gbanyan/novelty-seeking
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Add experiments framework and novelty-driven agent loop

Browse Source 
- Add complete experiments directory with pilot study infrastructure
  - 5 experimental conditions (direct, expert-only, attribute-only, full-pipeline, random-perspective)
  - Human assessment tool with React frontend and FastAPI backend
  - AUT flexibility analysis with jump signal detection
  - Result visualization and metrics computation

- Add novelty-driven agent loop module (experiments/novelty_loop/)
  - NoveltyDrivenTaskAgent with expert perspective perturbation
  - Three termination strategies: breakthrough, exhaust, coverage
  - Interactive CLI demo with colored output
  - Embedding-based novelty scoring

- Add DDC knowledge domain classification data (en/zh)
- Add CLAUDE.md project documentation
- Update research report with experiment findings

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
gbanyan
2026-01-20 10:16:21 +08:00
parent 26a56a2a07
commit 43c025e060
81 changed files with 18766 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
experiments/__init__.py Normal file
View File

@@ -0,0 +1,7 @@
"""
Experiment module for 5-condition idea generation study.
This module implements a 2×2 factorial design + control to test
the contributions of attribute decomposition and expert perspectives
to creative ideation quality.
"""