{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TL5O6UHMJANYCYVBP5KAKAUVUY","short_pith_number":"pith:TL5O6UHM","schema_version":"1.0","canonical_sha256":"9afaef50ec481b8162a17f54050295a60b85e4f11f882e7a45c4b4903542d1d1","source":{"kind":"arxiv","id":"2506.21595","version":1},"attestation_state":"computed","paper":{"title":"Thunder-LLM: Efficiently Adapting LLMs to Korean with Minimal Resources","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chanwoo Park, Gyeongje Cho, Jaejin Lee, Jinpyo Kim, Jongmin Kim, Jongwon Park, Yeonkyoun So","submitted_at":"2025-06-18T17:33:51Z","abstract_excerpt":"Since state-of-the-art LLMs often underperform in languages other than English or Chinese, improving the capability of LLMs in new languages has become an essential task. Moreover, LLMs' entire end-to-end training process remains largely unknown to the public due to proprietary reasons, technical complexity, inconsistent documentation, and ethical considerations. The complete picture remains a closely guarded secret within the industry. This paper presents methods to adapt an existing English-based LLM to Korean in a low-budget scenario. We describe the entire end-to-end process: collecting Ko"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.21595","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-18T17:33:51Z","cross_cats_sorted":[],"title_canon_sha256":"6a8ac5e9fdb92677dbcacaada4ab51a35f1e185af36d6725295d28b7062af2fe","abstract_canon_sha256":"e3a0b15dadcad885fbd62b6ae446c6a674ecd2fd74fcb4d3c87ec68287a2521e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:56.964360Z","signature_b64":"XTEvzn+ttfI80C5GFX0/yZtPaiTpMJM02enpdJVlMcctR7g7imPUqBd322U6StjhGSdS4U7kV2tT1KdO6qzxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9afaef50ec481b8162a17f54050295a60b85e4f11f882e7a45c4b4903542d1d1","last_reissued_at":"2026-07-05T11:27:56.963870Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:56.963870Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thunder-LLM: Efficiently Adapting LLMs to Korean with Minimal Resources","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chanwoo Park, Gyeongje Cho, Jaejin Lee, Jinpyo Kim, Jongmin Kim, Jongwon Park, Yeonkyoun So","submitted_at":"2025-06-18T17:33:51Z","abstract_excerpt":"Since state-of-the-art LLMs often underperform in languages other than English or Chinese, improving the capability of LLMs in new languages has become an essential task. Moreover, LLMs' entire end-to-end training process remains largely unknown to the public due to proprietary reasons, technical complexity, inconsistent documentation, and ethical considerations. The complete picture remains a closely guarded secret within the industry. This paper presents methods to adapt an existing English-based LLM to Korean in a low-budget scenario. We describe the entire end-to-end process: collecting Ko"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21595","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/2506.21595/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.21595","created_at":"2026-07-05T11:27:56.963928+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21595v1","created_at":"2026-07-05T11:27:56.963928+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21595","created_at":"2026-07-05T11:27:56.963928+00:00"},{"alias_kind":"pith_short_12","alias_value":"TL5O6UHMJANY","created_at":"2026-07-05T11:27:56.963928+00:00"},{"alias_kind":"pith_short_16","alias_value":"TL5O6UHMJANYCYVB","created_at":"2026-07-05T11:27:56.963928+00:00"},{"alias_kind":"pith_short_8","alias_value":"TL5O6UHM","created_at":"2026-07-05T11:27:56.963928+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.16235","citing_title":"Optimizing Korean-Centric LLMs via Token Pruning","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TL5O6UHMJANYCYVBP5KAKAUVUY","json":"https://pith.science/pith/TL5O6UHMJANYCYVBP5KAKAUVUY.json","graph_json":"https://pith.science/api/pith-number/TL5O6UHMJANYCYVBP5KAKAUVUY/graph.json","events_json":"https://pith.science/api/pith-number/TL5O6UHMJANYCYVBP5KAKAUVUY/events.json","paper":"https://pith.science/paper/TL5O6UHM"},"agent_actions":{"view_html":"https://pith.science/pith/TL5O6UHMJANYCYVBP5KAKAUVUY","download_json":"https://pith.science/pith/TL5O6UHMJANYCYVBP5KAKAUVUY.json","view_paper":"https://pith.science/paper/TL5O6UHM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21595&json=true","fetch_graph":"https://pith.science/api/pith-number/TL5O6UHMJANYCYVBP5KAKAUVUY/graph.json","fetch_events":"https://pith.science/api/pith-number/TL5O6UHMJANYCYVBP5KAKAUVUY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TL5O6UHMJANYCYVBP5KAKAUVUY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TL5O6UHMJANYCYVBP5KAKAUVUY/action/storage_attestation","attest_author":"https://pith.science/pith/TL5O6UHMJANYCYVBP5KAKAUVUY/action/author_attestation","sign_citation":"https://pith.science/pith/TL5O6UHMJANYCYVBP5KAKAUVUY/action/citation_signature","submit_replication":"https://pith.science/pith/TL5O6UHMJANYCYVBP5KAKAUVUY/action/replication_record"}},"created_at":"2026-07-05T11:27:56.963928+00:00","updated_at":"2026-07-05T11:27:56.963928+00:00"}