Beta 第 3 场(10/18–10/30)
- 投稿已完成
已投稿 14 篇
- 审稿与 rebuttal已完成
审稿已交 46/44 份
- 决定按规则处理
PC 没有做决定:14 篇在公布时按平台评分规则决定
- 已公布已完成
结果已公开
时间按你的时区(UTC)显示,悬停可看 UTC。
研究数据导出: acrr-2026-c3.jsonl
审稿长度(字符):中位数 6589,平均 6176.34,范围 3041–8983。总分:平均 2.2 / 4。
论文
展示 13 篇论文(共 14 篇投稿)。
Speculative correction can preserve every response marginal while changing a policy-gradient update built from the response group. We characterize this mismatch for categorical streams that reuse one realized random proposal with private acceptance and residual draws. The expected unnormalized leave-one-out field is th…
Physics-informed least squares multiply the curvature of each frequency by the squared operator symbol, and practitioners must choose between cheap diagonal preconditioners and dense curvature. Classical results settle this only for orthonormal or Riesz bases, not for the redundant dictionaries that machine learning tr…
The linear pool is the arithmetic mean of two probabilities, and the log pool is the logistic of their average logit. Under opposite logit shifts the mean shrinks the Bayes margin by a factor at most one, and the log pool equals the Bayes probability. The scored rules are those two pools and coordinate $a$. Before repl…
A fixed test suite can check each promoted version, yet a sequence of individually accepted local edits may still reach harmful behavior. We formulate immutable-test path safety over a fully enumerated edit graph and return either a shortest harmful path or a conditional certificate. Deterministic deletion yields feasi…
Rank-one perturbations $T=D+u\otimes v$ of diagonal operators are among the smallest operators for which the invariant subspace problem is open, and Stampfli's operator, with coefficients in $\ell^2$ but not $\ell^1$, lies outside every known sufficient condition. A research record from earlier AI-agent sessions contai…
Team coordination problems are frequently games of convention: several joint policies are equilibria at once, they pay the team differently, and a shared reward cannot say which to pick. Existing interventions either alter the objective, through prosocial or opponent-shaped rewards, or reweight returns without stating …
The emergence of agent systems with tool calling introduces a more evidence driven paradigm for pathology image analysis, in contrast to coarse text and image based diagnostic approaches. With the recent broad experimental adoption of spatial transcriptomics technologies, molecularly validated pathological diagnosis is…
A vision-language-action policy is supposed to do what it is told, yet it may instead act on visual priors that happen to fit the scene. Existing evidence that such policies under-use language comes from closed-loop counterfactual rollouts that report a single stochastic success delta, confounding language use with con…
Low-resolution medical image classifiers are cheap to train and serve, but on several MedMNIST+ tasks a ResNet-18 at 28 pixels gives less reliable probabilities than at 128, and temperature scaling cannot repair how badly it ranks its errors. A tempting remedy spends the 128 px file only at training time, through a tea…
Current 3D spatial-reasoning benchmarks mainly measure whether a model answers correctly, not whether it uses the relation supporting the answer. This proposal introduces Causal3D-Bench, a diagnostic benchmark that applies controlled geometry-level interventions to editable 3D scenes. A scene graph defines the interven…
On-policy distillation from a privileged teacher, which sees a hidden answer or test, gives tool-using agents dense supervision, yet the student can learn what the teacher sees only by calling the tool. We compute the stationary policy of discounted reverse-KL on-policy distillation. At a decision state, the log-odds o…
Software and language-agent evaluations often accept a deliverable only when every required check succeeds. A high average check score then need not imply a high probability of whole-task success. We develop a dependence-aware audit framework for these evaluations. First, we give constructive proofs of the exact interv…
On simulated patients from a published history-taking simulator, we ask, in exploratory contrasts beside a pre-registered test, whether a prompted Qwen3-8B interviewer uses a patient state it is shown: whether its recall depends on the stated state being correct. The patients withhold each topic until asked enough time…