Correct path-length label; add the 140 s (350-step) arm

README.md

@@ -163,7 +163,8 @@ paired on the same episodes.
 | oracle SPL (corrected, see below) | **0.348** |
 | NPWPL | **0.420** |
 | closest approach | 2.25 m |
-| path length | 14.26 m |
+| path length at closest approach | 14.26 m |
+| total path length | 19.83 m |
 
 Against the other checkpoints in this family, same episodes, same 70 s budget:
 
@@ -199,9 +200,13 @@ corrected column.
   does not reliably retrieve a goal announced once, deep in context. This model's PointNav
   component is there to teach a motion repertoire, not goal-following; do not deploy it as
   a point-goal navigator.
-* **Only measured at 70 s.** A 140 s arm has not been run for this checkpoint. Sibling
-  models gain oracle success and lose efficiency at longer budgets, so the ranking above
-  may not hold at 140 s.
+* **The efficiency lead is a 70 s result; the oracle lead holds at 140 s.** Doubling the
+  budget (`--max-steps 350`) raises oracle success to **0.733** -- still the best of the
+  flow-head family, and ahead of the 1:1 sibling's 0.703 -- but corrected oSPL falls to
+  **0.325** and NPWPL to 0.366, so the 1:1 sibling (0.339 / 0.384) matches it on
+  efficiency there. Within this checkpoint the 175 -> 350 gain is not significant
+  (McNemar p = 0.14; oSPL delta -0.024, 95% CI [-0.079, +0.031]). Read the 70 s numbers as
+  the efficiency claim and the 140 s numbers as the reachability claim.
 * **0.56 epochs** over its mixture -- undertrained rather than converged.
 * Trained on MP3D human demonstrations, evaluated on HM3D -- cross-dataset.
 * n=101 has a minimum detectable difference of roughly 0.10 on a success rate. Differences