{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PCFABEEDYEPVDKMJYPODC27RGQ","short_pith_number":"pith:PCFABEED","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"},"canonical_sha256":"788a009083c11f51a989c3dc316bf1343c1a7aa7633e50c58664b40d3674a647","source":{"kind":"arxiv","id":"2312.11011","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11011","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11011v1","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11011","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"pith_short_12","alias_value":"PCFABEEDYEPV","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"pith_short_16","alias_value":"PCFABEEDYEPVDKMJ","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"pith_short_8","alias_value":"PCFABEED","created_at":"2026-07-05T07:25:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PCFABEEDYEPVDKMJYPODC27RGQ","target":"record","payload":{"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"},"canonical_sha256":"788a009083c11f51a989c3dc316bf1343c1a7aa7633e50c58664b40d3674a647","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"},"source_kind":"arxiv","source_id":"2312.11011","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:25:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LMctQmeEQmsZzWCgEJjvmegtWyhM34bYfnOC928t/ofn2RNn5+je58KVvjowxqn+KZm7ZmeZlBjy44LCY1i6BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:55:32.218499Z"},"content_sha256":"043d7d6d82bf7f6e1ed730029e706cd1103fd7acad20a3bf0ca96b8ecbff2f46","schema_version":"1.0","event_id":"sha256:043d7d6d82bf7f6e1ed730029e706cd1103fd7acad20a3bf0ca96b8ecbff2f46"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PCFABEEDYEPVDKMJYPODC27RGQ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:25:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uhXNHOzaFNSVuag5lHV1KVy+EFliZZGFTXTvhTxl2BMEumOF/6SzLJnxPDt8dmm78SI1bDBl205ICiCkWc2tBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T18:55:32.219039Z"},"content_sha256":"abbf0d982e1c6fb4e773521b2433804cff3063bb1ef5f73d1453e36a99500396","schema_version":"1.0","event_id":"sha256:abbf0d982e1c6fb4e773521b2433804cff3063bb1ef5f73d1453e36a99500396"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ/bundle.json","state_url":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PCFABEEDYEPVDKMJYPODC27RGQ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T18:55:32Z","links":{"resolver":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ","bundle":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ/bundle.json","state":"https://pith.science/pith/PCFABEEDYEPVDKMJYPODC27RGQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PCFABEEDYEPVDKMJYPODC27RGQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PCFABEEDYEPVDKMJYPODC27RGQ","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":"ddd684e6c7bda1194023618e5ef84a5b2a4a040b84d259ef8b0b776605b2b2ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T08:27:33Z","title_canon_sha256":"80256df1a6a6a86b4339dcde20ff7558fb783b4bdfc68b97a9653437b6614bf0"},"schema_version":"1.0","source":{"id":"2312.11011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.11011","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"arxiv_version","alias_value":"2312.11011v1","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.11011","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"pith_short_12","alias_value":"PCFABEEDYEPV","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"pith_short_16","alias_value":"PCFABEEDYEPVDKMJ","created_at":"2026-07-05T07:25:15Z"},{"alias_kind":"pith_short_8","alias_value":"PCFABEED","created_at":"2026-07-05T07:25:15Z"}],"graph_snapshots":[{"event_id":"sha256:abbf0d982e1c6fb4e773521b2433804cff3063bb1ef5f73d1453e36a99500396","target":"graph","created_at":"2026-07-05T07:25:15Z","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/2312.11011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Dung Dao, Huy Pham, Quan Nguyen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T08:27:33Z","title":"VinaLLaMA: LLaMA-based Vietnamese Foundation Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.11011","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":"sha256:043d7d6d82bf7f6e1ed730029e706cd1103fd7acad20a3bf0ca96b8ecbff2f46","target":"record","created_at":"2026-07-05T07:25:15Z","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":"ddd684e6c7bda1194023618e5ef84a5b2a4a040b84d259ef8b0b776605b2b2ae","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-18T08:27:33Z","title_canon_sha256":"80256df1a6a6a86b4339dcde20ff7558fb783b4bdfc68b97a9653437b6614bf0"},"schema_version":"1.0","source":{"id":"2312.11011","kind":"arxiv","version":1}},"canonical_sha256":"788a009083c11f51a989c3dc316bf1343c1a7aa7633e50c58664b40d3674a647","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"788a009083c11f51a989c3dc316bf1343c1a7aa7633e50c58664b40d3674a647","first_computed_at":"2026-07-05T07:25:15.997237Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:25:15.997237Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"sH87/P4iLnMDuhV2Mk00owk0/aHpJWIIScjCACeueQWrQIYF7BODys0FEQZAKTGC6E1obeCZhL3y6xK03m93Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:25:15.997728Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.11011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:043d7d6d82bf7f6e1ed730029e706cd1103fd7acad20a3bf0ca96b8ecbff2f46","sha256:abbf0d982e1c6fb4e773521b2433804cff3063bb1ef5f73d1453e36a99500396"],"state_sha256":"9ae137a363a9fa91d2e1c1d701e98f4b2d9d91744d4d7a9ab068a39e35b9b9c7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"REC8ieZS3QopJYH7DtQISTBS2bIcAds+sJwraFNxCjoYfbRreefcltKU1P0yLb+zihp6O/fp8TTibtI0YZL8Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T18:55:32.225748Z","bundle_sha256":"38af16e9146bb4f321bcbae0595daab7a6933c86cba8d71cbd12032a6394775b"}}