{"paper":{"title":"DCD: Domain-Oriented Design for Controlled Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"The DCD architecture uses hierarchical domain-collection-document decomposition and multi-stage routing to progressively restrict retrieval and generation scopes in RAG systems.","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Igor Reshetnikov, Maksim Maksimov, Nikita Belov, Nikita Miteyko, Valerii Kovalskii","submitted_at":"2026-04-08T20:47:51Z","abstract_excerpt":"Retrieval-Augmented Generation (RAG) is widely used to ground large language models in external knowledge sources. However, when applied to heterogeneous corpora and multi-step queries, Naive RAG pipelines often degrade in quality due to flat knowledge representations and the absence of explicit workflows. In this work, we introduce DCD (Domain-Collection-Document), a domain-oriented design to structure knowledge and control query processing in RAG systems without modifying the underlying language model. The proposed approach relies on a hierarchical decomposition of the information space and "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The DCD architecture enables progressive restriction of both retrieval and generation scopes through hierarchical decomposition and multi-stage routing based on structured model outputs, improving robustness, factual accuracy, and answer relevance in applied RAG scenarios on heterogeneous corpora.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the hierarchical domain-collection-document decomposition and the multi-stage routing decisions derived from structured model outputs will reliably reduce scope without introducing new failure modes or excessive manual domain engineering on real heterogeneous data.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DCD introduces a domain-oriented hierarchical decomposition and staged routing workflow that restricts retrieval and generation scopes progressively to improve robustness and factual accuracy in RAG on complex, multi-source queries.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The DCD architecture uses hierarchical domain-collection-document decomposition and multi-stage routing to progressively restrict retrieval and generation scopes in RAG systems.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"a066e6d7d01908e540152f15e93a4e44d1cf55a3a29d53a715d712761782578f"},"source":{"id":"2604.07590","kind":"arxiv","version":2},"verdict":{"id":"2c2ee343-d979-457b-8a24-425253aa5e8a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T16:58:00.833676Z","strongest_claim":"The DCD architecture enables progressive restriction of both retrieval and generation scopes through hierarchical decomposition and multi-stage routing based on structured model outputs, improving robustness, factual accuracy, and answer relevance in applied RAG scenarios on heterogeneous corpora.","one_line_summary":"DCD introduces a domain-oriented hierarchical decomposition and staged routing workflow that restricts retrieval and generation scopes progressively to improve robustness and factual accuracy in RAG on complex, multi-source queries.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the hierarchical domain-collection-document decomposition and the multi-stage routing decisions derived from structured model outputs will reliably reduce scope without introducing new failure modes or excessive manual domain engineering on real heterogeneous data.","pith_extraction_headline":"The DCD architecture uses hierarchical domain-collection-document decomposition and multi-stage routing to progressively restrict retrieval and generation scopes in RAG systems."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.07590/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"}