E1c scored: easy routing solved (95.9% at 0.11 iters), hard recall regressed; threshold calibration = identified next knob

Browse Source

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

...

This commit is contained in:

Nils

2026-07-16 01:48:14 +02:00

co-authored by Claude Fable 5

parent a643b4a146

commit 21908a0e33

2 changed files with 1538 additions and 0 deletions

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

results-loop/eval_code_gatehead_c_e300.json

+1519

File diff suppressed because it is too large Load Diff