基于法律裁判文书的事件抽取及其应用,包括数据的分词、词性标注、命名实体识别、事件要素抽取和判决结果预测等内容
-
Updated
Mar 7, 2026 - Python
基于法律裁判文书的事件抽取及其应用,包括数据的分词、词性标注、命名实体识别、事件要素抽取和判决结果预测等内容
Practitioner-judgment skill for Claude Code, Codex, and AI agents under ambiguity, trade-offs, and incomplete information.
JEAM is a Python package for evidence accumulation modeling of continuous judgments
代入真实历史决策点、与史实对账来训练判断力——每次互动闭成数据闭环,判断力可 持续改善。Claude Code 技能。
MCP server for searching Taiwan judicial judgments (司法院裁判書系統) — 2 AI-callable tools over Model Context Protocol
Recursive adversarial judgment skill: 7 reasoning roles + cross-exam + red team + fact-grounded judge with Pre-Mortem, Time Horizon, Evidence Threshold. Single-file Python, MIT, adapter pattern for plug-in integration.
A framework and evaluation for the rigor-deficit account of agentic AI failure on judgment work. Pre-registered, blinded, dual-rater study (n=30) with reproducible scoring artifacts.
Add a description, image, and links to the judgment topic page so that developers can more easily learn about it.
To associate your repository with the judgment topic, visit your repo's landing page and select "manage topics."