https://derekwang2002.github.io/ai-intelligence/en/projects/silent-cue-loss/ Material changes in AI models, agents, engineering and infrastructure, with primary sources and recommendations. en Mon, 02 Nov 2026 16:56:00 GMT https://derekwang2002.github.io/ai-intelligence/en/events/ev-20261021-09/ ev-20261021-09-published Thu, 22 Oct 2026 16:37:30 GMT New WATCH <p>A study of 76 real policy documents finds that common ingestion pipelines drop meaning encoded in highlights, colour and other formatting. A deterministic OOXML scorer reports micro-F1 falling from 0.690 with preserved cues to 0.150 with Docling and 0.075 with plain text across six answering models. The paper provides a concrete failure mode but no public code or independent reproduction.</p><p>Recommendation: WATCH</p><p>Sources: <a href="https://arxiv.org/abs/2610.30026">Silent Cue Loss paper</a></p>