{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FUMV3LAZ2R2BCYUSMQR7MAWGCB","short_pith_number":"pith:FUMV3LAZ","schema_version":"1.0","canonical_sha256":"2d195dac19d4741162926423f602c6105eb6dd35bc251cc13e28078752fc86da","source":{"kind":"arxiv","id":"2410.02719","version":1},"attestation_state":"computed","paper":{"title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengming Li, Chuanyang Zheng, Fanghua Ye, Jianqiao Lu, Jing Xiong, Lingpeng Kong, Ngai Wong, Xiaodan Liang, Xun Wu, Zhenan Sun, Zhongwei Wan, Zixuan Li","submitted_at":"2024-10-03T17:39:38Z","abstract_excerpt":"We present UncertaintyRAG, a novel approach for long-context Retrieval-Augmented Generation (RAG) that utilizes Signal-to-Noise Ratio (SNR)-based span uncertainty to estimate similarity between text chunks. This span uncertainty enhances model calibration, improving robustness and mitigating semantic inconsistencies introduced by random chunking. Leveraging this insight, we propose an efficient unsupervised learning technique to train the retrieval model, alongside an effective data sampling and scaling strategy. UncertaintyRAG outperforms baselines by 2.03% on LLaMA-2-7B, achieving state-of-t"},"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":"2410.02719","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-03T17:39:38Z","cross_cats_sorted":[],"title_canon_sha256":"8eaa2b58bd3413abfa183e216e346ac8dbc484dd732202507c533f2c3d17e655","abstract_canon_sha256":"afd35cec12f40cee00fa343aef0f64ebfa3f2bdfd18e4bb59a7175a70ae29f2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:24.401697Z","signature_b64":"tpiYJH5CJHALiwKOsuUEQ4lU6B8af1t1vaJzXW8XoB0C4nw9Lhb4tbPfDX5WOPh1GNOJcPBl5QWDQvZ62W6eDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d195dac19d4741162926423f602c6105eb6dd35bc251cc13e28078752fc86da","last_reissued_at":"2026-07-05T09:15:24.401219Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:24.401219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UncertaintyRAG: Span-Level Uncertainty Enhanced Long-Context Modeling for Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengming Li, Chuanyang Zheng, Fanghua Ye, Jianqiao Lu, Jing Xiong, Lingpeng Kong, Ngai Wong, Xiaodan Liang, Xun Wu, Zhenan Sun, Zhongwei Wan, Zixuan Li","submitted_at":"2024-10-03T17:39:38Z","abstract_excerpt":"We present UncertaintyRAG, a novel approach for long-context Retrieval-Augmented Generation (RAG) that utilizes Signal-to-Noise Ratio (SNR)-based span uncertainty to estimate similarity between text chunks. This span uncertainty enhances model calibration, improving robustness and mitigating semantic inconsistencies introduced by random chunking. Leveraging this insight, we propose an efficient unsupervised learning technique to train the retrieval model, alongside an effective data sampling and scaling strategy. UncertaintyRAG outperforms baselines by 2.03% on LLaMA-2-7B, achieving state-of-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02719","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/2410.02719/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":"2410.02719","created_at":"2026-07-05T09:15:24.401271+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02719v1","created_at":"2026-07-05T09:15:24.401271+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02719","created_at":"2026-07-05T09:15:24.401271+00:00"},{"alias_kind":"pith_short_12","alias_value":"FUMV3LAZ2R2B","created_at":"2026-07-05T09:15:24.401271+00:00"},{"alias_kind":"pith_short_16","alias_value":"FUMV3LAZ2R2BCYUS","created_at":"2026-07-05T09:15:24.401271+00:00"},{"alias_kind":"pith_short_8","alias_value":"FUMV3LAZ","created_at":"2026-07-05T09:15:24.401271+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05721","citing_title":"SpanUQ: Span-Level Uncertainty Quantification for Large Language Model Generation","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24849","citing_title":"IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22728","citing_title":"When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23505","citing_title":"Uncertainty Propagation in LLM-Based Systems","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05244","citing_title":"Towards Dependable Retrieval-Augmented Generation Using Factual Confidence Prediction","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FUMV3LAZ2R2BCYUSMQR7MAWGCB","json":"https://pith.science/pith/FUMV3LAZ2R2BCYUSMQR7MAWGCB.json","graph_json":"https://pith.science/api/pith-number/FUMV3LAZ2R2BCYUSMQR7MAWGCB/graph.json","events_json":"https://pith.science/api/pith-number/FUMV3LAZ2R2BCYUSMQR7MAWGCB/events.json","paper":"https://pith.science/paper/FUMV3LAZ"},"agent_actions":{"view_html":"https://pith.science/pith/FUMV3LAZ2R2BCYUSMQR7MAWGCB","download_json":"https://pith.science/pith/FUMV3LAZ2R2BCYUSMQR7MAWGCB.json","view_paper":"https://pith.science/paper/FUMV3LAZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02719&json=true","fetch_graph":"https://pith.science/api/pith-number/FUMV3LAZ2R2BCYUSMQR7MAWGCB/graph.json","fetch_events":"https://pith.science/api/pith-number/FUMV3LAZ2R2BCYUSMQR7MAWGCB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FUMV3LAZ2R2BCYUSMQR7MAWGCB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FUMV3LAZ2R2BCYUSMQR7MAWGCB/action/storage_attestation","attest_author":"https://pith.science/pith/FUMV3LAZ2R2BCYUSMQR7MAWGCB/action/author_attestation","sign_citation":"https://pith.science/pith/FUMV3LAZ2R2BCYUSMQR7MAWGCB/action/citation_signature","submit_replication":"https://pith.science/pith/FUMV3LAZ2R2BCYUSMQR7MAWGCB/action/replication_record"}},"created_at":"2026-07-05T09:15:24.401271+00:00","updated_at":"2026-07-05T09:15:24.401271+00:00"}