{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7T4CXTBHVUD7WSWAKJ5S44IER7","short_pith_number":"pith:7T4CXTBH","schema_version":"1.0","canonical_sha256":"fcf82bcc27ad07fb4ac0527b2e71048fc579862b0d95b71dc02cf01ca0f60154","source":{"kind":"arxiv","id":"2506.16037","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Fang Sun, Kejian Tong, Wenchao Zhang, Xinyue Huang, Yunbo Liu, Ziqi Lin","submitted_at":"2025-06-19T05:22:18Z","abstract_excerpt":"This paper presents a novel Retrieval-Augmented Generation (RAG) framework tailored for complex question answering tasks, addressing challenges in multi-hop reasoning and contextual understanding across lengthy documents. Built upon LLaMA 3, the framework integrates a dense retrieval module with advanced context fusion and multi-hop reasoning mechanisms, enabling more accurate and coherent response generation. A joint optimization strategy combining retrieval likelihood and generation cross-entropy improves the model's robustness and adaptability. Experimental results show that the proposed sy"},"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":"2506.16037","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T05:22:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"72b8ee1f2657a349d6d7812712201bb588324ea1eb86a5a255c097e61d4e1b14","abstract_canon_sha256":"d31d6c57927b14f3488175dd7beaf34290d0129522e7994008a61ca883ea65d0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:29.037480Z","signature_b64":"EAwIk5lVN8JeithNoeKH5Q/z1SvBrC8l5u5icfeEDV1jGx3A4Bi0HsgNzozNSjwZu6tZBjq7p2bNKK+MAIKkCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fcf82bcc27ad07fb4ac0527b2e71048fc579862b0d95b71dc02cf01ca0f60154","last_reissued_at":"2026-07-05T11:24:29.036976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:29.036976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Document-Level Question Answering via Multi-Hop Retrieval-Augmented Generation with LLaMA 3","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Fang Sun, Kejian Tong, Wenchao Zhang, Xinyue Huang, Yunbo Liu, Ziqi Lin","submitted_at":"2025-06-19T05:22:18Z","abstract_excerpt":"This paper presents a novel Retrieval-Augmented Generation (RAG) framework tailored for complex question answering tasks, addressing challenges in multi-hop reasoning and contextual understanding across lengthy documents. Built upon LLaMA 3, the framework integrates a dense retrieval module with advanced context fusion and multi-hop reasoning mechanisms, enabling more accurate and coherent response generation. A joint optimization strategy combining retrieval likelihood and generation cross-entropy improves the model's robustness and adaptability. Experimental results show that the proposed sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16037","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/2506.16037/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":"2506.16037","created_at":"2026-07-05T11:24:29.037040+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16037v1","created_at":"2026-07-05T11:24:29.037040+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16037","created_at":"2026-07-05T11:24:29.037040+00:00"},{"alias_kind":"pith_short_12","alias_value":"7T4CXTBHVUD7","created_at":"2026-07-05T11:24:29.037040+00:00"},{"alias_kind":"pith_short_16","alias_value":"7T4CXTBHVUD7WSWA","created_at":"2026-07-05T11:24:29.037040+00:00"},{"alias_kind":"pith_short_8","alias_value":"7T4CXTBH","created_at":"2026-07-05T11:24:29.037040+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/7T4CXTBHVUD7WSWAKJ5S44IER7","json":"https://pith.science/pith/7T4CXTBHVUD7WSWAKJ5S44IER7.json","graph_json":"https://pith.science/api/pith-number/7T4CXTBHVUD7WSWAKJ5S44IER7/graph.json","events_json":"https://pith.science/api/pith-number/7T4CXTBHVUD7WSWAKJ5S44IER7/events.json","paper":"https://pith.science/paper/7T4CXTBH"},"agent_actions":{"view_html":"https://pith.science/pith/7T4CXTBHVUD7WSWAKJ5S44IER7","download_json":"https://pith.science/pith/7T4CXTBHVUD7WSWAKJ5S44IER7.json","view_paper":"https://pith.science/paper/7T4CXTBH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16037&json=true","fetch_graph":"https://pith.science/api/pith-number/7T4CXTBHVUD7WSWAKJ5S44IER7/graph.json","fetch_events":"https://pith.science/api/pith-number/7T4CXTBHVUD7WSWAKJ5S44IER7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7T4CXTBHVUD7WSWAKJ5S44IER7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7T4CXTBHVUD7WSWAKJ5S44IER7/action/storage_attestation","attest_author":"https://pith.science/pith/7T4CXTBHVUD7WSWAKJ5S44IER7/action/author_attestation","sign_citation":"https://pith.science/pith/7T4CXTBHVUD7WSWAKJ5S44IER7/action/citation_signature","submit_replication":"https://pith.science/pith/7T4CXTBHVUD7WSWAKJ5S44IER7/action/replication_record"}},"created_at":"2026-07-05T11:24:29.037040+00:00","updated_at":"2026-07-05T11:24:29.037040+00:00"}