AI & ML
Claim-Gated Source-Risk Auditing for Generative Search
arXiv cs.IR0 views
arXiv:2609.29145v2 Announce Type: replace-cross Abstract: A generative search answer can cite a supported passage yet omit a source relationship that changes its interpretation. We specify a claim-gated audit of the query-source-answer tuple. An omission is resolved only when relationship evidence, answer adoption, materiality, and disclosure are all observed; incomplete evidence remains unresolved rather than being treated as independence. The specification separates this endpoint from citation support and review priority, and binds decisions to versioned evidence spans. A reference checker makes the record contract executable. On an exhaustive synthetic suite, it reproduces all 81 three-state predicate combinations and rejects 192 deliberately malformed records. Common-guard baselines and predicate ablations isolate endpoint logic from missing-evidence handling, while controlled transitions check support separation and evidence removal. These are finite contract-conformance results, not detector accuracy or evidence of improved user outcomes. We define the independent annotation, held-out evaluation, and paired utility tests still required to establish semantic validity and deployment benefit.
Source:https://arxiv.org/abs/2609.29145PreviousTrust, but Validate the Instrument: Auditing AI-Generated RTL Verification Plans on Authored Security-Regression ProxiesNextQuaternion Gaussian Probes for Tensor Frobenius-Norm Estimation
Related posts
Hybrid retrieval with reciprocal rank fusion: notes from a RAG prototype
0dev.to
It is in co-creating, together. As humans do.
0dev.to
C64 Basic Dungeon Crawler: Stairs, Levels and Levelling Up (Part 11)
0Hacker News
Anthropic's internal AI use, at retail prices, now exceeds its employee pay
0Hacker News
Launch HN: Momentic (YC W24) – Agents that catch bugs by using your app
0Hacker News

Behavioral Design Unpacked: Nudges, Funnels & Persuasion | UX Unpacked #3
0dev.to UX