{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QPAN4S3MRITDVK2MEXPJDU6HVQ","short_pith_number":"pith:QPAN4S3M","canonical_record":{"source":{"id":"2602.03417","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-03T11:44:11Z","cross_cats_sorted":[],"title_canon_sha256":"e7f948d3451ac21821fd9fd5601ed2ef43d375c157f430b516e8e6d5e60eea77","abstract_canon_sha256":"44ede394c2295cdcfbeb879fabaecdfdcd1418eb824657a1ecf26848c61ebd49"},"schema_version":"1.0"},"canonical_sha256":"83c0de4b6c8a263aab4c25de91d3c7ac065916b9e63ab1b6ef22ae6f710f39ce","source":{"kind":"arxiv","id":"2602.03417","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.03417","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2602.03417v2","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03417","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"QPAN4S3MRITD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QPAN4S3MRITDVK2M","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QPAN4S3M","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QPAN4S3MRITDVK2MEXPJDU6HVQ","target":"record","payload":{"canonical_record":{"source":{"id":"2602.03417","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-03T11:44:11Z","cross_cats_sorted":[],"title_canon_sha256":"e7f948d3451ac21821fd9fd5601ed2ef43d375c157f430b516e8e6d5e60eea77","abstract_canon_sha256":"44ede394c2295cdcfbeb879fabaecdfdcd1418eb824657a1ecf26848c61ebd49"},"schema_version":"1.0"},"canonical_sha256":"83c0de4b6c8a263aab4c25de91d3c7ac065916b9e63ab1b6ef22ae6f710f39ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:16.411523Z","signature_b64":"Mkot2E3x4DUIBc3A3QSCPILmYkh/V24Cfy8xMhSLDE8ufbzpmBHbvOS7Ji/Yn8uoGZfjuGwZQlWDFHuVr1LUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"83c0de4b6c8a263aab4c25de91d3c7ac065916b9e63ab1b6ef22ae6f710f39ce","last_reissued_at":"2026-05-17T23:39:16.410798Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:16.410798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.03417","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IYrAQKzaMASuYz20ghZ1JkPeKR0+XYKFbkG5Vj0T6fOvjFezZwGEPG4irpoim48nYGUvC3321g9/xeVRYZEtBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:51:32.631919Z"},"content_sha256":"8fd77f806ce45b3008e3cbe2aebb8770ad6fa4868d4d342373bab81607225cd4","schema_version":"1.0","event_id":"sha256:8fd77f806ce45b3008e3cbe2aebb8770ad6fa4868d4d342373bab81607225cd4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QPAN4S3MRITDVK2MEXPJDU6HVQ","target":"graph","payload":{"graph_snapshot":{"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"},"verdict_id":"958013c9-9795-4f84-9b54-99cc3bda985f"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iCBxGlZkq+y40qRfhtwuXft3fuk+mzoPHvHm6RBffp3p4BkxvZCuS48MU5xLF2Ty/bC9Tnqx2KFE2YIpB9sNDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T15:51:32.632917Z"},"content_sha256":"ab526a9ca314a2b6cfa14b3e9792ac9334bb818657846e76295ec225d0574e97","schema_version":"1.0","event_id":"sha256:ab526a9ca314a2b6cfa14b3e9792ac9334bb818657846e76295ec225d0574e97"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QPAN4S3MRITDVK2MEXPJDU6HVQ/bundle.json","state_url":"https://pith.science/pith/QPAN4S3MRITDVK2MEXPJDU6HVQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QPAN4S3MRITDVK2MEXPJDU6HVQ/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":"2026-05-27T15:51:32Z","links":{"resolver":"https://pith.science/pith/QPAN4S3MRITDVK2MEXPJDU6HVQ","bundle":"https://pith.science/pith/QPAN4S3MRITDVK2MEXPJDU6HVQ/bundle.json","state":"https://pith.science/pith/QPAN4S3MRITDVK2MEXPJDU6HVQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QPAN4S3MRITDVK2MEXPJDU6HVQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QPAN4S3MRITDVK2MEXPJDU6HVQ","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":"44ede394c2295cdcfbeb879fabaecdfdcd1418eb824657a1ecf26848c61ebd49","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-03T11:44:11Z","title_canon_sha256":"e7f948d3451ac21821fd9fd5601ed2ef43d375c157f430b516e8e6d5e60eea77"},"schema_version":"1.0","source":{"id":"2602.03417","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.03417","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"arxiv_version","alias_value":"2602.03417v2","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.03417","created_at":"2026-05-17T23:39:16Z"},{"alias_kind":"pith_short_12","alias_value":"QPAN4S3MRITD","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QPAN4S3MRITDVK2M","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QPAN4S3M","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:ab526a9ca314a2b6cfa14b3e9792ac9334bb818657846e76295ec225d0574e97","target":"graph","created_at":"2026-05-17T23:39:16Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"FactNet couples 1.7 billion Wikidata assertions with traceable evidence spans from 316 Wikipedia editions to support multilingual factual grounding."