plot: #148 substrate emergence — per-mode hack-rate curves (4/5 learned, seed 41)

Browse Source

New scripts/plot_substrate.py parses the hk_<mode> cumulative columns from a
multi-loophole substrate run (one log, K interleaved modes) and draws one
learning curve per mode with first_step onset dots and direct end-labels.
plot_emergence.py can't do this (it groups logs by a single --env-mode).
Figure shows the headline: vanilla GRPO learns file_marker/run_tests/
stdout_marker/sentinel, eq_override flat at 0 (never).

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>

...

This commit is contained in:

wassname

2026-05-30 16:49:03 +00:00

co-authored by Claudypoo

parent b685a4495b

commit 0ea751c5bc

2 changed files with 112 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

out/figs/substrate_emergence.png

BIN

Binary file not shown.

Side by Side After Width:  |  Height:  |  Size: 65 KiB