Add EgoSpeak prediction alignment for floor evaluation

docs/easycom_competing_risk_floor_evaluation.md

@@ -9,6 +9,22 @@ timing-derived behavior evaluation, not semantic EOT/INT, addressee, or
 individual-speaker ground truth: EasyCom's `others` target is aggregate
 activity.
 
+Raw EgoSpeak MiniROADA predictions use a different source-indexed layout. Use
+`prepare_egospeak_floor_eval.py` to align them and create an explicit valid
+mask before including the GRU A+V baseline in the same comparison:
+
+```bash
+python3 prepare_egospeak_floor_eval.py \
+  --prediction-root /path/to/miniroad/raw/eval \
+  --target-root /path/to/easycom_target_frame \
+  --output-dir results/egospeak_miniroada_floor_eval \
+  --sessions Session_12 Session_3 Session_2 Session_1
+```
+
+The converter requires raw arrays shaped `[T-10,10,3]` and fails rather than
+guessing if their shape, range, or target length differs. Do not transpose or
+pad MiniROADA output by hand.
+
 ## Event attribution
 
 At each horizon from 0.2 to 2.0 seconds, every eligible aggregate-other