{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:SVT5FRFMPIOF2C6YVU6DUTHGIF","short_pith_number":"pith:SVT5FRFM","canonical_record":{"source":{"id":"2308.04948","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-09T13:32:06Z","cross_cats_sorted":[],"title_canon_sha256":"bcbd6c274443075df01f9731c0f96c0e1562ce883ebce2b7386565bb3fb69f0c","abstract_canon_sha256":"6bc1b05197166136de000251b7118b589d8e83e6193683adce781d55ec71896b"},"schema_version":"1.0"},"canonical_sha256":"9567d2c4ac7a1c5d0bd8ad3c3a4ce6416d895fc912201497480c1e8f2b002ae1","source":{"kind":"arxiv","id":"2308.04948","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.04948","created_at":"2026-07-05T06:58:41Z"},{"alias_kind":"arxiv_version","alias_value":"2308.04948v2","created_at":"2026-07-05T06:58:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04948","created_at":"2026-07-05T06:58:41Z"},{"alias_kind":"pith_short_12","alias_value":"SVT5FRFMPIOF","created_at":"2026-07-05T06:58:41Z"},{"alias_kind":"pith_short_16","alias_value":"SVT5FRFMPIOF2C6Y","created_at":"2026-07-05T06:58:41Z"},{"alias_kind":"pith_short_8","alias_value":"SVT5FRFM","created_at":"2026-07-05T06:58:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:SVT5FRFMPIOF2C6YVU6DUTHGIF","target":"record","payload":{"canonical_record":{"source":{"id":"2308.04948","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-09T13:32:06Z","cross_cats_sorted":[],"title_canon_sha256":"bcbd6c274443075df01f9731c0f96c0e1562ce883ebce2b7386565bb3fb69f0c","abstract_canon_sha256":"6bc1b05197166136de000251b7118b589d8e83e6193683adce781d55ec71896b"},"schema_version":"1.0"},"canonical_sha256":"9567d2c4ac7a1c5d0bd8ad3c3a4ce6416d895fc912201497480c1e8f2b002ae1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:58:41.759522Z","signature_b64":"aJaSVItTxtlorC/nX9jzgRUz/oewiK21+vpcS3lHgU/sggG73sButr2lHPB0UnNe39OGNVhCJ2gi2YGO6VRvBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9567d2c4ac7a1c5d0bd8ad3c3a4ce6416d895fc912201497480c1e8f2b002ae1","last_reissued_at":"2026-07-05T06:58:41.759003Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:58:41.759003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.04948","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":"2026-07-05T06:58:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q5X8jHDvc3TxrK18Ov788PMlDYW9MVuAEjenG/RU1DjMs3BAyPErLC+LoXP4OIb7mr/nbci5f5+decaxNwjiDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T11:19:50.529148Z"},"content_sha256":"f1d6e254ad60e993c39fef545884ed23e0ad3f4d359e6f9ff5831988c7a011e7","schema_version":"1.0","event_id":"sha256:f1d6e254ad60e993c39fef545884ed23e0ad3f4d359e6f9ff5831988c7a011e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:SVT5FRFMPIOF2C6YVU6DUTHGIF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extrapolating Large Language Models to Non-English by Aligning Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Yuan, Jiajun Chen, Jingjing Xu, Lei Li, Lingpeng Kong, Qingxiu Dong, Shujian Huang, Wenhao Zhu, Yunzhe Lv","submitted_at":"2023-08-09T13:32:06Z","abstract_excerpt":"Existing large language models show disparate capability across different languages, due to the imbalance in the training data. Their performances on English tasks are often stronger than on tasks of other languages. In this paper, we empower pre-trained LLMs on non-English languages by building semantic alignment across languages. We start from targeting individual languages by performing cross-lingual instruction-tuning (CoIT) on LLaMA, i.e. tuning it with translation task data and cross-lingual general task data to obtain cross-lingual models (x-LLaMAs), and formulate underlying scaling law"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04948","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/2308.04948/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":"2026-07-05T06:58:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pMJeOpSCNJ+MIGceGWaIJf7deBwZZLbn2bh1NYCIxfmdp6zt2+Hj9Mg9k4LmKviok2rVkzmjXPp2mIPUP/aYDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T11:19:50.529801Z"},"content_sha256":"4cd4d615833197e2b6331a29cdae1e11a5d617681045e7ed9b1b4b922fc29414","schema_version":"1.0","event_id":"sha256:4cd4d615833197e2b6331a29cdae1e11a5d617681045e7ed9b1b4b922fc29414"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SVT5FRFMPIOF2C6YVU6DUTHGIF/bundle.json","state_url":"https://pith