{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TMS64CPHPXHDVGTSAV5HTA5I4I","short_pith_number":"pith:TMS64CPH","schema_version":"1.0","canonical_sha256":"9b25ee09e77dce3a9a72057a7983a8e22b0da847fc1e736c6c78fcf14e71dfe9","source":{"kind":"arxiv","id":"2408.12480","version":2},"attestation_state":"computed","paper":{"title":"Vintern-1B: An Efficient Multimodal Large Language Model for Vietnamese","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bang Q. Vo, Bao G. Huynh, Dung T. Hoang, Khang T. Doan, Nhat H. Pham, Quan T.M. Nguyen, Suong N. Hoang, Thuc D. Pham","submitted_at":"2024-08-22T15:15:51Z","abstract_excerpt":"In this report, we introduce Vintern-1B, a reliable 1-billion-parameters multimodal large language model (MLLM) for Vietnamese language tasks. By integrating the Qwen2-0.5B-Instruct language model with the InternViT-300M-448px visual model, Vintern-1B is optimized for a range of applications, including optical character recognition (OCR), document extraction, and general question-answering in Vietnamese context. The model is fine-tuned on an extensive dataset of over 3 million image-question-answer pairs, achieving robust performance and reliable results across multiple Vietnamese language ben"},"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":"2408.12480","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-22T15:15:51Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b976b87501ba58b63fd9b848b862a49213bbbfe39d30baed6262b32df7c7547d","abstract_canon_sha256":"41d481544454487b498f3ff1f4148d335e5e9de208d2a94d2af05f6ad792ca30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:26.949339Z","signature_b64":"uqB93MUfkSfiioONkQ/sbqiwNz8GAnqdhIZENImwYhE4d7CiTmKPzpH43IGaaV4U+WnmE8uCLw9Vi10UpJ5ZBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b25ee09e77dce3a9a72057a7983a8e22b0da847fc1e736c6c78fcf14e71dfe9","last_reissued_at":"2026-07-05T08:58:26.948851Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:26.948851Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vintern-1B: An Efficient Multimodal Large Language Model for Vietnamese","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Bang Q. Vo, Bao G. Huynh, Dung T. Hoang, Khang T. Doan, Nhat H. Pham, Quan T.M. Nguyen, Suong N. Hoang, Thuc D. Pham","submitted_at":"2024-08-22T15:15:51Z","abstract_excerpt":"In this report, we introduce Vintern-1B, a reliable 1-billion-parameters multimodal large language model (MLLM) for Vietnamese language tasks. By integrating the Qwen2-0.5B-Instruct language model with the InternViT-300M-448px visual model, Vintern-1B is optimized for a range of applications, including optical character recognition (OCR), document extraction, and general question-answering in Vietnamese context. The model is fine-tuned on an extensive dataset of over 3 million image-question-answer pairs, achieving robust performance and reliable results across multiple Vietnamese language ben"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.12480","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/2408.12480/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":"2408.12480","created_at":"2026-07-05T08:58:26.948907+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.12480v2","created_at":"2026-07-05T08:58:26.948907+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.12480","created_at":"2026-07-05T08:58:26.948907+00:00"},{"alias_kind":"pith_short_12","alias_value":"TMS64CPHPXHD","created_at":"2026-07-05T08:58:26.948907+00:00"},{"alias_kind":"pith_short_16","alias_value":"TMS64CPHPXHDVGTS","created_at":"2026-07-05T08:58:26.948907+00:00"},{"alias_kind":"pith_short_8","alias_value":"TMS64CPH","created_at":"2026-07-05T08:58:26.948907+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23274","citing_title":"U-CESE: Unified Clip-based Event Search Engine for AI Challenge HCMC 2025","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2412.07584","citing_title":"Multimodal Contextualized Support for Enhancing Video Retrieval System","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TMS64CPHPXHDVGTSAV5HTA5I4I","json":"https://pith.science/pith/TMS64CPHPXHDVGTSAV5HTA5I4I.json","graph_json":"https://pith.science/api/pith-number/TMS64CPHPXHDVGTSAV5HTA5I4I/graph.json","events_json":"https://pith.science/api/pith-number/TMS64CPHPXHDVGTSAV5HTA5I4I/events.json","paper":"https://pith.science/paper/TMS64CPH"},"agent_actions":{"view_html":"https://pith.science/pith/TMS64CPHPXHDVGTSAV5HTA5I4I","download_json":"https://pith.science/pith/TMS64CPHPXHDVGTSAV5HTA5I4I.json","view_paper":"https://pith.science/paper/TMS64CPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.12480&json=true","fetch_graph":"https://pith.science/api/pith-number/TMS64CPHPXHDVGTSAV5HTA5I4I/graph.json","fetch_events":"https://pith.science/api/pith-number/TMS64CPHPXHDVGTSAV5HTA5I4I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TMS64CPHPXHDVGTSAV5HTA5I4I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TMS64CPHPXHDVGTSAV5HTA5I4I/action/storage_attestation","attest_author":"https://pith.science/pith/TMS64CPHPXHDVGTSAV5HTA5I4I/action/author_attestation","sign_citation":"https://pith.science/pith/TMS64CPHPXHDVGTSAV5HTA5I4I/action/citation_signature","submit_replication":"https://pith.science/pith/TMS64CPHPXHDVGTSAV5HTA5I4I/action/replication_record"}},"created_at":"2026-07-05T08:58:26.948907+00:00","updated_at":"2026-07-05T08:58:26.948907+00:00"}