{"paper":{"title":"FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"FactNet couples 1.7 billion Wikidata assertions with traceable evidence spans from 316 Wikipedia editions to support multilingual factual grounding.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Fraser, Ge Gao, Jie Zhou, Kangyang Luo, Maosong Sun, Shuo Wang, Wen Lai, Xueren Zhang, Yingli Shen, Yudong Wang","submitted_at":"2026-02-03T11:44:11Z","abstract_excerpt":"Large language models hallucinate factual claims and struggle to ground their outputs in retrievable evidence, particularly in non-English languages. Existing resources impose a trade-off: structured knowledge bases lack textual grounding, whereas grounded datasets remain small and monolingual. We introduce FactNet, a billion-scale open resource that couples 1.7B Wikidata assertions with 3.01B evidence pointers drawn from 316 native Wikipedia editions. FactNet employs a deterministic construction pipeline, ensuring that every evidence unit is traceable to its source with byte-level precision. "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We introduce FactNet, a billion-scale open resource that couples 1.7B Wikidata assertions with 3.01B evidence pointers drawn from 316 native Wikipedia editions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the deterministic construction pipeline produces accurate, unbiased links between Wikidata assertions and Wikipedia evidence spans without introducing systematic errors or language-specific artifacts.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FactNet is a billion-scale multilingual knowledge graph that links 1.7B Wikidata assertions to 3.01B byte-precise evidence spans from 316 Wikipedia editions, accompanied by a leakage-controlled benchmark suite.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"FactNet couples 1.7 billion Wikidata assertions with traceable evidence spans from 316 Wikipedia editions to support multilingual factual grounding.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"888776294cd610a9bc5e1b6c8e03be0a1586e7521c6c02661f80b7e8416dd54a"},"source":{"id":"2602.03417","kind":"arxiv","version":2},"verdict":{"id":"958013c9-9795-4f84-9b54-99cc3bda985f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T08:02:40.282142Z","strongest_claim":"We introduce FactNet, a billion-scale open resource that couples 1.7B Wikidata assertions with 3.01B evidence pointers drawn from 316 native Wikipedia editions.","one_line_summary":"FactNet is a billion-scale multilingual knowledge graph that links 1.7B Wikidata assertions to 3.01B byte-precise evidence spans from 316 Wikipedia editions, accompanied by a leakage-controlled benchmark suite.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the deterministic construction pipeline produces accurate, unbiased links between Wikidata assertions and Wikipedia evidence spans without introducing systematic errors or language-specific artifacts.","pith_extraction_headline":"FactNet couples 1.7 billion Wikidata assertions with traceable evidence spans from 316 Wikipedia editions to support multilingual factual grounding."},"references":{"count":18,"sample":[{"doi":"","year":2021,"title":"naacl-main.278/","work_id":"490b6be4-b966-4425-948e-2a48f8fc47b5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/d19-1475","year":2007,"title":"Proceedings of the 2019","work_id":"b60c367d-b6b7-43ac-8f57-49b5948bc22c","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/","year":2023,"title":"doi: 10.18653/v1/ 2024.findings-acl.586","work_id":"8d675bdd-79ca-48d6-9163-fc17ce0e8ece","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.18653/v1/w17-3518","year":2025,"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","ref_index":5,"cited_arxiv_id":"2407.21783","is_internal_anchor":true},{"doi":"","year":2023,"title":"findings-emnlp.123/","work_id":"b16e76bb-9ed5-439e-b448-028c8207762e","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":18,"snapshot_sha256":"94b158bd42b368f3a2dcc33a179d60a248fbccaeafb9b498131edcd2db8531ee","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6dee6d81ca8f78f169b8322a95f7ce8c586fa03c886806cae05c5fddad70a4af"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}