日期 影响因子
日期:
2020 年 — 2026 年
2020
2021
2022
2023
2024
2025
2026
影响因子:
–

Reply to Hu: Reasoning traces need not be faithful to account for the cost of human thinking

回复胡：推理痕迹不必完全忠实，以解释人类思维的成本

期刊:Proceedings of the National Academy of Sciences of the United States of America
影响因子:9.1
doi:10.1073/pnas.2606498123
de Varda, Andrea Gregor; D'Elia, Ferdinando Pio; Kean, Hope; Lampinen, Andrew; Fedorenko, Evelina
发表日期：2026
文献求助 收藏

Reply to Dujmović: The alignment in cost between human and model reasoning is an empirical phenomenon worth explaining

回复 Dujmović：人类推理和模型推理成本的一致性是一个值得解释的经验现象。

期刊:Proceedings of the National Academy of Sciences of the United States of America
影响因子:9.1
doi:10.1073/pnas.2536153123
de Varda, Andrea Gregor; D'Elia, Ferdinando Pio; Kean, Hope; Lampinen, Andrew; Fedorenko, Evelina
发表日期：2026
文献求助 收藏

Reply to Vankov et al.: Reasoning traces are linked to accuracy and capture key dimensions of problem complexity

回复 Vankov 等人：推理轨迹与准确性相关，并能捕捉问题复杂性的关键维度。

期刊:Proceedings of the National Academy of Sciences of the United States of America
影响因子:9.1
doi:10.1073/pnas.2603574123
de Varda, Andrea Gregor; D'Elia, Ferdinando Pio; Kean, Hope; Lampinen, Andrew; Fedorenko, Evelina
发表日期：2026
文献求助 收藏

The cost of thinking is similar between large reasoning models and humans

大型推理模型和人类的思考成本相似。

期刊:Proceedings of the National Academy of Sciences of the United States of America
影响因子:9.1
doi:10.1073/pnas.2520077122
de Varda, Andrea Gregor; D'Elia, Ferdinando Pio; Kean, Hope; Lampinen, Andrew; Fedorenko, Evelina
发表日期：2025
文献求助 收藏