{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5MYJHULEKVSAG2TCYBBBRE2HY3","short_pith_number":"pith:5MYJHULE","schema_version":"1.0","canonical_sha256":"eb3093d1645564036a62c042189347c6e8c93f641e9a3984c38cf3ed7712645d","source":{"kind":"arxiv","id":"2408.05141","version":3},"attestation_state":"computed","paper":{"title":"A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Chengwu Liu, Gongbo Sun, Jingyang Yuan, Ming Zhang, Siqi Li, Ye Yuan","submitted_at":"2024-08-09T15:53:55Z","abstract_excerpt":"Retrieval-augmented generation (RAG) is a framework enabling large language models (LLMs) to enhance their accuracy and reduce hallucinations by integrating external knowledge bases. In this paper, we introduce a hybrid RAG system enhanced through a comprehensive suite of optimizations that significantly improve retrieval quality, augment reasoning capabilities, and refine numerical computation ability. We refined the text chunks and tables in web pages, added attribute predictors to reduce hallucinations, conducted LLM Knowledge Extractor and Knowledge Graph Extractor, and finally built a rea"},"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":"2408.05141","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-09T15:53:55Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"57f3399420bf9e31964505631f3dd6aa06d4c062bbd9f201008dcc4999effb0a","abstract_canon_sha256":"e0da788991ddf4111b9863da7ab7c0188d90102e08344d3027e80ea30a341f9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:37.269441Z","signature_b64":"u5nCxHRPgK8QKcqh4cDD31D5rH2Q/uzl7EK+Yrn4b0g1nCF83xqmyYFIKREbJdv6lzA+fNcY7VR7h8r5aFWYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb3093d1645564036a62c042189347c6e8c93f641e9a3984c38cf3ed7712645d","last_reissued_at":"2026-07-05T09:01:37.268971Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:37.268971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Hybrid RAG System with Comprehensive Enhancement on Complex Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Chengwu Liu, Gongbo Sun, Jingyang Yuan, Ming Zhang, Siqi Li, Ye Yuan","submitted_at":"2024-08-09T15:53:55Z","abstract_excerpt":"Retrieval-augmented generation (RAG) is a framework enabling large language models (LLMs) to enhance their accuracy and reduce hallucinations by integrating external knowledge bases. In this paper, we introduce a hybrid RAG system enhanced through a comprehensive suite of optimizations that significantly improve retrieval quality, augment reasoning capabilities, and refine numerical computation ability. We refined the text chunks and tables in web pages, added attribute predictors to reduce hallucinations, conducted LLM Knowledge Extractor and Knowledge Graph Extractor, and finally built a rea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05141","kind":"arxiv","version":3},"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/2408.05141/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":"2408.05141","created_at":"2026-07-05T09:01:37.269023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.05141v3","created_at":"2026-07-05T09:01:37.269023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05141","created_at":"2026-07-05T09:01:37.269023+00:00"},{"alias_kind":"pith_short_12","alias_value":"5MYJHULEKVSA","created_at":"2026-07-05T09:01:37.269023+00:00"},{"alias_kind":"pith_short_16","alias_value":"5MYJHULEKVSAG2TC","created_at":"2026-07-05T09:01:37.269023+00:00"},{"alias_kind":"pith_short_8","alias_value":"5MYJHULE","created_at":"2026-07-05T09:01:37.269023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21059","citing_title":"DEFENGRAPH: Knowledge Graph-Enhanced LLMs for Blue Team Cyber Defense","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14172","citing_title":"Tug-of-War within A Decade: Conflict Resolution in Vulnerability Analysis via Teacher-Guided Retrieval-Augmented Generations","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25676","citing_title":"CORAL: Adaptive Retrieval Loop for Culturally-Aligned Multilingual RAG","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5MYJHULEKVSAG2TCYBBBRE2HY3","json":"https://pith.science/pith/5MYJHULEKVSAG2TCYBBBRE2HY3.json","graph_json":"https://pith.science/api/pith-number/5MYJHULEKVSAG2TCYBBBRE2HY3/graph.json","events_json":"https://pith.science/api/pith-number/5MYJHULEKVSAG2TCYBBBRE2HY3/events.json","paper":"https://pith.science/paper/5MYJHULE"},"agent_actions":{"view_html":"https://pith.science/pith/5MYJHULEKVSAG2TCYBBBRE2HY3","download_json":"https://pith.science/pith/5MYJHULEKVSAG2TCYBBBRE2HY3.json","view_paper":"https://pith.science/paper/5MYJHULE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.05141&json=true","fetch_graph":"https://pith.science/api/pith-number/5MYJHULEKVSAG2TCYBBBRE2HY3/graph.json","fetch_events":"https://pith.science/api/pith-number/5MYJHULEKVSAG2TCYBBBRE2HY3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5MYJHULEKVSAG2TCYBBBRE2HY3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5MYJHULEKVSAG2TCYBBBRE2HY3/action/storage_attestation","attest_author":"https://pith.science/pith/5MYJHULEKVSAG2TCYBBBRE2HY3/action/author_attestation","sign_citation":"https://pith.science/pith/5MYJHULEKVSAG2TCYBBBRE2HY3/action/citation_signature","submit_replication":"https://pith.science/pith/5MYJHULEKVSAG2TCYBBBRE2HY3/action/replication_record"}},"created_at":"2026-07-05T09:01:37.269023+00:00","updated_at":"2026-07-05T09:01:37.269023+00:00"}