English(EN) Which Signals of Code Correctness Survive Distribution Shift? Hidden-State and Causal Predictors of Program and Verdict Correctness

代码正确性预测器在模型和语言上的鲁棒性经过测试

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-06 05:00

研究人员评估了六种无执行的代码正确性预测器在不同模型和编程语言下的鲁棒性，以评估其在分布变化下的表现。研究在 Qwen3-Coder-30B 和 gpt-oss-20b 上比较了预测器，并测试了基准变化（LiveCodeBench 到 BigCodeBench）和语言变化（Python、C++、Java）。因果定位方法在结果正确性方面表现出更强的鲁棒性，尤其是在语言变化下对 Qwen3-Coder 而言，其表现优于非因果预测器。 AI

影响这项研究可能带来更可靠的 AI 代码验证工具，减少昂贵的手动执行和推理的需求。

排序理由该集群包含一篇详细介绍 AI 模型研究结果的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 16 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍 AI 模型研究结果的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Viola Campos, Thomas Klassert, Adrian Ulges · 2026-11-06 05:00

代码正确性的哪些信号能经受分布变化？程序和结果正确性的隐藏状态与因果预测器

arXiv:2611.07876v1 Announce Type: cross Abstract: Large language models increasingly judge code, yet without external feedback such judgments are unreliable, and verifying them by executing tests or by extended reasoning is costly. Instead, execution-free correctness predictors u…

本文如何被排名

报道来源 [1]

代码正确性的哪些信号能经受分布变化？程序和结果正确性的隐藏状态与因果预测器

相关实体

相关话题