{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HZGLOBFSB7QDGGICCADFQPDIPR","short_pith_number":"pith:HZGLOBFS","schema_version":"1.0","canonical_sha256":"3e4cb704b20fe03319021006583c687c7bec4e3e1693dfa0b43cbd43054616e6","source":{"kind":"arxiv","id":"2406.13779","version":1},"attestation_state":"computed","paper":{"title":"FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinjie Gu, Jiyan Jiang, Tao Sun, Tianchi Cai, Xierui Song, Yinger Zhang, Yunqi Xu, Zhiwen Tan","submitted_at":"2024-06-19T19:06:36Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) has become prevalent in question-answering (QA) tasks due to its ability of utilizing search engine to enhance the quality of long-form question-answering (LFQA). Despite the emergence of various open source methods and web-enhanced commercial systems such as Bing Chat, two critical problems remain unsolved, i.e., the lack of factuality and clear logic in the generated long-form answers. In this paper, we remedy these issues via a systematic study on answer generation in web-enhanced LFQA. Specifically, we first propose a novel outline-enhanced generator to"},"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":"2406.13779","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-19T19:06:36Z","cross_cats_sorted":[],"title_canon_sha256":"5341cf44ab744a68686c1d51a4482a517548e0168fbdd787cf51a6cb97bf4b89","abstract_canon_sha256":"76bd21cd688371e6abb8104ccfece87a918ededc3dff876e60cfef1970f3ac18"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:38:38.942057Z","signature_b64":"VT21gesqEwvmGFMIFaYp6FYmoxB12jyx8VOs0xIFS1u4wCv/kkN+6QhffFqmREWnvWjWL7v9/trgn6RT1Rq4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3e4cb704b20fe03319021006583c687c7bec4e3e1693dfa0b43cbd43054616e6","last_reissued_at":"2026-07-05T08:38:38.941606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:38:38.941606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FoRAG: Factuality-optimized Retrieval Augmented Generation for Web-enhanced Long-form Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jinjie Gu, Jiyan Jiang, Tao Sun, Tianchi Cai, Xierui Song, Yinger Zhang, Yunqi Xu, Zhiwen Tan","submitted_at":"2024-06-19T19:06:36Z","abstract_excerpt":"Retrieval Augmented Generation (RAG) has become prevalent in question-answering (QA) tasks due to its ability of utilizing search engine to enhance the quality of long-form question-answering (LFQA). Despite the emergence of various open source methods and web-enhanced commercial systems such as Bing Chat, two critical problems remain unsolved, i.e., the lack of factuality and clear logic in the generated long-form answers. In this paper, we remedy these issues via a systematic study on answer generation in web-enhanced LFQA. Specifically, we first propose a novel outline-enhanced generator to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.13779","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/2406.13779/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":"2406.13779","created_at":"2026-07-05T08:38:38.941665+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.13779v1","created_at":"2026-07-05T08:38:38.941665+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.13779","created_at":"2026-07-05T08:38:38.941665+00:00"},{"alias_kind":"pith_short_12","alias_value":"HZGLOBFSB7QD","created_at":"2026-07-05T08:38:38.941665+00:00"},{"alias_kind":"pith_short_16","alias_value":"HZGLOBFSB7QDGGIC","created_at":"2026-07-05T08:38:38.941665+00:00"},{"alias_kind":"pith_short_8","alias_value":"HZGLOBFS","created_at":"2026-07-05T08:38:38.941665+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HZGLOBFSB7QDGGICCADFQPDIPR","json":"https://pith.science/pith/HZGLOBFSB7QDGGICCADFQPDIPR.json","graph_json":"https://pith.science/api/pith-number/HZGLOBFSB7QDGGICCADFQPDIPR/graph.json","events_json":"https://pith.science/api/pith-number/HZGLOBFSB7QDGGICCADFQPDIPR/events.json","paper":"https://pith.science/paper/HZGLOBFS"},"agent_actions":{"view_html":"https://pith.science/pith/HZGLOBFSB7QDGGICCADFQPDIPR","download_json":"https://pith.science/pith/HZGLOBFSB7QDGGICCADFQPDIPR.json","view_paper":"https://pith.science/paper/HZGLOBFS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.13779&json=true","fetch_graph":"https://pith.science/api/pith-number/HZGLOBFSB7QDGGICCADFQPDIPR/graph.json","fetch_events":"https://pith.science/api/pith-number/HZGLOBFSB7QDGGICCADFQPDIPR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HZGLOBFSB7QDGGICCADFQPDIPR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HZGLOBFSB7QDGGICCADFQPDIPR/action/storage_attestation","attest_author":"https://pith.science/pith/HZGLOBFSB7QDGGICCADFQPDIPR/action/author_attestation","sign_citation":"https://pith.science/pith/HZGLOBFSB7QDGGICCADFQPDIPR/action/citation_signature","submit_replication":"https://pith.science/pith/HZGLOBFSB7QDGGICCADFQPDIPR/action/replication_record"}},"created_at":"2026-07-05T08:38:38.941665+00:00","updated_at":"2026-07-05T08:38:38.941665+00:00"}