Z","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/2407.05975/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) demonstrate remarkable translation capabilities in high-resource language tasks, yet their performance in low-resource languages is hindered by insufficient multilingual data during pre-training. To address this, we conduct extensive multilingual continual pre-training on the LLaMA series models, enabling translation support across more than 100 languages. Through a comprehensive analysis of training strategies, such as vocabulary expansion and data augmentation, we develop LLaMAX. Remarkably, without sacrificing its generalization ability, LLaMAX achieves signific","authors_text":"Fei Yuan, Lei Li, Wenhao Zhu, Yinquan Lu, Yu Qiao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T14:18:28Z","title":"LLaMAX: Scaling Linguistic Horizons of LLM by Enhancing Translation Capabilities Beyond 100 Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05975","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":"sha256:51785b930f7e99f58bbdf4c9e616c1f91d28ee47b855899dd0937c13f5ca40b6","target":"record","created_at":"2026-07-05T09:19:29Z","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":"2a95f2806b03581191dbcf9004083fb320537ca4455d13ed0c6e19f3a30da6e1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-08T14:18:28Z","title_canon_sha256":"8c272b623b2c68d214b81f5d67cb24ac08cb98edac575d883281ab411a5dc547"},"schema_version":"1.0","source":{"id":"2407.05975","kind":"arxiv","version":2}},"canonical_sha256":"da3591efbd943d5dd153553b87296b1a524faba6dcfea890dda5add3c301db36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da3591efbd943d5dd153553b87296b1a524faba6dcfea890dda5add3c301db36","first_computed_at":"2026-07-05T09:19:29.900499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:29.900499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qS/8mk996qoYlS/f35O7a/Lkj3eZB3qKLVydk+GyOGZYFrEzQus5hhajzTE0jjklUcbduqKa0TXW6FXJKL4oCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:29.900930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.05975","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:51785b930f7e99f58bbdf4c9e616c1f91d28ee47b855899dd0937c13f5ca40b6","sha256:cf5bb8c1c825d26bce47ae70c8d25808704e28be03b94d556abcd05eefd86c8c"],"state_sha256":"131720a93768c31e249329d2387ed4d2b71c5b25755a05627a8eabce4464ddef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"adWBOoz2FFO4hrhojhTetx8LwZyz1XDGKo7zXziFMeShkonEwAlZlVWzG5FfW4uYg7DtlcTayGIA3SGy8tH6Cw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:28:23.166992Z","bundle_sha256":"2c632e1d39a19addef7d926c8593cfebca248764393edbb838fa62feaaba3654"}}