{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IU2UFX4WK5F4RHYYNO3OIDAOP2","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":"edaa1805af3ce15a2ab473249ad01bba4a31e24bd28d1a9596048f5883777e64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-21T15:38:41Z","title_canon_sha256":"037a6868e9929f6fa622a076baf986acac05ad49cf6c3fceb2a7dbcabf0b9569"},"schema_version":"1.0","source":{"id":"2312.13951","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.13951","created_at":"2026-07-05T07:26:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.13951v1","created_at":"2026-07-05T07:26:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13951","created_at":"2026-07-05T07:26:58Z"},{"alias_kind":"pith_short_12","alias_value":"IU2UFX4WK5F4","created_at":"2026-07-05T07:26:58Z"},{"alias_kind":"pith_short_16","alias_value":"IU2UFX4WK5F4RHYY","created_at":"2026-07-05T07:26:58Z"},{"alias_kind":"pith_short_8","alias_value":"IU2UFX4W","created_at":"2026-07-05T07:26:58Z"}],"graph_snapshots":[{"event_id":"sha256:36afae247fa80a71cacf27bb3104722dbd28e9f1a93ac2d62449dd7050111a5f","target":"graph","created_at":"2026-07-05T07:26:58Z","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/2312.13951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Typhoon is a series of Thai large language models (LLMs) developed specifically for the Thai language. This technical report presents challenges and insights in developing Thai LLMs, including data preparation, pretraining, instruction-tuning, and evaluation. As one of the challenges of low-resource languages is the amount of pretraining data, we apply continual training to transfer existing world knowledge from a strong LLM. To evaluate the Thai knowledge encapsulated in each model from the pretraining stage, we develop ThaiExam, a benchmark based on examinations for high-school students and ","authors_text":"Kasima Tharnpipitchai, Kunat Pipatanakul, Pathomporn Chokchainant, Phatrasek Jirabovonvisut, Potsawee Manakul, Ruangsak Patomwong, Sittipong Sripaisarnmongkol","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-21T15:38:41Z","title":"Typhoon: Thai Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.13951","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:c69df3b06373260ee27abcb9aea3e526be46938e72e24b70ff97a95affc6ceb3","target":"record","created_at":"2026-07-05T07:26:58Z","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":"edaa1805af3ce15a2ab473249ad01bba4a31e24bd28d1a9596048f5883777e64","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-21T15:38:41Z","title_canon_sha256":"037a6868e9929f6fa622a076baf986acac05ad49cf6c3fceb2a7dbcabf0b9569"},"schema_version":"1.0","source":{"id":"2312.13951","kind":"arxiv","version":1}},"canonical_sha256":"453542df96574bc89f186bb6e40c0e7ea18b2532d0dd79a46014d14e74cd0fb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"453542df96574bc89f186bb6e40c0e7ea18b2532d0dd79a46014d14e74cd0fb9","first_computed_at":"2026-07-05T07:26:58.566088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:26:58.566088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"79bhdDXXehE7OuivzTzURAJek3Nx5GowIPb4bMCmnHQrVOnOagMsSqDfgpF9xLiNtNQxoak089fqC6piswfMBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:26:58.566604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.13951","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c69df3b06373260ee27abcb9aea3e526be46938e72e24b70ff97a95affc6ceb3","sha256:36afae247fa80a71cacf27bb3104722dbd28e9f1a93ac2d62449dd7050111a5f"],"state_sha256":"33153016284d771bc1b43a39197e89435df04a23e1880a4a11717a2a711174a6"}