{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KX22QOPDYIJANPOUB4MCBFSQNH","short_pith_number":"pith:KX22QOPD","schema_version":"1.0","canonical_sha256":"55f5a839e3c21206bdd40f1820965069ec405284b4cc23cb912c5d44b46d3af3","source":{"kind":"arxiv","id":"2604.25928","version":2},"attestation_state":"computed","paper":{"title":"CogRAG: Tackling Heterogeneous Cognitive Demands in RAG via Stratified Retrieval and Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CogRAG+ separates retrieval from reasoning in LLMs using dual paths and structured templates to fix knowledge gaps on professional exams.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kui Su, Xudong Wang, Zhaoyan Ming, Zilong Wang","submitted_at":"2026-04-01T13:31:12Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) frameworks typically process all queries through a one-size-fits-all pipeline, ignoring the heterogeneous cognitive demands of different tasks. This cognitive-blind approach causes two failure modes: cascading errors when low-level factual gaps trigger hallucinated reasoning, and reasoning-answer inconsistency in higher-order analytical tasks. We introduce CogRAG, a training-free, domain-agnostic framework that tackles these heterogeneous cognitive demands via stratified retrieval and reasoning. Inspired by Bloom's Taxonomy, CogRAG uses the predicted cognit"},"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":"2604.25928","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-04-01T13:31:12Z","cross_cats_sorted":[],"title_canon_sha256":"9cce5771b904db0a97992173e7393cfc956537ed62f258162045cbb829a4f483","abstract_canon_sha256":"5a3ef9266d69cd2cef9046f9e9820edb0e3578e4f61a6d2c56fbc8e01a1b5c8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-03T01:05:14.150929Z","signature_b64":"by8dfuzV4hJ/uJTBYzDTLhey7Vnz+9AvFCx6oasPuQbNrPtBtP4atYfPS09Oc9jXdifR938P70cjR8RQhh30DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"55f5a839e3c21206bdd40f1820965069ec405284b4cc23cb912c5d44b46d3af3","last_reissued_at":"2026-06-03T01:05:14.150446Z","signature_status":"signed_v1","first_computed_at":"2026-06-03T01:05:14.150446Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CogRAG: Tackling Heterogeneous Cognitive Demands in RAG via Stratified Retrieval and Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"CogRAG+ separates retrieval from reasoning in LLMs using dual paths and structured templates to fix knowledge gaps on professional exams.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kui Su, Xudong Wang, Zhaoyan Ming, Zilong Wang","submitted_at":"2026-04-01T13:31:12Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) frameworks typically process all queries through a one-size-fits-all pipeline, ignoring the heterogeneous cognitive demands of different tasks. This cognitive-blind approach causes two failure modes: cascading errors when low-level factual gaps trigger hallucinated reasoning, and reasoning-answer inconsistency in higher-order analytical tasks. We introduce CogRAG, a training-free, domain-agnostic framework that tackles these heterogeneous cognitive demands via stratified retrieval and reasoning. Inspired by Bloom's Taxonomy, CogRAG uses the predicted cognit"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on two representative models, Qwen3-8B and Llama3.1-8B, show that CogRAG+ consistently outperforms general-purpose models and standard RAG methods on the Registered Dietitian qualification exam. In single-question mode, it raises overall accuracy to 85.8% for Qwen3-8B and 60.3% for Llama3.1-8B, with clear gains over vanilla baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that a judge-driven dual-path retrieval strategy can reliably identify and supply missing foundational knowledge without domain-specific tuning or additional training data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"CogRAG+ raises LLM accuracy on a dietitian exam to 85.8% by using dual-path retrieval and structured reasoning templates.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"CogRAG+ separates retrieval from reasoning in LLMs using dual paths and structured templates to fix knowledge gaps on professional exams.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"31c80d4001398e2cebb6dd379eeb4b14d9922f9e5d72a8c5e52c55572ae9d3e6"},"source":{"id":"2604.25928","kind":"arxiv","version":2},"verdict":{"id":"cda35c8d-83bd-4227-b831-0118372c87fa","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-13T22:25:57.600245Z","strongest_claim":"Experiments on two representative models, Qwen3-8B and Llama3.1-8B, show that CogRAG+ consistently outperforms general-purpose models and standard RAG methods on the Registered Dietitian qualification exam. In single-question mode, it raises overall accuracy to 85.8% for Qwen3-8B and 60.3% for Llama3.1-8B, with clear gains over vanilla baselines.","one_line_summary":"CogRAG+ raises LLM accuracy on a dietitian exam to 85.8% by using dual-path retrieval and structured reasoning templates.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that a judge-driven dual-path retrieval strategy can reliably identify and supply missing foundational knowledge without domain-specific tuning or additional training data.","pith_extraction_headline":"CogRAG+ separates retrieval from reasoning in LLMs using dual paths and structured templates to fix knowledge gaps on professional exams."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.25928/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":1,"snapshot_sha256":"5ae7427c5dec90fa7a133fe61c0eb10fc6d6deb82aacadf975738200f7c5b8b6"},"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":"2604.25928","created_at":"2026-06-03T01:05:14.150509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.25928v2","created_at":"2026-06-03T01:05:14.150509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.25928","created_at":"2026-06-03T01:05:14.150509+00:00"},{"alias_kind":"pith_short_12","alias_value":"KX22QOPDYIJA","created_at":"2026-06-03T01:05:14.150509+00:00"},{"alias_kind":"pith_short_16","alias_value":"KX22QOPDYIJANPOU","created_at":"2026-06-03T01:05:14.150509+00:00"},{"alias_kind":"pith_short_8","alias_value":"KX22QOPD","created_at":"2026-06-03T01:05:14.150509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KX22QOPDYIJANPOUB4MCBFSQNH","json":"https://pith.science/pith/KX22QOPDYIJANPOUB4MCBFSQNH.json","graph_json":"https://pith.science/api/pith-number/KX22QOPDYIJANPOUB4MCBFSQNH/graph.json","events_json":"https://pith.science/api/pith-number/KX22QOPDYIJANPOUB4MCBFSQNH/events.json","paper":"https://pith.science/paper/KX22QOPD"},"agent_actions":{"view_html":"https://pith.science/pith/KX22QOPDYIJANPOUB4MCBFSQNH","download_json":"https://pith.science/pith/KX22QOPDYIJANPOUB4MCBFSQNH.json","view_paper":"https://pith.science/paper/KX22QOPD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.25928&json=true","fetch_graph":"https://pith.science/api/pith-number/KX22QOPDYIJANPOUB4MCBFSQNH/graph.json","fetch_events":"https://pith.science/api/pith-number/KX22QOPDYIJANPOUB4MCBFSQNH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KX22QOPDYIJANPOUB4MCBFSQNH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KX22QOPDYIJANPOUB4MCBFSQNH/action/storage_attestation","attest_author":"https://pith.science/pith/KX22QOPDYIJANPOUB4MCBFSQNH/action/author_attestation","sign_citation":"https://pith.science/pith/KX22QOPDYIJANPOUB4MCBFSQNH/action/citation_signature","submit_replication":"https://pith.science/pith/KX22QOPDYIJANPOUB4MCBFSQNH/action/replication_record"}},"created_at":"2026-06-03T01:05:14.150509+00:00","updated_at":"2026-06-03T01:05:14.150509+00:00"}