wantsong
/
ccpe-system
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
ccpe-system/workbench/analysis/review-agent-regression-202.../README.md

1.1 KiB
Raw Permalink Blame History

Review Agent Regression Test Workspace

This workspace isolates regression testing for review-oriented CCPE artifacts.

Purpose

Evaluate whether migrated CCPE System Lite prompts preserve or improve the review quality of mature CCPE 2.0 prompts.

Primary question:

Should mature review agents be migrated by full CCPE System rewrite, or by original-kernel + minimal Lite wrapping?

Directory Layout

articles/
  User-provided full article texts for testing.

prompts/
  Prompt variants under test.

results/
  Raw model outputs from ChatGPT/Codex-side tests and Gemini-side tests.

rubrics/
  Evaluation rubric and scoring protocol.

reports/
  Final comparison reports.

Test Families

1. 巨人认知 / Giant Cognition
2. 认知显影 / Cognitive Imaging

Each family should test three prompt variants:

A. original-ccpe-2
B. ccpe-system-lite
C. original-kernel-minimal-lite

Each variant should be tested in two environments:

1. ChatGPT / Codex-side model
2. Gemini 3.1 Pro

Use a fresh thread or subthread for each test run to avoid context contamination.