{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q5AVBUDS5ULTNGOHYOP5LEEVC5","short_pith_number":"pith:Q5AVBUDS","schema_version":"1.0","canonical_sha256":"874150d072ed173699c7c39fd590951745457991bd788fbfc7288e534fb6a30b","source":{"kind":"arxiv","id":"2504.13079","version":2},"attestation_state":"computed","paper":{"title":"Retrieval-Augmented Generation with Conflicting Evidence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Archiki Prasad, Elias Stengel-Eskin, Han Wang, Mohit Bansal","submitted_at":"2025-04-17T16:46:11Z","abstract_excerpt":"Large language model (LLM) agents are increasingly employing retrieval-augmented generation (RAG) to improve the factuality of their responses. However, in practice, these systems often need to handle ambiguous user queries and potentially conflicting information from multiple sources while also suppressing inaccurate information from noisy or irrelevant documents. Prior work has generally studied and addressed these challenges in isolation, considering only one aspect at a time, such as handling ambiguity or robustness to noise and misinformation. We instead consider multiple factors simultan"},"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":"2504.13079","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-17T16:46:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"65c1520cf831c1a9137ae21a783fb09943b29a0eb6fef54e9d1b9d715848b1ab","abstract_canon_sha256":"5547ab51707aaa10c66a1848fe4f011ef32d23eff8fd04d2482b8f389548f9c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:20.121104Z","signature_b64":"75nCCEaPKKC6QBT8teNUu/ac3VR7Sg3Vgl6ClRQuJRjlPppe8oA1yhK3ke1kTqfskqQ/Y2aCl3NrTWpYVhD3Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"874150d072ed173699c7c39fd590951745457991bd788fbfc7288e534fb6a30b","last_reissued_at":"2026-07-05T11:52:20.120514Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:20.120514Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval-Augmented Generation with Conflicting Evidence","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Archiki Prasad, Elias Stengel-Eskin, Han Wang, Mohit Bansal","submitted_at":"2025-04-17T16:46:11Z","abstract_excerpt":"Large language model (LLM) agents are increasingly employing retrieval-augmented generation (RAG) to improve the factuality of their responses. However, in practice, these systems often need to handle ambiguous user queries and potentially conflicting information from multiple sources while also suppressing inaccurate information from noisy or irrelevant documents. Prior work has generally studied and addressed these challenges in isolation, considering only one aspect at a time, such as handling ambiguity or robustness to noise and misinformation. We instead consider multiple factors simultan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13079","kind":"arxiv","version":2},"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/2504.13079/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":"2504.13079","created_at":"2026-07-05T11:52:20.120593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13079v2","created_at":"2026-07-05T11:52:20.120593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13079","created_at":"2026-07-05T11:52:20.120593+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5AVBUDS5ULT","created_at":"2026-07-05T11:52:20.120593+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5AVBUDS5ULTNGOH","created_at":"2026-07-05T11:52:20.120593+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5AVBUDS","created_at":"2026-07-05T11:52:20.120593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25191","citing_title":"To Isolate or to Score? Model-Adaptive Assessment for Cost-Efficient Multi-Agent RAG","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12903","citing_title":"X-MADAM-RAG: Diagnosing and Handling Chinese-English Evidence Conflict in Retrieval-Augmented Generation","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17301","citing_title":"ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27157","citing_title":"Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28017","citing_title":"Can It Reach the Generator? Investigating the Survival of Prompt-Injection Attacks in Realistic RAG Settings","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2603.16091","citing_title":"CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":191,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17301","citing_title":"ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17830","citing_title":"Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents","ref_index":61,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03540","citing_title":"Improving Factuality in LLMs via Inference-Time Knowledge Graph Construction","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2603.16091","citing_title":"CounterRefine: Answer-Conditioned Counterevidence Retrieval for Inference-Time Knowledge Repair in Factual Question Answering","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09874","citing_title":"EgoMemReason: A Memory-Driven Reasoning Benchmark for Long-Horizon Egocentric Video Understanding","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03255","citing_title":"Do LLMs have core beliefs?","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00505","citing_title":"LLM-Oriented Information Retrieval: A Denoising-First Perspective","ref_index":184,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q5AVBUDS5ULTNGOHYOP5LEEVC5","json":"https://pith.science/pith/Q5AVBUDS5ULTNGOHYOP5LEEVC5.json","graph_json":"https://pith.science/api/pith-number/Q5AVBUDS5ULTNGOHYOP5LEEVC5/graph.json","events_json":"https://pith.science/api/pith-number/Q5AVBUDS5ULTNGOHYOP5LEEVC5/events.json","paper":"https://pith.science/paper/Q5AVBUDS"},"agent_actions":{"view_html":"https://pith.science/pith/Q5AVBUDS5ULTNGOHYOP5LEEVC5","download_json":"https://pith.science/pith/Q5AVBUDS5ULTNGOHYOP5LEEVC5.json","view_paper":"https://pith.science/paper/Q5AVBUDS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13079&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5AVBUDS5ULTNGOHYOP5LEEVC5/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5AVBUDS5ULTNGOHYOP5LEEVC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5AVBUDS5ULTNGOHYOP5LEEVC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5AVBUDS5ULTNGOHYOP5LEEVC5/action/storage_attestation","attest_author":"https://pith.science/pith/Q5AVBUDS5ULTNGOHYOP5LEEVC5/action/author_attestation","sign_citation":"https://pith.science/pith/Q5AVBUDS5ULTNGOHYOP5LEEVC5/action/citation_signature","submit_replication":"https://pith.science/pith/Q5AVBUDS5ULTNGOHYOP5LEEVC5/action/replication_record"}},"created_at":"2026-07-05T11:52:20.120593+00:00","updated_at":"2026-07-05T11:52:20.120593+00:00"}