{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:K44MCLWEZS754NDO46MNROQ55V","short_pith_number":"pith:K44MCLWE","canonical_record":{"source":{"id":"2401.01055","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-02T06:29:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af06cc5072127fa375936e94a5443b31f22398f139f7faf439bed0c32cf7bb32","abstract_canon_sha256":"eca0fd054943ef4b3c41bff63d8b9a890e317a3d3620bbdad1996db530847b83"},"schema_version":"1.0"},"canonical_sha256":"5738c12ec4ccbfde346ee798d8ba1ded4bba5171806420a7a17b6d51afcbe7a8","source":{"kind":"arxiv","id":"2401.01055","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01055","created_at":"2026-07-05T07:32:45Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01055v2","created_at":"2026-07-05T07:32:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01055","created_at":"2026-07-05T07:32:45Z"},{"alias_kind":"pith_short_12","alias_value":"K44MCLWEZS75","created_at":"2026-07-05T07:32:45Z"},{"alias_kind":"pith_short_16","alias_value":"K44MCLWEZS754NDO","created_at":"2026-07-05T07:32:45Z"},{"alias_kind":"pith_short_8","alias_value":"K44MCLWE","created_at":"2026-07-05T07:32:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:K44MCLWEZS754NDO46MNROQ55V","target":"record","payload":{"canonical_record":{"source":{"id":"2401.01055","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-02T06:29:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"af06cc5072127fa375936e94a5443b31f22398f139f7faf439bed0c32cf7bb32","abstract_canon_sha256":"eca0fd054943ef4b3c41bff63d8b9a890e317a3d3620bbdad1996db530847b83"},"schema_version":"1.0"},"canonical_sha256":"5738c12ec4ccbfde346ee798d8ba1ded4bba5171806420a7a17b6d51afcbe7a8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:32:45.436470Z","signature_b64":"/c+/mFThj1cEu0cScu7dR5BKvUH0AFZS8Zo/7Na/omqqGNeoxjZnnDYeIVk9hc7B0rCiDHX2O8oUWboEOzoTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5738c12ec4ccbfde346ee798d8ba1ded4bba5171806420a7a17b6d51afcbe7a8","last_reissued_at":"2026-07-05T07:32:45.435977Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:32:45.435977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.01055","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":"2026-07-05T07:32:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vuslXC/VwpiWuYiSRNJLPVJBIllXjZMZiHUPMAxO1KQc1Y5NO2Km6/OT25XEVBJ0UrwYkGi7CXQLw+Qav0RBBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:26:38.840008Z"},"content_sha256":"a5718200b0e1c6c7626a0787f85b07edb178088292faddb12d0e5951003c7486","schema_version":"1.0","event_id":"sha256:a5718200b0e1c6c7626a0787f85b07edb178088292faddb12d0e5951003c7486"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:K44MCLWEZS754NDO46MNROQ55V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LLaMA Beyond English: An Empirical Study on Language Capability Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jun Zhao, Luhui Gao, Qi Zhang, Tao Gui, Xuanjing Huang, Zhihao Zhang","submitted_at":"2024-01-02T06:29:02Z","abstract_excerpt":"In recent times, substantial advancements have been witnessed in large language models (LLMs), exemplified by ChatGPT, showcasing remarkable proficiency across a range of complex tasks. However, many mainstream LLMs (e.g. LLaMA) are pretrained on English-dominant corpus, which limits their performance in other non-English languages. In this paper, we focus on how to effectively transfer the capabilities of language generation and following instructions to a non-English language. To answer this question, we conduct an extensive empirical investigation based on LLaMA, accumulating over 1440 GPU "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01055","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/2401.01055/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":"2026-07-05T07:32:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"shJe7Qz1TGsHvQqXwtuAEkGVf4rZAihAF2cdQuRoAIv4a1JEP8VyaFu2AyvTfrXAFdeiiqu7xSVjJ6v7oqqiBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:26:38.840521Z"},"content_sha256":"2388326ab17da53fdaf0c18cc529eaeb0866d516cc314b76a5a9d3b72dade67c","schema_version":"1.0","event_id":"sha256:2388326ab17da53fdaf0c18cc529eaeb0866d516cc314b76a5a9d3b72dade67c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/K44MCLWEZS754NDO46MNROQ55V/bundle.json","state_url":"https