fix §4.4 interpretation to match data; aligned in §6

make_report.py

@@ -735,9 +735,15 @@ def report(evals, rows):
         "",
         *ss_lines,
         "",
-        "**Observation:** accuracy degrades only mildly when the state",
-        "space shrinks, i.e. what is learned is partly vocabulary-",
-        "independent rather than a lookup over specific states.",
+        "**Observation:** accuracy degrades sharply and non-monotonically:",
+        "fixed-4 drops from 0.48 at S'=64 to 0.12 at S'=32 and 0.22 at",
+        "S'=16; rec-1x4 from 0.76 to 0.10 and 0.22. Relative to chance",
+        "(1/S'), smaller state spaces are far harder (roughly 3-4x chance,",
+        "vs ~30x chance at S'=64), so the learned solution is strongly",
+        "tied to the trained state space - it is not a clean, vocabulary-",
+        "independent algorithm. (The S'=16 > S'=32 inversion is unexplained;",
+        "random functions on smaller domains enter cycles sooner, which may",
+        "change the task's structure.)",
         "",
         "### 4.5 Training dynamics",
         "",
@@ -844,6 +850,9 @@ def report(evals, rows):
         "- The rec-1x-dynamic family trains at ~5 average block-",
         "  applications per step (R ~ U{2..8}), slightly above the matched",
         "  4 - flagged rather than hidden.",
+        "- The aligned-unroll variant (R=k) is a negative result at this",
+        "  budget: ~0.10 in-distribution across 3 seeds at 25k steps, and a",
+        "  100k-step probe still only reaches 0.24 - see 4.7.",
         "- Two duplicate jobs created by interrupted tool calls were",
         "  cancelled (~$0.30 wasted).",
         "- Dependency pin: trackio 0.42.0 requires huggingface-hub<2.0;",