{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:VN7O55ANOFMC76HMB7ABKBOYHY","short_pith_number":"pith:VN7O55AN","canonical_record":{"source":{"id":"2404.04042","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T11:52:02Z","cross_cats_sorted":[],"title_canon_sha256":"4f8b6b22a881e7461dec3f10abd3811415a6ef796e7f233ded8a85fad1cb6c42","abstract_canon_sha256":"6e4a0e3707915eea4c7a685f72adb35c76deca62190374fa4de812741e221ec4"},"schema_version":"1.0"},"canonical_sha256":"ab7eeef40d71582ff8ec0fc01505d83e3263ac15e76a0e09f762efef4c835b18","source":{"kind":"arxiv","id":"2404.04042","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04042","created_at":"2026-07-05T08:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04042v1","created_at":"2026-07-05T08:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04042","created_at":"2026-07-05T08:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"VN7O55ANOFMC","created_at":"2026-07-05T08:38:58Z"},{"alias_kind":"pith_short_16","alias_value":"VN7O55ANOFMC76HM","created_at":"2026-07-05T08:38:58Z"},{"alias_kind":"pith_short_8","alias_value":"VN7O55AN","created_at":"2026-07-05T08:38:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:VN7O55ANOFMC76HMB7ABKBOYHY","target":"record","payload":{"canonical_record":{"source":{"id":"2404.04042","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T11:52:02Z","cross_cats_sorted":[],"title_canon_sha256":"4f8b6b22a881e7461dec3f10abd3811415a6ef796e7f233ded8a85fad1cb6c42","abstract_canon_sha256":"6e4a0e3707915eea4c7a685f72adb35c76deca62190374fa4de812741e221ec4"},"schema_version":"1.0"},"canonical_sha256":"ab7eeef40d71582ff8ec0fc01505d83e3263ac15e76a0e09f762efef4c835b18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:58.927158Z","signature_b64":"pc3LR0FjBx1lV7Mk6hym6cHMnieRFNZNBTaivGAjpKTm4owQvf+lb7eLfkBrIa9nYs69iNxDZXeGxNU2w6xWBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab7eeef40d71582ff8ec0fc01505d83e3263ac15e76a0e09f762efef4c835b18","last_reissued_at":"2026-07-05T08:38:58.926670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:58.926670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.04042","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u6cp0vo6yk0OTigL77JBXeVvq+pQ4+8bxoDicK0l23XfkWntmWK0SJ2t6fe7W7GsJ0iMX5jlMkkvjDVoSNDpAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:07:45.319885Z"},"content_sha256":"05149dd4e9a490af20e93110f782336492a0925146caf6add76df891ddc2a117","schema_version":"1.0","event_id":"sha256:05149dd4e9a490af20e93110f782336492a0925146caf6add76df891ddc2a117"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:VN7O55ANOFMC76HMB7ABKBOYHY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Agnes Luhtaru, Hele-Andra Kuulmets, Mark Fishel, Taido Purason","submitted_at":"2024-04-05T11:52:02Z","abstract_excerpt":"This paper explores cost-efficient methods to adapt pretrained Large Language Models (LLMs) to new lower-resource languages, with a specific focus on Estonian. Leveraging the Llama 2 model, we investigate the impact of combining cross-lingual instruction-tuning with additional monolingual pretraining. Our results demonstrate that even a relatively small amount of additional monolingual pretraining followed by cross-lingual instruction-tuning significantly enhances results on Estonian. Furthermore, we showcase cross-lingual knowledge transfer from high-quality English instructions to Estonian, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04042","kind":"arxiv","version":1},"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/2404.04042/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":"2026-07-05T08:38:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ol14Yp6GHpMmbgUwA4Mhs4jHlvVSLdLxCPb8RZNeyXQGUW0TvTL1PYE1fIHmwtEu/G4r0exrvH6urdjPFQkWCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:07:45.320417Z"},"content_sha256":"887654c55c9cc41520f31665d9a5469ba530dfa51d56bb2d5f3444b624091efa","schema_version":"1.0","event_id":"sha256:887654c55c9cc41520f31665d9a5469ba530dfa51d56bb2d5f3444b624091efa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VN7O55ANOFMC76HMB7ABKBOYHY/bundle.json","state_url":"https://pith.science/pith/VN7O55ANOFMC76HMB7ABKBOYHY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VN7