A Calibrated Test of Internal Action Maps: State Signals Without Global Affine Closure
arXiv cs.AIen
arXiv:2608.13626v1 Announce Type: new Abstract: A hidden state signal can be decodable or causally usable without supporting a reusable action map. We test whether action maps fitted without a source reach its natural post-action activation and compose. We organize the tests as an evidence lattice and validate the geometric branch on a known affine S_5 carrier: all held-source folds pass one-step, composition, inverse, decoding, and commutativity gates. Structured curvature and held-domain conjugacy raise error monotonically, but only 23/30 strongest cells flip a closure gate, bounding rather than universalizing calibration. In post-trained Qwen/Qwen3-4B, frozen final-token h28 affine maps h
This is a short summary published by AI Global Wire. The full article is owned and hosted by arXiv cs.AI — open it there to read it in full.
Read the full story at arXiv cs.AI- Forskning
Related AI news
- Qwen 3.8 27B shows a 17GB open-weight general purpose model can have long context, effective tool calling, strong vision ability, and competent code generation (Simon Willison/Simon Willison's Weblog)Techmeme · August 17, 2026
- Modular Cognitive Architecture Emerges in Large Language ModelsarXiv cs.AI · August 17, 2026
- No Universal Signal Predicts Sample-Level LLM Regression under Version UpdatesarXiv cs.AI · August 17, 2026
- Cross-Disciplinary Taxonomy and Modeling of Misunderstanding Generation, Amplification, and Detection, from Pragmatics to AI AgentsarXiv cs.AI · August 17, 2026
- Reward Machines for Signal Temporal LogicarXiv cs.AI · August 17, 2026
- Second Thought: Reasoning in Parallel as LLM Agents Act and ObservearXiv cs.AI · August 17, 2026