{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7QL2LDXCLBGTI3KB3F752RRU6I","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b72e296e3214f6120cbbf964fd537abd3c44ac41ab136811850c173b9dfe1f66","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-10T09:59:43Z","title_canon_sha256":"371dc5dc3f64795385b009f5e051e10a8d3cadf71e7fc648299898a3426b87be"},"schema_version":"1.0","source":{"id":"2604.09174","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.09174","created_at":"2026-05-21T01:04:25Z"},{"alias_kind":"arxiv_version","alias_value":"2604.09174v2","created_at":"2026-05-21T01:04:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09174","created_at":"2026-05-21T01:04:25Z"},{"alias_kind":"pith_short_12","alias_value":"7QL2LDXCLBGT","created_at":"2026-05-21T01:04:25Z"},{"alias_kind":"pith_short_16","alias_value":"7QL2LDXCLBGTI3KB","created_at":"2026-05-21T01:04:25Z"},{"alias_kind":"pith_short_8","alias_value":"7QL2LDXC","created_at":"2026-05-21T01:04:25Z"}],"graph_snapshots":[{"event_id":"sha256:56af459d99176ddfc7aa168d1a83a7df9936572290a593bd3346d17e8e528186","target":"graph","created_at":"2026-05-21T01:04:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Hallucinations in RAG systems arise mainly from how retrieved evidence is integrated during generation rather than from retrieval failures."}],"snapshot_sha256":"f14b32f3698266917a34f5c7875a11c4e27a5bb6b0500ee6e89721a3cca5a613"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0389b5fb664821386237ee476a91e6624e154de8066af1c2f2855a6bbc79be01"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.09174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Markus Schedl, Monorama Swain, Passant Elchafei, Shahed Masoudian","cross_cats":[],"headline":"Hallucinations in RAG systems arise mainly from how retrieved evidence is integrated during generation rather than from retrieval failures.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-10T09:59:43Z","title":"Facet-Level Tracing of Evidence Uncertainty and Hallucination in RAG"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.09174","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T17:56:29.868503Z","id":"0ccf916c-6be8-4b0d-93e5-f558a2699a7b","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Hallucinations in RAG systems arise mainly from how retrieved evidence is integrated during generation rather than from retrieval failures.","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.","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."}},"verdict_id":"0ccf916c-6be8-4b0d-93e5-f558a2699a7b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9be399153492fec8f56a9f8fb911520135efba3b0118903d1235df836cfa990d","target":"record","created_at":"2026-05-21T01:04:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b72e296e3214f6120cbbf964fd537abd3c44ac41ab136811850c173b9dfe1f66","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-10T09:59:43Z","title_canon_sha256":"371dc5dc3f64795385b009f5e051e10a8d3cadf71e7fc648299898a3426b87be"},"schema_version":"1.0","source":{"id":"2604.09174","kind":"arxiv","version":2}},"canonical_sha256":"fc17a58ee2584d346d41d97fdd4634f221b1c5cc9d651b058d3bc2791de1e1e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc17a58ee2584d346d41d97fdd4634f221b1c5cc9d651b058d3bc2791de1e1e5","first_computed_at":"2026-05-21T01:04:25.596868Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:25.596868Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VYxqkjBR7jsYIXwamB8WMcEdoHNbm0kNhs6p9H52vnBOx7j81QSSJlFpmRB+ISjsM/1heyD/eL7OxXQ7Gl59Aw==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:25.597592Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.09174","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9be399153492fec8f56a9f8fb911520135efba3b0118903d1235df836cfa990d","sha256:56af459d99176ddfc7aa168d1a83a7df9936572290a593bd3346d17e8e528186"],"state_sha256":"dcc15f8cf0c5fe51e995c997a7cd93172a9057f1206774c0aca30ac6cbcfc697"}