v2.0: Combined with cgrt-consensus-5model data (8,050 disagreements, 1,556 contested) ca5e3d7 verified Adam1010 commited on 10 days ago
v1.1: Financial domain audit - confirms Goodhart Gap hypothesis b684ab3 verified Adam1010 commited on 10 days ago
v1.1: Document financial domain findings - strongest Goodhart Gap detector dc1a656 verified Adam1010 commited on 10 days ago