{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7QL2LDXCLBGTI3KB3F752RRU6I","short_pith_number":"pith:7QL2LDXC","schema_version":"1.0","canonical_sha256":"fc17a58ee2584d346d41d97fdd4634f221b1c5cc9d651b058d3bc2791de1e1e5","source":{"kind":"arxiv","id":"2604.09174","version":2},"attestation_state":"computed","paper":{"title":"Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Hallucinations in RAG systems arise mainly from how retrieved evidence is integrated during generation rather than from retrieval failures.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Markus Schedl, Monorama Swain, Passant Elchafei, Shahed Masoudian","submitted_at":"2026-04-10T09:59:43Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) aims to reduce hallucination by grounding answers in retrieved evidence, yet hallucinated answers remain common even when relevant documents are available. Existing evaluations focus on answer-level or passage-level accuracy, offering limited insight into how evidence is used during generation. In this work, we introduce a facet-level diagnostics framework for QA that decomposes each input question into atomic reasoning facets. For each facet, we assess evidence sufficiency and grounding using a structured Facet x Chunk matrix that combines retrieval releva"},"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":true},"canonical_record":{"source":{"id":"2604.09174","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-10T09:59:43Z","cross_cats_sorted":[],"title_canon_sha256":"371dc5dc3f64795385b009f5e051e10a8d3cadf71e7fc648299898a3426b87be","abstract_canon_sha256":"b72e296e3214f6120cbbf964fd537abd3c44ac41ab136811850c173b9dfe1f66"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:25.597592Z","signature_b64":"VYxqkjBR7jsYIXwamB8WMcEdoHNbm0kNhs6p9H52vnBOx7j81QSSJlFpmRB+ISjsM/1heyD/eL7OxXQ7Gl59Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc17a58ee2584d346d41d97fdd4634f221b1c5cc9d651b058d3bc2791de1e1e5","last_reissued_at":"2026-05-21T01:04:25.596868Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:25.596868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Hallucinations in RAG systems arise mainly from how retrieved evidence is integrated during generation rather than from retrieval failures.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Markus Schedl, Monorama Swain, Passant Elchafei, Shahed Masoudian","submitted_at":"2026-04-10T09:59:43Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) aims to reduce hallucination by grounding answers in retrieved evidence, yet hallucinated answers remain common even when relevant documents are available. Existing evaluations focus on answer-level or passage-level accuracy, offering limited insight into how evidence is used during generation. In this work, we introduce a facet-level diagnostics framework for QA that decomposes each input question into atomic reasoning facets. For each facet, we assess evidence sufficiency and grounding using a structured Facet x Chunk matrix that combines retrieval releva"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"hallucinations in RAG systems are driven less by retrieval accuracy and more by how retrieved evidence is integrated during generation, with facet-level analysis exposing systematic evidence override and misalignment patterns that remain hidden under answer-level evaluation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That automatic decomposition of questions into atomic facets combined with NLI-based faithfulness scoring reliably captures whether and how evidence is used or overridden during generation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Facet-level analysis of RAG systems on medical QA and HotpotQA shows hallucinations stem primarily from evidence integration and override failures during generation, not from retrieval inaccuracy.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Hallucinations in RAG systems arise mainly from how retrieved evidence is integrated during generation rather than from retrieval failures.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"f14b32f3698266917a34f5c7875a11c4e27a5bb6b0500ee6e89721a3cca5a613"},"source":{"id":"2604.09174","kind":"arxiv","version":2},"verdict":{"id":"0ccf916c-6be8-4b0d-93e5-f558a2699a7b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T17:56:29.868503Z","strongest_claim":"hallucinations in RAG systems are driven less by retrieval accuracy and more by how retrieved evidence is integrated during generation, with facet-level analysis exposing systematic evidence override and misalignment patterns that remain hidden under answer-level evaluation.","one_line_summary":"Facet-level analysis of RAG systems on medical QA and HotpotQA shows hallucinations stem primarily from evidence integration and override failures during generation, not from retrieval inaccuracy.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That automatic decomposition of questions into atomic facets combined with NLI-based faithfulness scoring reliably captures whether and how evidence is used or overridden during generation.","pith_extraction_headline":"Hallucinations in RAG systems arise mainly from how retrieved evidence is integrated during generation rather than from retrieval failures."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09174/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":2,"snapshot_sha256":"0389b5fb664821386237ee476a91e6624e154de8066af1c2f2855a6bbc79be01"},"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":"2604.09174","created_at":"2026-05-21T01:04:25.596943+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.09174v2","created_at":"2026-05-21T01:04:25.596943+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09174","created_at":"2026-05-21T01:04:25.596943+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QL2LDXCLBGT","created_at":"2026-05-21T01:04:25.596943+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QL2LDXCLBGTI3KB","created_at":"2026-05-21T01:04:25.596943+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QL2LDXC","created_at":"2026-05-21T01:04:25.596943+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7QL2LDXCLBGTI3KB3F752RRU6I","json":"https://pith.science/pith/7QL2LDXCLBGTI3KB3F752RRU6I.json","graph_json":"https://pith.science/api/pith-number/7QL2LDXCLBGTI3KB3F752RRU6I/graph.json","events_json":"https://pith.science/api/pith-number/7QL2LDXCLBGTI3KB3F752RRU6I/events.json","paper":"https://pith.science/paper/7QL2LDXC"},"agent_actions":{"view_html":"https://pith.science/pith/7QL2LDXCLBGTI3KB3F752RRU6I","download_json":"https://pith.science/pith/7QL2LDXCLBGTI3KB3F752RRU6I.json","view_paper":"https://pith.science/paper/7QL2LDXC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.09174&json=true","fetch_graph":"https://pith.science/api/pith-number/7QL2LDXCLBGTI3KB3F752RRU6I/graph.json","fetch_events":"https://pith.science/api/pith-number/7QL2LDXCLBGTI3KB3F752RRU6I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QL2LDXCLBGTI3KB3F752RRU6I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QL2LDXCLBGTI3KB3F752RRU6I/action/storage_attestation","attest_author":"https://pith.science/pith/7QL2LDXCLBGTI3KB3F752RRU6I/action/author_attestation","sign_citation":"https://pith.science/pith/7QL2LDXCLBGTI3KB3F752RRU6I/action/citation_signature","submit_replication":"https://pith.science/pith/7QL2LDXCLBGTI3KB3F752RRU6I/action/replication_record"}},"created_at":"2026-05-21T01:04:25.596943+00:00","updated_at":"2026-05-21T01:04:25.596943+00:00"}