{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DAT2LIWCJ2KZ62IBG7LEUH5CMM","short_pith_number":"pith:DAT2LIWC","schema_version":"1.0","canonical_sha256":"1827a5a2c24e959f690137d64a1fa2632c5495ee9b2ed0384e39adb0ac7cc3ad","source":{"kind":"arxiv","id":"2510.07074","version":2},"attestation_state":"computed","paper":{"title":"LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fred Philippy, Jacques Klein, Laura Bernardy, Siwen Guo, Tegawend\\'e F. Bissyand\\'e","submitted_at":"2025-10-08T14:35:59Z","abstract_excerpt":"Instruction tuning has become a key technique for enhancing the performance of large language models, enabling them to better follow human prompts. However, low-resource languages such as Luxembourgish face severe limitations due to the lack of high-quality instruction datasets. Traditional reliance on machine translation often introduces semantic misalignment and cultural inaccuracies. In this work, we address these challenges by creating a cross-lingual instruction tuning dataset for Luxembourgish, without resorting to machine-generated translations into it. Instead, by leveraging aligned da"},"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":"2510.07074","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-08T14:35:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"111da065b28efb206122fe0f96171e6155278b4a01f93d42a1d11cc1d5adb591","abstract_canon_sha256":"902205a2fa8d2a5bb6888d91a3d9a9ab37efe198230d1c6044d5ba10cb17ba01"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:23.416225Z","signature_b64":"qXxZOL6n1Qrnz1qDHazbYeHxZWhCrI6n15tcvFAwj2O6xqor9Ea8hxlGjpnQeMXnEBQHrcVNmYcJGdrUTvWQDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1827a5a2c24e959f690137d64a1fa2632c5495ee9b2ed0384e39adb0ac7cc3ad","last_reissued_at":"2026-07-28T01:22:23.415156Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:23.415156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LuxInstruct: A Cross-Lingual Instruction Tuning Dataset For Luxembourgish","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Fred Philippy, Jacques Klein, Laura Bernardy, Siwen Guo, Tegawend\\'e F. Bissyand\\'e","submitted_at":"2025-10-08T14:35:59Z","abstract_excerpt":"Instruction tuning has become a key technique for enhancing the performance of large language models, enabling them to better follow human prompts. However, low-resource languages such as Luxembourgish face severe limitations due to the lack of high-quality instruction datasets. Traditional reliance on machine translation often introduces semantic misalignment and cultural inaccuracies. In this work, we address these challenges by creating a cross-lingual instruction tuning dataset for Luxembourgish, without resorting to machine-generated translations into it. Instead, by leveraging aligned da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.07074","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/2510.07074/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":"2510.07074","created_at":"2026-07-28T01:22:23.415700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.07074v2","created_at":"2026-07-28T01:22:23.415700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.07074","created_at":"2026-07-28T01:22:23.415700+00:00"},{"alias_kind":"pith_short_12","alias_value":"DAT2LIWCJ2KZ","created_at":"2026-07-28T01:22:23.415700+00:00"},{"alias_kind":"pith_short_16","alias_value":"DAT2LIWCJ2KZ62IB","created_at":"2026-07-28T01:22:23.415700+00:00"},{"alias_kind":"pith_short_8","alias_value":"DAT2LIWC","created_at":"2026-07-28T01:22:23.415700+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DAT2LIWCJ2KZ62IBG7LEUH5CMM","json":"https://pith.science/pith/DAT2LIWCJ2KZ62IBG7LEUH5CMM.json","graph_json":"https://pith.science/api/pith-number/DAT2LIWCJ2KZ62IBG7LEUH5CMM/graph.json","events_json":"https://pith.science/api/pith-number/DAT2LIWCJ2KZ62IBG7LEUH5CMM/events.json","paper":"https://pith.science/paper/DAT2LIWC"},"agent_actions":{"view_html":"https://pith.science/pith/DAT2LIWCJ2KZ62IBG7LEUH5CMM","download_json":"https://pith.science/pith/DAT2LIWCJ2KZ62IBG7LEUH5CMM.json","view_paper":"https://pith.science/paper/DAT2LIWC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.07074&json=true","fetch_graph":"https://pith.science/api/pith-number/DAT2LIWCJ2KZ62IBG7LEUH5CMM/graph.json","fetch_events":"https://pith.science/api/pith-number/DAT2LIWCJ2KZ62IBG7LEUH5CMM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DAT2LIWCJ2KZ62IBG7LEUH5CMM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DAT2LIWCJ2KZ62IBG7LEUH5CMM/action/storage_attestation","attest_author":"https://pith.science/pith/DAT2LIWCJ2KZ62IBG7LEUH5CMM/action/author_attestation","sign_citation":"https://pith.science/pith/DAT2LIWCJ2KZ62IBG7LEUH5CMM/action/citation_signature","submit_replication":"https://pith.science/pith/DAT2LIWCJ2KZ62IBG7LEUH5CMM/action/replication_record"}},"created_at":"2026-07-28T01:22:23.415700+00:00","updated_at":"2026-07-28T01:22:23.415700+00:00"}