}],"snapshot_sha256":"888776294cd610a9bc5e1b6c8e03be0a1586e7521c6c02661f80b7e8416dd54a"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"6dee6d81ca8f78f169b8322a95f7ce8c586fa03c886806cae05c5fddad70a4af"},"paper":{"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. ","authors_text":"Alexander Fraser, Ge Gao, Jie Zhou, Kangyang Luo, Maosong Sun, Shuo Wang, Wen Lai, Xueren Zhang, Yingli Shen, Yudong Wang","cross_cats":[],"headline":"FactNet couples 1.7 billion Wikidata assertions with traceable evidence spans from 316 Wikipedia editions to support multilingual factual grounding.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-03T11:44:11Z","title":"FactNet: A Billion-Scale Knowledge Graph for Multilingual Factual Grounding"},"references":{"count":18,"internal_anchors":3,"resolved_work":18,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"naacl-main.278/","work_id":"490b6be4-b966-4425-948e-2a48f8fc47b5","year":2021},{"cited_arxiv_id":"","doi":"10.18653/v1/d19-1475","is_internal_anchor":false,"ref_index":2,"title":"Proceedings of the 2019","work_id":"b60c367d-b6b7-43ac-8f57-49b5948bc22c","year":2007},{"cited_arxiv_id":"","doi":"10.18653/v1/","is_internal_anchor":false,"ref_index":3,"title":"doi: 10.18653/v1/ 2024.findings-acl.586","work_id":"8d675bdd-79ca-48d6-9163-fc17ce0e8ece","year":2023},{"cited_arxiv_id":"2407.21783","doi":"10.18653/v1/w17-3518","is_internal_anchor":true,"ref_index":5,"title":"The Llama 3 Herd of Models","work_id":"1549a635-88af-4ac1-acfe-51ae7bb53345","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":6,"title":"findings-emnlp.123/","work_id":"b16e76bb-9ed5-439e-b448-028c8207762e","year":2023}],"snapshot_sha256":"94b158bd42b368f3a2dcc33a179d60a248fbccaeafb9b498131edcd2db8531ee"},"source":{"id":"2602.03417","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T08:02:40.282142Z","id":"958013c9-9795-4f84-9b54-99cc3bda985f","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"FactNet couples 1.7 billion Wikidata assertions with traceable evidence spans from 316 Wikipedia editions to support multilingual factual grounding.","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.","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."}},"verdict_id":"958013c9-9795-4f84-9b54-99cc3bda985f"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:8fd77f806ce45b3008e3cbe2aebb8770ad6fa4868d4d342373bab81607225cd4","target":"record","created_at":"2026-05-17T23:39:16Z","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":"44ede394c2295cdcfbeb879fabaecdfdcd1418eb824657a1ecf26848c61ebd49","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-03T11:44:11Z","title_canon_sha256":"e7f948d3451ac21821fd9fd5601ed2ef43d375c157f430b516e8e6d5e60eea77"},"schema_version":"1.0","source":{"id":"2602.03417","kind":"arxiv","version":2}},"canonical_sha256":"83c0de4b6c8a263aab4c25de91d3c7ac065916b9e63ab1b6ef22ae6f710f39ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83c0de4b6c8a263aab4c25de91d3c7ac065916b9e63ab1b6ef22ae6f710f39ce","first_computed_at":"2026-05-17T23:39:16.410798Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:16.410798Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Mkot2E3x4DUIBc3A3QSCPILmYkh/V24Cfy8xMhSLDE8ufbzpmBHbvOS7Ji/Yn8uoGZfjuGwZQlWDFHuVr1LUCQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:16.411523Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.03417","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8fd77f806ce45b3008e3cbe2aebb8770ad6fa4868d4d342373bab81607225cd4","sha256:ab526a9ca314a2b6cfa14b3e9792ac9334bb818657846e76295ec225d0574e97"],"state_sha256":"45773bad2af117acfe64c564a6c5b4b8aa6a7ad2f0580e5c1db5a9bf42380b62"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wRPIEesHwqp90Cs2wscmEsKXU61e/Ro4K7uMdmfi65mi0+Y40wYhSZHv5tChPnhV94gZZKEGFfMqKcxUb07xCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T15:51:32.637525Z","bundle_sha256":"6526181fa4b50cfb9e2377e957234c1a0d9439d65b347a00c290034aaf5b28f4"}}