{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:GOHVRAXPIZBUIBZZI6ATR7QTWM","short_pith_number":"pith:GOHVRAXP","schema_version":"1.0","canonical_sha256":"338f5882ef4643440739478138fe13b32e109747cffcbf96e267f42fd05ff130","source":{"kind":"arxiv","id":"2608.02011","version":1},"attestation_state":"computed","paper":{"title":"Before Reasoning Fails: Pre-Evidence Procedural Failures in Agentic RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daeyoung Roh, Donghee Han","submitted_at":"2026-08-03T10:09:19Z","abstract_excerpt":"Agentic retrieval-augmented generation (RAG) systems can fail before evidence-conditioned reasoning is tested: an agent may retrieve candidate snippets but finalize without inspecting them. We study this failure mode as a procedural property of the agent trajectory, decomposing wrong answers into pre-evidence discipline failures and post-gold-read failures using saved tool-call traces, retrieved evidence, read passages, and final answers. Across 12,000 paired trajectories on HotpotQA, 2WikiMultiHopQA, and MuSiQue, the two failure types are largely non-redundant: the both-trigger rate is in [11"},"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":"2608.02011","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-03T10:09:19Z","cross_cats_sorted":[],"title_canon_sha256":"8905534dc9ad799935147befcc7f46dae9329fde9fa2537542d83940f92ae7cf","abstract_canon_sha256":"87ab966e1435336d64378f4b4a303df702529af64bafb2ad5264c607c36730b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:10:29.701722Z","signature_b64":"sg3zfawSbkWI7rh31ti7LcwLJocfQCXZTdOH5PqVJOm3fLfotMWL5Cfa0Bj3I3EUvhqO5erGGjZm9e2g4Qu3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"338f5882ef4643440739478138fe13b32e109747cffcbf96e267f42fd05ff130","last_reissued_at":"2026-08-04T02:10:29.700130Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:10:29.700130Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Before Reasoning Fails: Pre-Evidence Procedural Failures in Agentic RAG","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Daeyoung Roh, Donghee Han","submitted_at":"2026-08-03T10:09:19Z","abstract_excerpt":"Agentic retrieval-augmented generation (RAG) systems can fail before evidence-conditioned reasoning is tested: an agent may retrieve candidate snippets but finalize without inspecting them. We study this failure mode as a procedural property of the agent trajectory, decomposing wrong answers into pre-evidence discipline failures and post-gold-read failures using saved tool-call traces, retrieved evidence, read passages, and final answers. Across 12,000 paired trajectories on HotpotQA, 2WikiMultiHopQA, and MuSiQue, the two failure types are largely non-redundant: the both-trigger rate is in [11"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.02011","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/2608.02011/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":"2608.02011","created_at":"2026-08-04T02:10:29.701730+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.02011v1","created_at":"2026-08-04T02:10:29.701730+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.02011","created_at":"2026-08-04T02:10:29.701730+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOHVRAXPIZBU","created_at":"2026-08-04T02:10:29.701730+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOHVRAXPIZBUIBZZ","created_at":"2026-08-04T02:10:29.701730+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOHVRAXP","created_at":"2026-08-04T02:10:29.701730+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOHVRAXPIZBUIBZZI6ATR7QTWM","json":"https://pith.science/pith/GOHVRAXPIZBUIBZZI6ATR7QTWM.json","graph_json":"https://pith.science/api/pith-number/GOHVRAXPIZBUIBZZI6ATR7QTWM/graph.json","events_json":"https://pith.science/api/pith-number/GOHVRAXPIZBUIBZZI6ATR7QTWM/events.json","paper":"https://pith.science/paper/GOHVRAXP"},"agent_actions":{"view_html":"https://pith.science/pith/GOHVRAXPIZBUIBZZI6ATR7QTWM","download_json":"https://pith.science/pith/GOHVRAXPIZBUIBZZI6ATR7QTWM.json","view_paper":"https://pith.science/paper/GOHVRAXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.02011&json=true","fetch_graph":"https://pith.science/api/pith-number/GOHVRAXPIZBUIBZZI6ATR7QTWM/graph.json","fetch_events":"https://pith.science/api/pith-number/GOHVRAXPIZBUIBZZI6ATR7QTWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOHVRAXPIZBUIBZZI6ATR7QTWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOHVRAXPIZBUIBZZI6ATR7QTWM/action/storage_attestation","attest_author":"https://pith.science/pith/GOHVRAXPIZBUIBZZI6ATR7QTWM/action/author_attestation","sign_citation":"https://pith.science/pith/GOHVRAXPIZBUIBZZI6ATR7QTWM/action/citation_signature","submit_replication":"https://pith.science/pith/GOHVRAXPIZBUIBZZI6ATR7QTWM/action/replication_record"}},"created_at":"2026-08-04T02:10:29.701730+00:00","updated_at":"2026-08-04T02:10:29.701730+00:00"}