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 The theoretical paper is not withdrawn.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.
Behavioural auditing asks whether a language model behaves as it claims, but detection scores are reported without separating two targets: whether a reply was produced under a behaviour-inducing condition (exposure) and whether the behaviour surfaced in it (manifestation). Scoring a compact 146-million-parameter auditor's frozen-representation read-out and a frontier judge against each label on the identical 720 replies, the gap between the instruments moves by roughly 0.2 AUROC when the target changes. Under the judge's deployed interface, a single verdict, the ranking reverses: the auditor leads on exposure, 0.804 against 0.718, and trails on manifestation, 0.690 against 0.811. Matching the output resolution from either direction, by asking the judge a target-specific question answered with a continuous confidence score or by thresholding the auditor's read-out, removes the reversal but not the interaction, which excludes zero at all three resolutions (0.207, 0.237 and 0.169). The target governs how far apart the instruments are; the interface governs whether that distance changes their order. The auditor's hyperbolic geometry confers no advantage here. A single behavioural-detection AUROC is under-specified: such claims are comparable only when they state the estimand, the evaluator, and its output interface.
Zhengchi Ma, Pengfei Lyu, Anru R. Zhangstat.ML cs.LG
Synthetic data augmentation is widely used to mitigate class imbalance, but its theoretical effects on score-based classification remain poorly understood. This paper develops a framework for characterizing when synthetic minority augmentation can improve threshold-integrated and threshold-optimized metrics, including AUROC, AUPRC, best-threshold balanced accuracy, and best-threshold \(\F_1\) score. We separate the effect of augmentation into two components: a change in effective class weighting and a discrepancy between the synthetic and true minority distributions. Under well-specified score models, the raw estimator already targets the likelihood-ratio ordering, which is population-optimal for the metrics considered. Consequently, augmentation cannot provide a fundamental population-level improvement beyond possible finite-sample variance reduction, and may introduce additional bias through synthetic distributional error. We further establish minimax lower bounds showing that the raw estimator already achieves the optimal metric-regret rate in the well-specified regime. Under misspecification, however, augmentation can play a qualitatively different role: by changing the effective class balance, it can alter the restricted-class projection and correct ranking errors induced by the raw imbalanced objective. We provide explicit improvement bounds quantifying the roles of approximation error, finite-sample estimation error, and synthetic distributional error. Simulation studies corroborate the theory, demonstrating limited gains under well-specification and nontrivial but nonmonotone improvements under misspecification.