Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Adam1010
/
goodhart-gap-benchmark
like
0
English
benchmark
reasoning
multi-step
evaluation
llm-evaluation
goodhart
execution-vs-understanding
consensus
multi-model
License:
mit
Model card
Files
Files and versions
xet
Community
Copy to bucket
new
main
goodhart-gap-benchmark
91.2 MB
Ctrl+K
Ctrl+K
1 contributor
History:
4 commits
Adam1010
v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested)
ca5e3d7
verified
6 months ago
data
v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested)
6 months ago
results
v1.1: Financial domain audit - confirms Goodhart Gap hypothesis
6 months ago
.gitattributes
1.72 kB
v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested)
6 months ago
README.md
6.33 kB
v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested)
6 months ago
create_combined_dataset.py
7.18 kB
v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested)
6 months ago
evaluate.py
16 kB
v1.1: Financial domain audit - confirms Goodhart Gap hypothesis
6 months ago
generate_dataset.py
45.8 kB
v1.1: Financial domain audit - confirms Goodhart Gap hypothesis
6 months ago
requirements.txt
Safe
17 Bytes
v1.1: Financial domain audit - confirms Goodhart Gap hypothesis
6 months ago
