Two locked tests of phase-structure features for transition prediction
Summary
This paper describes two pre-specified empirical tests to evaluate whether phase-derived features improve prediction accuracy for commitment or contradiction endpoints, but results show no significant improvement over baseline models.
View Cached Full Text
Cached at: 09/02/26, 05:50 AM
# Two locked tests of phase-structure features for transition prediction Source: [https://arxiv.org/abs/2609.00335](https://arxiv.org/abs/2609.00335) [View PDF](https://arxiv.org/pdf/2609.00335) > Abstract:A published theoretical account of phase structure in rotary attention was subjected to two pre\-specified empirical tests of whether phase\-derived features improve prediction of a commitment or contradiction endpoint over a baseline that does not receive those features\. Study 1 froze a contradiction\-category pipeline and scored a sealed primary comparison of PC\-2 against baseline\. On 1,136 eligible cases the paired AUROC difference was \+0\.00087\. The 99% interval included zero, and the difference did not reach the pre\-specified threshold of \+0\.05\. Advancement was not passed\. Study 2 developed fifteen layer treatments on open blocks b0\-b4 only \(1,415 transitions, 20x5 grouped folds\)\. A locked conjunctive rule required a positive PC\-2 mean\-repeat increment, a positive increment on at least four of five seed blocks, and a positive mean of those five differences\. No treatment advanced\. The official selection is null\. The theoretical paper is not withdrawn\. The extra ranking lift was not found under the rules locked in advance\. ## Submission history From: Abraham Chachamovits \[[view email](https://arxiv.org/show-email/8f64906b/2609.00335)\] **\[v1\]**Mon, 31 Aug 2026 20:29:18 UTC \(298 KB\)
Similar Articles
Probing Minimalist Phase Structure in LLMs: What Universal Dependencies Cannot Represent
This paper investigates whether large language models encode syntactic abstractions like phase boundaries that are not captured by Universal Dependencies, using structural probes on wh-movement stimuli with invariant UD distances, finding evidence across 13 LLMs for phase-structure representations that are causally active.
The Spectral Geometry of Thought: Phase Transitions, Instruction Reversal, Token-Level Dynamics, and Perfect Correctness Prediction in How Transformers Reason
A comprehensive spectral analysis across 11 LLMs revealing that transformers exhibit phase transitions in hidden activation spaces during reasoning versus factual recall, with seven fundamental phenomena including spectral compression, instruction-tuning reversal, and perfect correctness prediction (AUC=1.0) based solely on spectral properties.
Phase Structure in Rotary Attention: A Spectral Framework for Semantic Continuity and Execution-Boundary Governance
This paper develops a spectral framework for analyzing rotary phase alignment, semantic continuity, and representation drift in transformer language models, proposing a bounded spectral method and distinguishing internal coherence from execution-boundary governance.
Dimension-Level Intent Fidelity Evaluation for Large Language Models: Evidence from Structured Prompt Ablation
This paper introduces a dimension-level evaluation method for measuring intent fidelity in large language models using structured prompt ablation.
Beyond Feature Importance: A Comparative Analysis of Pattern Detection Methods in Cluster Interpretation
This paper presents a comparative evaluation of post-hoc analysis methods (Random Forest surrogate, LIME, PCA) for detecting structured patterns in clustering results, using synthetic datasets with injected patterns. It finds that none of the methods consistently detects all pattern types, highlighting a gap in existing explainability tools.