{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NRHLX6GM3DDWBKCK5Y644GL3LN","short_pith_number":"pith:NRHLX6GM","schema_version":"1.0","canonical_sha256":"6c4ebbf8ccd8c760a84aee3dce197b5b7fbdabdf97e67896a0e3ceef8aa6077e","source":{"kind":"arxiv","id":"2510.11483","version":3},"attestation_state":"computed","paper":{"title":"Uncertainty Quantification for Retrieval-Augmented Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Faegheh Hasibi, Hamed Zamani, Heydar Soudani","submitted_at":"2025-10-13T14:55:28Z","abstract_excerpt":"Retrieval-augmented reasoning (RAR) is a recent evolution of retrieval-augmented generation (RAG) that employs multiple reasoning steps for retrieval and generation. While effective for some complex queries, RAR remains vulnerable to errors and misleading outputs. Uncertainty quantification (UQ) offers methods to estimate the confidence of systems' outputs. These methods, however, often handle simple queries with no retrieval or single-step retrieval, without properly handling RAR setup. Accurate estimation of UQ for RAR requires accounting for all sources of uncertainty, including those arisi"},"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":"2510.11483","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-10-13T14:55:28Z","cross_cats_sorted":[],"title_canon_sha256":"3e7f99239cc1a569b667aaab86417745170c9a607e5dc4a44fb0099a7e1e329b","abstract_canon_sha256":"d19ced9864fa7b19430a7ac1d939733b2b13845a7f32c68287dde8d9ee13bb3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T02:04:43.645485Z","signature_b64":"xcZNdzLjwd25pyem9oldeigxGzhY4QEXwbhrCqDJhwyDxByIW7EHlSAKzmlLotP4PreB82KmVDvJWZKSWgGYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6c4ebbf8ccd8c760a84aee3dce197b5b7fbdabdf97e67896a0e3ceef8aa6077e","last_reissued_at":"2026-05-28T02:04:43.644932Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T02:04:43.644932Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty Quantification for Retrieval-Augmented Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Faegheh Hasibi, Hamed Zamani, Heydar Soudani","submitted_at":"2025-10-13T14:55:28Z","abstract_excerpt":"Retrieval-augmented reasoning (RAR) is a recent evolution of retrieval-augmented generation (RAG) that employs multiple reasoning steps for retrieval and generation. While effective for some complex queries, RAR remains vulnerable to errors and misleading outputs. Uncertainty quantification (UQ) offers methods to estimate the confidence of systems' outputs. These methods, however, often handle simple queries with no retrieval or single-step retrieval, without properly handling RAR setup. Accurate estimation of UQ for RAR requires accounting for all sources of uncertainty, including those arisi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.11483","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/2510.11483/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":"2510.11483","created_at":"2026-05-28T02:04:43.645008+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.11483v3","created_at":"2026-05-28T02:04:43.645008+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.11483","created_at":"2026-05-28T02:04:43.645008+00:00"},{"alias_kind":"pith_short_12","alias_value":"NRHLX6GM3DDW","created_at":"2026-05-28T02:04:43.645008+00:00"},{"alias_kind":"pith_short_16","alias_value":"NRHLX6GM3DDWBKCK","created_at":"2026-05-28T02:04:43.645008+00:00"},{"alias_kind":"pith_short_8","alias_value":"NRHLX6GM","created_at":"2026-05-28T02:04:43.645008+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.22728","citing_title":"When Confidence Takes the Wrong Path: Diagnosing Retrieval-State Lock-In in RAG","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2606.07783","citing_title":"Evaluating RAG Reliability under Clean, Misleading, and Mixed Retrieval","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12645","citing_title":"Training LLMs with Reinforcement Learning for Intent-Aware Personalized Question Answering","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13277","citing_title":"Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NRHLX6GM3DDWBKCK5Y644GL3LN","json":"https://pith.science/pith/NRHLX6GM3DDWBKCK5Y644GL3LN.json","graph_json":"https://pith.science/api/pith-number/NRHLX6GM3DDWBKCK5Y644GL3LN/graph.json","events_json":"https://pith.science/api/pith-number/NRHLX6GM3DDWBKCK5Y644GL3LN/events.json","paper":"https://pith.science/paper/NRHLX6GM"},"agent_actions":{"view_html":"https://pith.science/pith/NRHLX6GM3DDWBKCK5Y644GL3LN","download_json":"https://pith.science/pith/NRHLX6GM3DDWBKCK5Y644GL3LN.json","view_paper":"https://pith.science/paper/NRHLX6GM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.11483&json=true","fetch_graph":"https://pith.science/api/pith-number/NRHLX6GM3DDWBKCK5Y644GL3LN/graph.json","fetch_events":"https://pith.science/api/pith-number/NRHLX6GM3DDWBKCK5Y644GL3LN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NRHLX6GM3DDWBKCK5Y644GL3LN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NRHLX6GM3DDWBKCK5Y644GL3LN/action/storage_attestation","attest_author":"https://pith.science/pith/NRHLX6GM3DDWBKCK5Y644GL3LN/action/author_attestation","sign_citation":"https://pith.science/pith/NRHLX6GM3DDWBKCK5Y644GL3LN/action/citation_signature","submit_replication":"https://pith.science/pith/NRHLX6GM3DDWBKCK5Y644GL3LN/action/replication_record"}},"created_at":"2026-05-28T02:04:43.645008+00:00","updated_at":"2026-05-28T02:04:43.645008+00:00"}