{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OTZWYGK73Z55N7N4FNN3OQURXS","short_pith_number":"pith:OTZWYGK7","schema_version":"1.0","canonical_sha256":"74f36c195fde7bd6fdbc2b5bb74291bcb778df45dc207d4da8d75fb2f48783ce","source":{"kind":"arxiv","id":"2411.15484","version":1},"attestation_state":"computed","paper":{"title":"Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Udomcharoenchaikit, Parinthapat Pengpun, Peerat Limkonchotiwat, Weerayut Buaphet","submitted_at":"2024-11-23T07:50:59Z","abstract_excerpt":"We present a synthetic data approach for instruction-tuning large language models (LLMs) for low-resource languages in a data-efficient manner, specifically focusing on Thai. We identify three key properties that contribute to the effectiveness of instruction-tuning datasets: fluency, diversity, and cultural context. We propose a seed-data-free framework for generating synthetic instruction-tuning data that incorporates these essential properties. Our framework employs an LLM to generate diverse topics, retrieve relevant contexts from Wikipedia, and create instructions for various tasks, such "},"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":"2411.15484","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-23T07:50:59Z","cross_cats_sorted":[],"title_canon_sha256":"5fd80bb6751dd8b80f320e2b023542c2a133556814c3898de45760ac008869b3","abstract_canon_sha256":"e66bb0e6f5e1cc638d0d7d885e2fd2ed2f77c734c62019f09482357f568e7181"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:39:35.625844Z","signature_b64":"O4cwhn3LJg8vgmWpQvvQ93VOPGzXVP8fwvD3jir32BVqeWzD4EMwL1b/fTbaULm2PbQIgLAUkha32wfQA6hsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74f36c195fde7bd6fdbc2b5bb74291bcb778df45dc207d4da8d75fb2f48783ce","last_reissued_at":"2026-07-05T09:39:35.625423Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:39:35.625423Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seed-Free Synthetic Data Generation Framework for Instruction-Tuning LLMs: A Case Study in Thai","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Udomcharoenchaikit, Parinthapat Pengpun, Peerat Limkonchotiwat, Weerayut Buaphet","submitted_at":"2024-11-23T07:50:59Z","abstract_excerpt":"We present a synthetic data approach for instruction-tuning large language models (LLMs) for low-resource languages in a data-efficient manner, specifically focusing on Thai. We identify three key properties that contribute to the effectiveness of instruction-tuning datasets: fluency, diversity, and cultural context. We propose a seed-data-free framework for generating synthetic instruction-tuning data that incorporates these essential properties. Our framework employs an LLM to generate diverse topics, retrieve relevant contexts from Wikipedia, and create instructions for various tasks, such "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15484","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/2411.15484/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":"2411.15484","created_at":"2026-07-05T09:39:35.625482+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.15484v1","created_at":"2026-07-05T09:39:35.625482+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15484","created_at":"2026-07-05T09:39:35.625482+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTZWYGK73Z55","created_at":"2026-07-05T09:39:35.625482+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTZWYGK73Z55N7N4","created_at":"2026-07-05T09:39:35.625482+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTZWYGK7","created_at":"2026-07-05T09:39:35.625482+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/OTZWYGK73Z55N7N4FNN3OQURXS","json":"https://pith.science/pith/OTZWYGK73Z55N7N4FNN3OQURXS.json","graph_json":"https://pith.science/api/pith-number/OTZWYGK73Z55N7N4FNN3OQURXS/graph.json","events_json":"https://pith.science/api/pith-number/OTZWYGK73Z55N7N4FNN3OQURXS/events.json","paper":"https://pith.science/paper/OTZWYGK7"},"agent_actions":{"view_html":"https://pith.science/pith/OTZWYGK73Z55N7N4FNN3OQURXS","download_json":"https://pith.science/pith/OTZWYGK73Z55N7N4FNN3OQURXS.json","view_paper":"https://pith.science/paper/OTZWYGK7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.15484&json=true","fetch_graph":"https://pith.science/api/pith-number/OTZWYGK73Z55N7N4FNN3OQURXS/graph.json","fetch_events":"https://pith.science/api/pith-number/OTZWYGK73Z55N7N4FNN3OQURXS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTZWYGK73Z55N7N4FNN3OQURXS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTZWYGK73Z55N7N4FNN3OQURXS/action/storage_attestation","attest_author":"https://pith.science/pith/OTZWYGK73Z55N7N4FNN3OQURXS/action/author_attestation","sign_citation":"https://pith.science/pith/OTZWYGK73Z55N7N4FNN3OQURXS/action/citation_signature","submit_replication":"https://pith.science/pith/OTZWYGK73Z55N7N4FNN3OQURXS/action/replication_record"}},"created_at":"2026-07-05T09:39:35.625482+00:00","updated_at":"2026-07-05T09:39:35.625482+00:00"}