.science/pith/SVT5FRFMPIOF2C6YVU6DUTHGIF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SVT5FRFMPIOF2C6YVU6DUTHGIF/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":"2026-08-01T11:19:50Z","links":{"resolver":"https://pith.science/pith/SVT5FRFMPIOF2C6YVU6DUTHGIF","bundle":"https://pith.science/pith/SVT5FRFMPIOF2C6YVU6DUTHGIF/bundle.json","state":"https://pith.science/pith/SVT5FRFMPIOF2C6YVU6DUTHGIF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SVT5FRFMPIOF2C6YVU6DUTHGIF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:SVT5FRFMPIOF2C6YVU6DUTHGIF","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":"6bc1b05197166136de000251b7118b589d8e83e6193683adce781d55ec71896b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-09T13:32:06Z","title_canon_sha256":"bcbd6c274443075df01f9731c0f96c0e1562ce883ebce2b7386565bb3fb69f0c"},"schema_version":"1.0","source":{"id":"2308.04948","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.04948","created_at":"2026-07-05T06:58:41Z"},{"alias_kind":"arxiv_version","alias_value":"2308.04948v2","created_at":"2026-07-05T06:58:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04948","created_at":"2026-07-05T06:58:41Z"},{"alias_kind":"pith_short_12","alias_value":"SVT5FRFMPIOF","created_at":"2026-07-05T06:58:41Z"},{"alias_kind":"pith_short_16","alias_value":"SVT5FRFMPIOF2C6Y","created_at":"2026-07-05T06:58:41Z"},{"alias_kind":"pith_short_8","alias_value":"SVT5FRFM","created_at":"2026-07-05T06:58:41Z"}],"graph_snapshots":[{"event_id":"sha256:4cd4d615833197e2b6331a29cdae1e11a5d617681045e7ed9b1b4b922fc29414","target":"graph","created_at":"2026-07-05T06:58:41Z","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/2308.04948/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing large language models show disparate capability across different languages, due to the imbalance in the training data. Their performances on English tasks are often stronger than on tasks of other languages. In this paper, we empower pre-trained LLMs on non-English languages by building semantic alignment across languages. We start from targeting individual languages by performing cross-lingual instruction-tuning (CoIT) on LLaMA, i.e. tuning it with translation task data and cross-lingual general task data to obtain cross-lingual models (x-LLaMAs), and formulate underlying scaling law","authors_text":"Fei Yuan, Jiajun Chen, Jingjing Xu, Lei Li, Lingpeng Kong, Qingxiu Dong, Shujian Huang, Wenhao Zhu, Yunzhe Lv","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-09T13:32:06Z","title":"Extrapolating Large Language Models to Non-English by Aligning Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04948","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:f1d6e254ad60e993c39fef545884ed23e0ad3f4d359e6f9ff5831988c7a011e7","target":"record","created_at":"2026-07-05T06:58:41Z","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":"6bc1b05197166136de000251b7118b589d8e83e6193683adce781d55ec71896b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-08-09T13:32:06Z","title_canon_sha256":"bcbd6c274443075df01f9731c0f96c0e1562ce883ebce2b7386565bb3fb69f0c"},"schema_version":"1.0","source":{"id":"2308.04948","kind":"arxiv","version":2}},"canonical_sha256":"9567d2c4ac7a1c5d0bd8ad3c3a4ce6416d895fc912201497480c1e8f2b002ae1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9567d2c4ac7a1c5d0bd8ad3c3a4ce6416d895fc912201497480c1e8f2b002ae1","first_computed_at":"2026-07-05T06:58:41.759003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:58:41.759003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aJaSVItTxtlorC/nX9jzgRUz/oewiK21+vpcS3lHgU/sggG73sButr2lHPB0UnNe39OGNVhCJ2gi2YGO6VRvBA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:58:41.759522Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.04948","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1d6e254ad60e993c39fef545884ed23e0ad3f4d359e6f9ff5831988c7a011e7","sha256:4cd4d615833197e2b6331a29cdae1e11a5d617681045e7ed9b1b4b922fc29414"],"state_sha256":"051ba6d6e740d5603dc2da939f5d063997ac6bb38143e045ee34aa24c412aa73"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"H0jslBRPAOfE1KG9siTrjrq6ItxlLDoUJShc4yuhvZGWoTqxAyW0ffOU7LjMnG0twv6CruItQ0FGRCNOrVDrAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T11:19:50.536262Z","bundle_sha256":"02415d60f4dd421e62f55826b16df05e365ddf665b9148665e75e711e0b1d5ee"}}