遇见数据集

Data and code for: One Wrong Hint Is Enough: Planted-Answer Adoption and the Limits of Confidence-Based Abstention on Physics Problems

收藏
Zenodo2026-10-29 更新2026-11-05 收录
官方服务:

资源简介:

Scored per-cell data, analysis and scoring code, result tables and verification records for the PRST pilot preprint: One Wrong Hint Is Enough: Planted-Answer Adoption and the Limits of Confidence-Based Abstention on Physics Problems. This release excludes raw response databases, complete prompts and question text. Scored rows permit numerical reanalysis but not an independent end-to-end extraction audit. Code: MIT; author-generated data: CC BY 4.0. The package README specifies scope and limitations. No new paid inference was performed for this release.

提供机构:
Zenodo
创建时间:
2026-10-29
二维码
社区交流群
二维码
科研交流群
商业服务