Lower CONF_THRESH 0.5 -> 0.4 to recover missing edges

Single-line tuning experiment. Targets the recall bottleneck
(corner_f1 0.5104 vs leader 0.6472). With confidence threshold at 0.5,
real edges with mid-confidence model output were being filtered out.
Lowering to 0.4 trades a small amount of precision for higher recall
on segment retention, before the downstream merge / snap / hybrid_merge
post-processing further consolidates noise.

Easy revert if it regresses: change back to 0.5.

script.py

@@ -55,7 +55,7 @@ from s23dr_2026_example.postprocess_v2 import snap_to_point_cloud, snap_horizont
 SEQ_LEN = 4096
 COLMAP_QUOTA = 3072
 DEPTH_QUOTA = 1024
-CONF_THRESH = 0.5
+CONF_THRESH = 0.4
 MERGE_THRESH = 0.4
 SNAP_RADIUS = 0.5