From 4cc233db3c8cd95324e43c64a5f038ef3ec3cd78 Mon Sep 17 00:00:00 2001
From: wassname <1103714+wassname@users.noreply.github.com>
Date: Sat, 27 Jun 2026 08:32:43 +0800
Subject: [PATCH] eval: add a load-bearing SHOULD next to the default-level aux
 stats

At verbose level 1 (default) the aux-stats line and 64-char free-form had no
interpretation; only verbose>=2 carried SHOULDs. Pair a directional/counterfactual
SHOULD with the always-shown aux stats: pmass_allowed near base + informedness>0 =
in-format signal; pmass_allowed falling / frac_unscorable rising while informedness->0
= the steer broke format and the moral numbers are noise (the steer/breakage confound).

Co-Authored-By: Claudypoo <288921227+claudypoo@users.noreply.github.com>
---
 src/tinymfv/eval.py | 8 +++++++-
 1 file changed, 7 insertions(+), 1 deletion(-)

diff --git a/src/tinymfv/eval.py b/src/tinymfv/eval.py
index 55514d7..698efc1 100644
--- a/src/tinymfv/eval.py
+++ b/src/tinymfv/eval.py
@@ -437,7 +437,13 @@ def evaluate(
             "T": T, "informedness": informedness, "mean_pmass_allowed": mean_pmass_allowed,
             "frac_unscorable": frac_unscorable, "mean_nll_prefill": mean_nll_prefill,
         }.items() if v is not None}
-        logger.debug("aux stats: " + json.dumps(aux))
+        logger.debug(
+            "aux stats: " + json.dumps(aux) + "\n"
+            "SHOULD: mean_pmass_allowed stays near base (model answers in-format) and informedness > 0 "
+            "(discriminates the violated foundation above chance). If pmass_allowed falls or "
+            "frac_unscorable rises while informedness -> 0, the steer broke FORMAT -> the moral "
+            "numbers are noise, not signal (the steer/breakage confound)."
+        )
         if verbose >= 2:
             # full first-row score dump + profile table (DEMO A trace already printed
             # above in the rollout, first batch).