{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PCFABEEDYEPVDKMJYPODC27RGQ","short_pith_number":"pith:PCFABEED","schema_version":"1.0","canonical_sha256":"788a009083c11f51a989c3dc316bf1343c1a7aa7633e50c58664b40d3674a647","source":{"kind":"arxiv","id":"2312.11011","version":1},"attestation_state":"computed","paper":{"title":"VinaLLaMA: LLaMA-based Vietnamese Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dung Dao, Huy Pham, Quan Nguyen","submitted_at":"2023-12-18T08:27:33Z","abstract_excerpt":"In this technical report, we present VinaLLaMA, an open-weight, state-of-the-art (SOTA) Large Language Model for the Vietnamese language, built upon LLaMA-2 with an additional 800 billion trained tokens. VinaLLaMA not only demonstrates fluency in Vietnamese but also exhibits a profound understanding of Vietnamese culture, making it a truly indigenous model. VinaLLaMA-7B-chat, trained on 1 million high-quality synthetic samples, achieves SOTA results on key benchmarks, including VLSP, VMLU, and Vicuna Benchmark Vietnamese, marking a significant advancement in the Vietnamese AI landscape and off"},"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":"2312.11011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T08:27:33Z","cross_cats_sorted":[],"title_canon_sha256":"80256df1a6a6a86b4339dcde20ff7558fb783b4bdfc68b97a9653437b6614bf0","abstract_canon_sha256":"ddd684e6c7bda1194023618e5ef84a5b2a4a040b84d259ef8b0b776605b2b2ae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:25:15.997728Z","signature_b64":"sH87/P4iLnMDuhV2Mk00owk0/aHpJWIIScjCACeueQWrQIYF7BODys0FEQZAKTGC6E1obeCZhL3y6xK03m93Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"788a009083c11f51a989c3dc316bf1343c1a7aa7633e50c58664b40d3674a647","last_reissued_at":"2026-07-05T07:25:15.997237Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:25:15.997237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VinaLLaMA: LLaMA-based Vietnamese Foundation Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dung Dao, Huy Pham, Quan Nguyen","submitted_at":"2023-12-18T08:27:33Z","abstract_excerpt":"In this technical report, we present VinaLLaMA, an open-weight, state-of-the-art (SOTA) Large Language Model for the Vietnamese language, built upon LLaMA-2 with an additional 800 billion trained tokens. VinaLLaMA not only demonstrates fluency in Vietnamese but also exhibits a profound understanding of Vietnamese culture, making it a truly indigenous model. VinaLLaMA-7B-chat, trained on 1 million high-quality synthetic samples, achieves SOTA results on key benchmarks, including VLSP, VMLU, and Vicuna Benchmark Vietnamese, marking a significant advancement in the Vietnamese AI landscape and off"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11011","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/2312.11011/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":"2312.11011","created_at":"2026-07-05T07:25:15.997295+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.11011v1","created_at":"2026-07-05T07:25:15.997295+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11011","created_at":"2026-07-05T07:25:15.997295+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCFABEEDYEPV","created_at":"2026-07-05T07:25:15.997295+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCFABEEDYEPVDKMJ","created_at":"2026-07-05T07:25:15.997295+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCFABEED","created_at":"2026-07-05T07:25:15.997295+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.27379","citing_title":"Soro: A Lightweight Foundation Model and Chatbot for Tajik","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ","json":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ.json","graph_json":"https://pith.science/api/pith-number/PCFABEEDYEPVDKMJYPODC27RGQ/graph.json","events_json":"https://pith.science/api/pith-number/PCFABEEDYEPVDKMJYPODC27RGQ/events.json","paper":"https://pith.science/paper/PCFABEED"},"agent_actions":{"view_html":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ","download_json":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ.json","view_paper":"https://pith.science/paper/PCFABEED","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.11011&json=true","fetch_graph":"https://pith.science/api/pith-number/PCFABEEDYEPVDKMJYPODC27RGQ/graph.json","fetch_events":"https://pith.science/api/pith-number/PCFABEEDYEPVDKMJYPODC27RGQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ/action/storage_attestation","attest_author":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ/action/author_attestation","sign_citation":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ/action/citation_signature","submit_replication":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ/action/replication_record"}},"created_at":"2026-07-05T07:25:15.997295+00:00","updated_at":"2026-07-05T07:25:15.997295+00:00"}