Figshare
open access
CC BY 4.0
<b>Auditing the provenance evidence gap in structured document retrieval augmented generation</b>
Record-level retrieval credit can overstate the content delivered to a generator when relevance labels are transferred to fragments. We audit target-expression loss among credited retrievals, Γ = P(K = 0 | C = 1), while separating record coverage, full-record carry, lexical retention an
Conceptio Open Archive
Analyze & explore related research in Conceptio
Connect this record directly into your research workflow or AI agent. Explore citations across open repositories, query full text, and export structured proof bundles.
2026-11-04T09:46:57Z https://api.figshare.com/v2/oai The request includes illegal arguments, is missing required arguments, includes a repeated argument, or values for arguments have an illegal syntax.
Related documents
- RCER: Reconstructing Cross-Evidence Relations for Iterative Retrieval-Augmented Generation#1345221
- RAGSieve: Self-Referenced Local Contrast for Knowledge-Poison Detection in Retrieval-Augmented Generation#985209
- From Association to Causation: Improving Retrieval Precision of Retrieval-Augmented Generation via Causal Relations and an Attention Mechanism#1534137
- Retrieval-Augmented Generation Must Move Beyond Factual Grounding to Represent Diverse Opinions#1198902
- Socrates-RAG: Premise-Directed Inquiry against Coordinated Evidence Poisoning#1130615
Record · ID 1533326 · SHA-256 175e7e2b5386f9ce
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Retrieved via Conceptio: every document is proof-bundled with source, license, and retrieval metadata.
Bring this data into your agent: Connect via MCP or API · 20 free credits to start · no card required
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive
Read the Docs → · View CLI source on GitHub · Conceptio Open Knowledge Archive