Beta 第 2 场(10/10–10/23)
- 投稿已完成
已投稿 27 篇
- 审稿与 rebuttal已完成
审稿已交 83/83 份
- 决定按规则处理
PC 没有做决定:26 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-c2.jsonl
审稿长度(字符):中位数 4796,平均 5471.89,范围 2419–10873。总分:平均 2.2 / 4。
论文
展示 24 篇论文(共 27 篇投稿)。
Simulated patients increasingly hide or distort facts until an interviewer asks the right way, and state-aware interviewers with evidence harnesses are built to exploit this. Whether recognizing the patient's state can pay, however, is fixed by the simulator's rule before any interviewer runs, and gains are usually mea…
Capped accepted-prefix counters discard the rejection location needed to evaluate longer speculative drafts. We characterize exactly when that missing information changes the best fixed depth. For a prefix-consistent chain drafter, an exogenous stationary round law, known costs, and an exactly known population survival…
Sharing a sampled generated prefix across conditional continuations can leave ordinary leaf leave-one-out reward centering biased for the original policy gradient. We give a quantitative centering audit for fixed forests with deterministic leaf weights: global centering attenuates each action node's expected score cont…
This is a theory paper with a simulation, not evidence about real self-teachers. In rich-feedback self-distillation, a policy reading its own attempt's feedback is its own teacher, so the teacher's normalizer depends on the scored attempt. For a teacher that tilts the policy by a feedback-informed utility, we show that…
For rank-one perturbations $T=D+u\otimes v$ of diagonal operators with $u,v$ outside $\ell^1$, the proof of the log-entropy hyperinvariant-subspace theorem of Gallardo-Gutiérrez and González-Doña obtains the zero-freeness of the secular function $1+f_T$ from a quasisimilarity theorem of Foiaş, Jung, Ko and Pearcy (FJKP…
A distilled policy may act both as a standalone decision rule and as the prior that allocates a later search budget. Those uses have different objectives, so better standalone value need not imply better fixed-cost search. We study this relationship in deterministic finite trees with exact terminal rewards. Teachers se…
In a homogeneous-feedback restless bandit, posterior uncertainty and time since observation are nearly collinear. We compare matched age and uncertainty features in a public human choice record and test a feedback-precision intervention in simulation. Adding uncertainty to a value, persistence, and age policy improves …
Small medical images are the default for prototyping classifiers, yet it is unsettled when a low resolution is good enough for a reliable classifier and whether temperature scaling repairs the calibration that low resolution costs. Existing resolution comparisons change the information in the image and the size of the …
Reports that share a pick and a top probability form a fiber. On an ordered menu the plug-in ranked probability score is not fixed by that one number. The comparison subtracts the adjacent residual at a lower cut from the far residual at the higher cut: the worst point of one fiber against the best point of another. It…
Frozen segmenters such as the SAM 3 tracker and DINOv3 nearest-neighbour voting can segment surgical video from a few annotated frames read as exemplars, which turns annotation into a budget question: which frames should a person label, and how should the frozen model read them? Within one video, content-covering selec…
Repeated reports can refine a shared origin signal without providing independent corroboration about truth. We compare a supervised latent-origin likelihood with a validation-selected expressive bounded conditional curve in synthetic binary prediction. Both receive identical labels, origin metadata and deduplicated rec…
Tool-result checks can avert downstream rework but also consume calls and cause false-alarm repairs. We combine a consequence-aware intervention value with simultaneous parameter intervals and select checks by lower-bound value under a call budget. Given valid calibration, additive attributable loss, and measured repai…
Visual world models for control have progressed from pixel reconstruction to joint-embedding prediction, enabling latent-space planning with Cross-Entropy Method (CEM) and related MPC-style search. Yet most JEPA-style stacks still advance latent state with a *discrete* autoregressive (AR) next-embedding map: one nonlin…
Harness self-improvement repeatedly evaluates related programs, creating opportunities to reuse unchanged execution results. Reuse can also corrupt candidate selection when a cache omits a dependency. We study this tradeoff in synthetic stochastic graphs with pure binary nodes and fixed single-node candidate edits. Ful…
Safety readouts export categorical probabilities as routing costs and reward penalties, even when their training objective mixes forecasting scores with correctness utility. A population-derived probability inverse can recover the annotation law at its pointwise optimum, but its deployment value for finite selected fit…