{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5FJ7GDSP6YYRMAPB2OV6S4YFPE","short_pith_number":"pith:5FJ7GDSP","schema_version":"1.0","canonical_sha256":"e953f30e4ff6311601e1d3abe973057928ac0f786360bfe74e9710069e63369f","source":{"kind":"arxiv","id":"2504.16832","version":2},"attestation_state":"computed","paper":{"title":"GreenMind: A Next-Generation Vietnamese Large Language Model for Structured and Logical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hoang Quoc Viet, Luu Quy Tung, Pham Bao Loc, Vo Trong Thu","submitted_at":"2025-04-23T15:48:55Z","abstract_excerpt":"Chain-of-Thought (CoT) is a robust approach for tackling LLM tasks that require intermediate reasoning steps prior to generating a final answer. In this paper, we present GreenMind-Medium-14B-R1, the Vietnamese reasoning model inspired by the finetuning strategy based on Group Relative Policy Optimization. We also leverage a high-quality Vietnamese synthesized reasoning dataset and design two reward functions to tackle the main limitations of this technique: (i) language mixing, where we explicitly detect the presence of biased language characters during the process of sampling tokens, and (ii"},"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":"2504.16832","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-23T15:48:55Z","cross_cats_sorted":[],"title_canon_sha256":"91cbf3857018062c0385d51340c0aa29909dd4a988d6a966490fb1b996c66dfd","abstract_canon_sha256":"3f840feb1a6f6b33d9fb27b686c813ae455025529ed4be4c87b48890deb92b5c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:51:26.248464Z","signature_b64":"7iLGOb7oJ3Tg75oVLopeqaPeuaG68lgNVa3EJuV0D/+zs0rbosrnHqV4FYR+exOq3ZyrZhBXe6n3blJrFyqtBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e953f30e4ff6311601e1d3abe973057928ac0f786360bfe74e9710069e63369f","last_reissued_at":"2026-07-05T11:51:26.247929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:51:26.247929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GreenMind: A Next-Generation Vietnamese Large Language Model for Structured and Logical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hoang Quoc Viet, Luu Quy Tung, Pham Bao Loc, Vo Trong Thu","submitted_at":"2025-04-23T15:48:55Z","abstract_excerpt":"Chain-of-Thought (CoT) is a robust approach for tackling LLM tasks that require intermediate reasoning steps prior to generating a final answer. In this paper, we present GreenMind-Medium-14B-R1, the Vietnamese reasoning model inspired by the finetuning strategy based on Group Relative Policy Optimization. We also leverage a high-quality Vietnamese synthesized reasoning dataset and design two reward functions to tackle the main limitations of this technique: (i) language mixing, where we explicitly detect the presence of biased language characters during the process of sampling tokens, and (ii"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16832","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/2504.16832/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":"2504.16832","created_at":"2026-07-05T11:51:26.247992+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.16832v2","created_at":"2026-07-05T11:51:26.247992+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16832","created_at":"2026-07-05T11:51:26.247992+00:00"},{"alias_kind":"pith_short_12","alias_value":"5FJ7GDSP6YYR","created_at":"2026-07-05T11:51:26.247992+00:00"},{"alias_kind":"pith_short_16","alias_value":"5FJ7GDSP6YYRMAPB","created_at":"2026-07-05T11:51:26.247992+00:00"},{"alias_kind":"pith_short_8","alias_value":"5FJ7GDSP","created_at":"2026-07-05T11:51:26.247992+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.28647","citing_title":"ConnectED: A Curriculum-Aligned AI System for Vietnamese Instructional Lesson Planning and Student Learning","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5FJ7GDSP6YYRMAPB2OV6S4YFPE","json":"https://pith.science/pith/5FJ7GDSP6YYRMAPB2OV6S4YFPE.json","graph_json":"https://pith.science/api/pith-number/5FJ7GDSP6YYRMAPB2OV6S4YFPE/graph.json","events_json":"https://pith.science/api/pith-number/5FJ7GDSP6YYRMAPB2OV6S4YFPE/events.json","paper":"https://pith.science/paper/5FJ7GDSP"},"agent_actions":{"view_html":"https://pith.science/pith/5FJ7GDSP6YYRMAPB2OV6S4YFPE","download_json":"https://pith.science/pith/5FJ7GDSP6YYRMAPB2OV6S4YFPE.json","view_paper":"https://pith.science/paper/5FJ7GDSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.16832&json=true","fetch_graph":"https://pith.science/api/pith-number/5FJ7GDSP6YYRMAPB2OV6S4YFPE/graph.json","fetch_events":"https://pith.science/api/pith-number/5FJ7GDSP6YYRMAPB2OV6S4YFPE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5FJ7GDSP6YYRMAPB2OV6S4YFPE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5FJ7GDSP6YYRMAPB2OV6S4YFPE/action/storage_attestation","attest_author":"https://pith.science/pith/5FJ7GDSP6YYRMAPB2OV6S4YFPE/action/author_attestation","sign_citation":"https://pith.science/pith/5FJ7GDSP6YYRMAPB2OV6S4YFPE/action/citation_signature","submit_replication":"https://pith.science/pith/5FJ7GDSP6YYRMAPB2OV6S4YFPE/action/replication_record"}},"created_at":"2026-07-05T11:51:26.247992+00:00","updated_at":"2026-07-05T11:51:26.247992+00:00"}