{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KX44EKQPZIOJAI2VALLUHO6KNW","short_pith_number":"pith:KX44EKQP","schema_version":"1.0","canonical_sha256":"55f9c22a0fca1c90235502d743bbca6dbea0167690358076f382bb0bc57bd240","source":{"kind":"arxiv","id":"2304.04358","version":1},"attestation_state":"computed","paper":{"title":"WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoqi Gu, Hongjing Qian, Jian-Yun Nie, Ji-Rong Wen, Ruofei Lai, Xinyu Zhang, Yutao Zhu, Zhao Cao, Zheng Liu, Zhicheng Dou","submitted_at":"2023-04-10T02:55:48Z","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"},"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":"2304.04358","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-04-10T02:55:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a143a0f7c17f5ae2a367f7c4843c914fc4d99de2f997506c30ba5198100118d9","abstract_canon_sha256":"1b3b6f02a992854055a08139fa83db73475090fcdf09af62455eacfda61e3fb8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:25.346375Z","signature_b64":"1tzfb9V+3RIdQ6BaossQ1R/b1EVhQVKvCAqDi4FcPCdMa5v+Q49OjUEPWJyD00ZeLuMFXxIOfS1OwXFV2O2LAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55f9c22a0fca1c90235502d743bbca6dbea0167690358076f382bb0bc57bd240","last_reissued_at":"2026-07-05T05:59:25.345957Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:25.345957Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WebBrain: Learning to Generate Factually Correct Articles for Queries by Grounding on Large Web Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoqi Gu, Hongjing Qian, Jian-Yun Nie, Ji-Rong Wen, Ruofei Lai, Xinyu Zhang, Yutao Zhu, Zhao Cao, Zheng Liu, Zhicheng Dou","submitted_at":"2023-04-10T02:55:48Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.04358","kind":"arxiv","version":1},"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/2304.04358/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":"2304.04358","created_at":"2026-07-05T05:59:25.346013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.04358v1","created_at":"2026-07-05T05:59:25.346013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.04358","created_at":"2026-07-05T05:59:25.346013+00:00"},{"alias_kind":"pith_short_12","alias_value":"KX44EKQPZIOJ","created_at":"2026-07-05T05:59:25.346013+00:00"},{"alias_kind":"pith_short_16","alias_value":"KX44EKQPZIOJAI2V","created_at":"2026-07-05T05:59:25.346013+00:00"},{"alias_kind":"pith_short_8","alias_value":"KX44EKQP","created_at":"2026-07-05T05:59:25.346013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2409.10102","citing_title":"Trustworthiness in Retrieval-Augmented Generation Systems: A Survey","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KX44EKQPZIOJAI2VALLUHO6KNW","json":"https://pith.science/pith/KX44EKQPZIOJAI2VALLUHO6KNW.json","graph_json":"https://pith.science/api/pith-number/KX44EKQPZIOJAI2VALLUHO6KNW/graph.json","events_json":"https://pith.science/api/pith-number/KX44EKQPZIOJAI2VALLUHO6KNW/events.json","paper":"https://pith.science/paper/KX44EKQP"},"agent_actions":{"view_html":"https://pith.science/pith/KX44EKQPZIOJAI2VALLUHO6KNW","download_json":"https://pith.science/pith/KX44EKQPZIOJAI2VALLUHO6KNW.json","view_paper":"https://pith.science/paper/KX44EKQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.04358&json=true","fetch_graph":"https://pith.science/api/pith-number/KX44EKQPZIOJAI2VALLUHO6KNW/graph.json","fetch_events":"https://pith.science/api/pith-number/KX44EKQPZIOJAI2VALLUHO6KNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KX44EKQPZIOJAI2VALLUHO6KNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KX44EKQPZIOJAI2VALLUHO6KNW/action/storage_attestation","attest_author":"https://pith.science/pith/KX44EKQPZIOJAI2VALLUHO6KNW/action/author_attestation","sign_citation":"https://pith.science/pith/KX44EKQPZIOJAI2VALLUHO6KNW/action/citation_signature","submit_replication":"https://pith.science/pith/KX44EKQPZIOJAI2VALLUHO6KNW/action/replication_record"}},"created_at":"2026-07-05T05:59:25.346013+00:00","updated_at":"2026-07-05T05:59:25.346013+00:00"}