O55ANOFMC76HMB7ABKBOYHY/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":"2026-08-07T18:07:45Z","links":{"resolver":"https://pith.science/pith/VN7O55ANOFMC76HMB7ABKBOYHY","bundle":"https://pith.science/pith/VN7O55ANOFMC76HMB7ABKBOYHY/bundle.json","state":"https://pith.science/pith/VN7O55ANOFMC76HMB7ABKBOYHY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VN7O55ANOFMC76HMB7ABKBOYHY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VN7O55ANOFMC76HMB7ABKBOYHY","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":"6e4a0e3707915eea4c7a685f72adb35c76deca62190374fa4de812741e221ec4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T11:52:02Z","title_canon_sha256":"4f8b6b22a881e7461dec3f10abd3811415a6ef796e7f233ded8a85fad1cb6c42"},"schema_version":"1.0","source":{"id":"2404.04042","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04042","created_at":"2026-07-05T08:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04042v1","created_at":"2026-07-05T08:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04042","created_at":"2026-07-05T08:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"VN7O55ANOFMC","created_at":"2026-07-05T08:38:58Z"},{"alias_kind":"pith_short_16","alias_value":"VN7O55ANOFMC76HM","created_at":"2026-07-05T08:38:58Z"},{"alias_kind":"pith_short_8","alias_value":"VN7O55AN","created_at":"2026-07-05T08:38:58Z"}],"graph_snapshots":[{"event_id":"sha256:887654c55c9cc41520f31665d9a5469ba530dfa51d56bb2d5f3444b624091efa","target":"graph","created_at":"2026-07-05T08:38:58Z","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/2404.04042/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper explores cost-efficient methods to adapt pretrained Large Language Models (LLMs) to new lower-resource languages, with a specific focus on Estonian. Leveraging the Llama 2 model, we investigate the impact of combining cross-lingual instruction-tuning with additional monolingual pretraining. Our results demonstrate that even a relatively small amount of additional monolingual pretraining followed by cross-lingual instruction-tuning significantly enhances results on Estonian. Furthermore, we showcase cross-lingual knowledge transfer from high-quality English instructions to Estonian, ","authors_text":"Agnes Luhtaru, Hele-Andra Kuulmets, Mark Fishel, Taido Purason","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T11:52:02Z","title":"Teaching Llama a New Language Through Cross-Lingual Knowledge Transfer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04042","kind":"arxiv","version":1},"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":"sha256:05149dd4e9a490af20e93110f782336492a0925146caf6add76df891ddc2a117","target":"record","created_at":"2026-07-05T08:38:58Z","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":"6e4a0e3707915eea4c7a685f72adb35c76deca62190374fa4de812741e221ec4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-05T11:52:02Z","title_canon_sha256":"4f8b6b22a881e7461dec3f10abd3811415a6ef796e7f233ded8a85fad1cb6c42"},"schema_version":"1.0","source":{"id":"2404.04042","kind":"arxiv","version":1}},"canonical_sha256":"ab7eeef40d71582ff8ec0fc01505d83e3263ac15e76a0e09f762efef4c835b18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab7eeef40d71582ff8ec0fc01505d83e3263ac15e76a0e09f762efef4c835b18","first_computed_at":"2026-07-05T08:38:58.926670Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:58.926670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pc3LR0FjBx1lV7Mk6hym6cHMnieRFNZNBTaivGAjpKTm4owQvf+lb7eLfkBrIa9nYs69iNxDZXeGxNU2w6xWBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:58.927158Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.04042","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05149dd4e9a490af20e93110f782336492a0925146caf6add76df891ddc2a117","sha256:887654c55c9cc41520f31665d9a5469ba530dfa51d56bb2d5f3444b624091efa"],"state_sha256":"a5588e5070dc96ca9d009ea7b081af2493031aba9214ced9e3f27442b63736d1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WkeP9qr2Eo6tRhMtDNdYjspvw/ohZ9FutRfeIOi5gpiKWDY8MFBT8tcuSa4kkccnzLqh9icCY3buReNvE6cJDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:07:45.326737Z","bundle_sha256":"66ccabdf14ab5c566e6b7f97ff031e5789cac840dd9cb795b102b92be2096a92"}}