From 9398567e91560daf480392f9aa1f6ca50bf9ac2b Mon Sep 17 00:00:00 2001 From: wassname <1103714+wassname@users.noreply.github.com> Date: Tue, 9 Jun 2026 04:51:34 +0000 Subject: [PATCH] results: base model solve=0.126 hack=0.000 (matches paper ~0.115) Fills baseline row in Q14 table and main.tex tab:anchors. Context: job 23 (steps=0, zero-shot eval, seed 43, n=119). Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com> --- docs/results.md | 2 +- docs/writeup/main.tex | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/results.md b/docs/results.md index 0c56a7f..3771763 100644 --- a/docs/results.md +++ b/docs/results.md @@ -54,7 +54,7 @@ in the answer. | routeV act_vote | authored | per-rollout (global vote) | queued (19) | | | | routeV LoRA-B | authored | per-rollout | queued (20) | | | | routeV random-V | authored (Haar dir) | per-rollout | queued (21) | | | -| base model (job 23) | -- | -- | running | | | +| base model (job 23) | -- | -- | **0.000** | **0.126** | **+0.126** | | no-loophole ceiling (job 24) | -- | -- | queued | | | **Answer: vanilla hack_deploy=0.613 -- suppression is real and large.** diff --git a/docs/writeup/main.tex b/docs/writeup/main.tex index 0ead9ed..fbaca07 100644 --- a/docs/writeup/main.tex +++ b/docs/writeup/main.tex @@ -289,7 +289,7 @@ hack \emph{generalises} off the demonstrated mode. Condition & Description & Solve $\uparrow$ & Hack $\downarrow$ \\ \midrule Base model (no training) & Zero-shot Qwen3-4B & paper: 0.115 & -- \\ - \rowcolor{lightgray} Ours (base, job 23) & \TODO{fill} & -- & -- \\ + \rowcolor{lightgray} Ours (base, job 23) & Qwen3-4B, zero-shot (steps=0), seed 43 & 0.126 & 0.000 \\ \midrule Vanilla GRPO & Paper reference & paper: 0.149 & paper: high \\ \rowcolor{lightgray} Ours (vanilla, job 16) & Qwen3-4B, 60-step fast, seed 43 & 0.101 & 0.613 \\