Papers

2026.09.25 Pauper Consensus: Two Pre-Registered LLM StudiesA jury of twelve 3–4B local models votes on 8,000 claims from 200 news articles, aggregated by Dawid–Skene with frozen calibration maps. The instrument is the object under test.

2026.08.19 Do Instructional Fingerprints Produce Stable Expert-Routing Signatures in a Mixture-of-Experts Model?A controlled negative: fingerprints implanted in Qwen1.5-MoE-A2.7B shift expert routing but no stable trigger signature emerges above matched nulls.

2026.08.08 Measured Pruning Damage Depends on the Evaluation Corpus: A Renaming Control for Mixture-of-Experts Expert PruningExpert-pruning damage on code depends on the eval corpus: a renaming control on CPython stdlib moves reported damage 1.6x at constant program structure.