{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CGVWIY2WRIZQLESAWSETAHYCKO","short_pith_number":"pith:CGVWIY2W","schema_version":"1.0","canonical_sha256":"11ab6463568a33059240b489301f02539c1dd28054c1c7653ec716e64fa30f15","source":{"kind":"arxiv","id":"2509.09713","version":1},"attestation_state":"computed","paper":{"title":"HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dan Yang, Duolin Sun, Jian Wang, Jie Feng, Jinjie Gu, Lianzhen Zhong, Peng Wei, Yihan Jiao, Yue Shen, Zhehao Tan","submitted_at":"2025-09-08T06:22:38Z","abstract_excerpt":"The Retrieval-Augmented Generation (RAG) approach enhances question-answering systems and dialogue generation tasks by integrating information retrieval (IR) technologies with large language models (LLMs). This strategy, which retrieves information from external knowledge bases to bolster the response capabilities of generative models, has achieved certain successes. However, current RAG methods still face numerous challenges when dealing with multi-hop queries. For instance, some approaches overly rely on iterative retrieval, wasting too many retrieval steps on compound queries. Additionally,"},"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":"2509.09713","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-09-08T06:22:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"72b2d18c4519d7c01edafcec799b8fc8f2f4e7892601d3bb4f5f37dffd3d8b5b","abstract_canon_sha256":"bdd8f84613987a414465d61e48843aff891ba40a57647239207115e816559c45"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:47.650309Z","signature_b64":"PFgJt+cZVzyKkl4xr/B8+R5upBW729wRe9EFZyiBnZ+0PZ3mt5phFx3+3UAXOHyQcaJ1gHm1Q6u+o9UQBjHDBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11ab6463568a33059240b489301f02539c1dd28054c1c7653ec716e64fa30f15","last_reissued_at":"2026-07-05T12:09:47.649804Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:47.649804Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HANRAG: Heuristic Accurate Noise-resistant Retrieval-Augmented Generation for Multi-hop Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dan Yang, Duolin Sun, Jian Wang, Jie Feng, Jinjie Gu, Lianzhen Zhong, Peng Wei, Yihan Jiao, Yue Shen, Zhehao Tan","submitted_at":"2025-09-08T06:22:38Z","abstract_excerpt":"The Retrieval-Augmented Generation (RAG) approach enhances question-answering systems and dialogue generation tasks by integrating information retrieval (IR) technologies with large language models (LLMs). This strategy, which retrieves information from external knowledge bases to bolster the response capabilities of generative models, has achieved certain successes. However, current RAG methods still face numerous challenges when dealing with multi-hop queries. For instance, some approaches overly rely on iterative retrieval, wasting too many retrieval steps on compound queries. Additionally,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.09713","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/2509.09713/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":"2509.09713","created_at":"2026-07-05T12:09:47.649861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.09713v1","created_at":"2026-07-05T12:09:47.649861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.09713","created_at":"2026-07-05T12:09:47.649861+00:00"},{"alias_kind":"pith_short_12","alias_value":"CGVWIY2WRIZQ","created_at":"2026-07-05T12:09:47.649861+00:00"},{"alias_kind":"pith_short_16","alias_value":"CGVWIY2WRIZQLESA","created_at":"2026-07-05T12:09:47.649861+00:00"},{"alias_kind":"pith_short_8","alias_value":"CGVWIY2W","created_at":"2026-07-05T12:09:47.649861+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.11653","citing_title":"GroupRank: A Groupwise Paradigm for Effective and Efficient Passage Reranking with LLMs","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CGVWIY2WRIZQLESAWSETAHYCKO","json":"https://pith.science/pith/CGVWIY2WRIZQLESAWSETAHYCKO.json","graph_json":"https://pith.science/api/pith-number/CGVWIY2WRIZQLESAWSETAHYCKO/graph.json","events_json":"https://pith.science/api/pith-number/CGVWIY2WRIZQLESAWSETAHYCKO/events.json","paper":"https://pith.science/paper/CGVWIY2W"},"agent_actions":{"view_html":"https://pith.science/pith/CGVWIY2WRIZQLESAWSETAHYCKO","download_json":"https://pith.science/pith/CGVWIY2WRIZQLESAWSETAHYCKO.json","view_paper":"https://pith.science/paper/CGVWIY2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.09713&json=true","fetch_graph":"https://pith.science/api/pith-number/CGVWIY2WRIZQLESAWSETAHYCKO/graph.json","fetch_events":"https://pith.science/api/pith-number/CGVWIY2WRIZQLESAWSETAHYCKO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CGVWIY2WRIZQLESAWSETAHYCKO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CGVWIY2WRIZQLESAWSETAHYCKO/action/storage_attestation","attest_author":"https://pith.science/pith/CGVWIY2WRIZQLESAWSETAHYCKO/action/author_attestation","sign_citation":"https://pith.science/pith/CGVWIY2WRIZQLESAWSETAHYCKO/action/citation_signature","submit_replication":"https://pith.science/pith/CGVWIY2WRIZQLESAWSETAHYCKO/action/replication_record"}},"created_at":"2026-07-05T12:09:47.649861+00:00","updated_at":"2026-07-05T12:09:47.649861+00:00"}