遇见数据集

Agentic AI Test Checklist 110 — Assurance Catalog v1.1

收藏
Zenodo2026-10-23 更新2026-11-05 收录
官方服务:

资源简介:

Assurance test-design catalog for tool-using / agentic AI systems (not a model leaderboard). Stable IDs T1–T7; 110 checklist rows with role packs. v1.1 deepens all P0 rows and adds columns false_positive_note, audience, control_refs, plus MVP 14-gate, control map, FAQ, CONTRIBUTING, and a worked finding narrative. Runnable harness code is deferred to company GitLab. Companion Hub: https://huggingface.co/datasets/srinivaspadmanabhuni/agentic-ai-test-checklist-110 . Taxonomy (T1–T7 definitions): https://doi.org/10.5281/zenodo.23587407 . Contact: srinivas AT testAIng.com

提供机构:
Zenodo
创建时间:
2026-10-23
二维码
社区交流群
二维码
科研交流群
商业服务