://pith.science/pith/K44MCLWEZS754NDO46MNROQ55V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/K44MCLWEZS754NDO46MNROQ55V/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":"2026-08-07T21:26:38Z","links":{"resolver":"https://pith.science/pith/K44MCLWEZS754NDO46MNROQ55V","bundle":"https://pith.science/pith/K44MCLWEZS754NDO46MNROQ55V/bundle.json","state":"https://pith.science/pith/K44MCLWEZS754NDO46MNROQ55V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/K44MCLWEZS754NDO46MNROQ55V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:K44MCLWEZS754NDO46MNROQ55V","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":"eca0fd054943ef4b3c41bff63d8b9a890e317a3d3620bbdad1996db530847b83","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-02T06:29:02Z","title_canon_sha256":"af06cc5072127fa375936e94a5443b31f22398f139f7faf439bed0c32cf7bb32"},"schema_version":"1.0","source":{"id":"2401.01055","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.01055","created_at":"2026-07-05T07:32:45Z"},{"alias_kind":"arxiv_version","alias_value":"2401.01055v2","created_at":"2026-07-05T07:32:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.01055","created_at":"2026-07-05T07:32:45Z"},{"alias_kind":"pith_short_12","alias_value":"K44MCLWEZS75","created_at":"2026-07-05T07:32:45Z"},{"alias_kind":"pith_short_16","alias_value":"K44MCLWEZS754NDO","created_at":"2026-07-05T07:32:45Z"},{"alias_kind":"pith_short_8","alias_value":"K44MCLWE","created_at":"2026-07-05T07:32:45Z"}],"graph_snapshots":[{"event_id":"sha256:2388326ab17da53fdaf0c18cc529eaeb0866d516cc314b76a5a9d3b72dade67c","target":"graph","created_at":"2026-07-05T07:32:45Z","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/2401.01055/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent times, substantial advancements have been witnessed in large language models (LLMs), exemplified by ChatGPT, showcasing remarkable proficiency across a range of complex tasks. However, many mainstream LLMs (e.g. LLaMA) are pretrained on English-dominant corpus, which limits their performance in other non-English languages. In this paper, we focus on how to effectively transfer the capabilities of language generation and following instructions to a non-English language. To answer this question, we conduct an extensive empirical investigation based on LLaMA, accumulating over 1440 GPU ","authors_text":"Jun Zhao, Luhui Gao, Qi Zhang, Tao Gui, Xuanjing Huang, Zhihao Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-02T06:29:02Z","title":"LLaMA Beyond English: An Empirical Study on Language Capability Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.01055","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:a5718200b0e1c6c7626a0787f85b07edb178088292faddb12d0e5951003c7486","target":"record","created_at":"2026-07-05T07:32:45Z","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":"eca0fd054943ef4b3c41bff63d8b9a890e317a3d3620bbdad1996db530847b83","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-02T06:29:02Z","title_canon_sha256":"af06cc5072127fa375936e94a5443b31f22398f139f7faf439bed0c32cf7bb32"},"schema_version":"1.0","source":{"id":"2401.01055","kind":"arxiv","version":2}},"canonical_sha256":"5738c12ec4ccbfde346ee798d8ba1ded4bba5171806420a7a17b6d51afcbe7a8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5738c12ec4ccbfde346ee798d8ba1ded4bba5171806420a7a17b6d51afcbe7a8","first_computed_at":"2026-07-05T07:32:45.435977Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:32:45.435977Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/c+/mFThj1cEu0cScu7dR5BKvUH0AFZS8Zo/7Na/omqqGNeoxjZnnDYeIVk9hc7B0rCiDHX2O8oUWboEOzoTAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:32:45.436470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.01055","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5718200b0e1c6c7626a0787f85b07edb178088292faddb12d0e5951003c7486","sha256:2388326ab17da53fdaf0c18cc529eaeb0866d516cc314b76a5a9d3b72dade67c"],"state_sha256":"0c3a1aa7d2e660c7efac062e17b47e8891c63580b4f4f78f508ae717dfc8e487"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JWc0KyTTDUODSCQdatDTvU3QFqTGhKG2XmoqF7rx4iUsVtEmkVWJezHJnqKiA2XJHZneOG59afsu3Rz589yJAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:26:38.845559Z","bundle_sha256":"48411c60eb369eb15c43c9147a6ceb1e2bf67e41ddb16564074cb52a9153cac3"}}