{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KX44EKQPZIOJAI2VALLUHO6KNW","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":"1b3b6f02a992854055a08139fa83db73475090fcdf09af62455eacfda61e3fb8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-10T02:55:48Z","title_canon_sha256":"a143a0f7c17f5ae2a367f7c4843c914fc4d99de2f997506c30ba5198100118d9"},"schema_version":"1.0","source":{"id":"2304.04358","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.04358","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"arxiv_version","alias_value":"2304.04358v1","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04358","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"pith_short_12","alias_value":"KX44EKQPZIOJ","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"pith_short_16","alias_value":"KX44EKQPZIOJAI2V","created_at":"2026-07-05T05:59:25Z"},{"alias_kind":"pith_short_8","alias_value":"KX44EKQP","created_at":"2026-07-05T05:59:25Z"}],"graph_snapshots":[{"event_id":"sha256:87cdcd466bb312cd1c3f6e3c658c06ea8bcf12971555eb1369f64316138365f2","target":"graph","created_at":"2026-07-05T05:59:25Z","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/2304.04358/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce a new NLP task -- generating short factual articles with references for queries by mining supporting evidence from the Web. In this task, called WebBrain, the ultimate goal is to generate a fluent, informative, and factually-correct short article (e.g., a Wikipedia article) for a factual query unseen in Wikipedia. To enable experiments on WebBrain, we construct a large-scale dataset WebBrain-Raw by extracting English Wikipedia articles and their crawlable Wikipedia references. WebBrain-Raw is ten times larger than the previous biggest peer dataset, which can greatly","authors_text":"Haoqi Gu, Hongjing Qian, Jian-Yun Nie, Ji-Rong Wen, Ruofei Lai, Xinyu Zhang, Yutao Zhu, Zhao Cao, Zheng Liu, Zhicheng Dou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-10T02:55:48Z","title":"WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04358","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":"sha256:2d35ec15179788285ef6523540e3ea5e0fd6c4ac93089e8b2f99cceb747ce697","target":"record","created_at":"2026-07-05T05:59:25Z","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":"1b3b6f02a992854055a08139fa83db73475090fcdf09af62455eacfda61e3fb8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-10T02:55:48Z","title_canon_sha256":"a143a0f7c17f5ae2a367f7c4843c914fc4d99de2f997506c30ba5198100118d9"},"schema_version":"1.0","source":{"id":"2304.04358","kind":"arxiv","version":1}},"canonical_sha256":"55f9c22a0fca1c90235502d743bbca6dbea0167690358076f382bb0bc57bd240","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"55f9c22a0fca1c90235502d743bbca6dbea0167690358076f382bb0bc57bd240","first_computed_at":"2026-07-05T05:59:25.345957Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:25.345957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1tzfb9V+3RIdQ6BaossQ1R/b1EVhQVKvCAqDi4FcPCdMa5v+Q49OjUEPWJyD00ZeLuMFXxIOfS1OwXFV2O2LAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:25.346375Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.04358","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d35ec15179788285ef6523540e3ea5e0fd6c4ac93089e8b2f99cceb747ce697","sha256:87cdcd466bb312cd1c3f6e3c658c06ea8bcf12971555eb1369f64316138365f2"],"state_sha256":"bf463d740e9a38362542d8a09e87890fcabb2afbf22c63bf9d641ead666ba469"}