Rewrite: GatedFusion architecture + UAV-GeoLoc dataset

Architecture v2:
- Query branch: drone + text -> GatedFusion -> proj -> query_emb
- Gallery branch: satellite -> proj -> gallery_emb
- Single InfoNCE loss (asymmetric 0.6/0.4)
- GatedFusion: learnable gated addition (sigma(alpha)*img + (1-sigma(alpha))*text)
- Baseline mode: gate=1.0 (text ignored)

Dataset:
- UAV-GeoLoc loader with template captions from path metadata
- 27 terrain types with predefined features
- Random positive crop sampling per epoch

Configs: balanced (gate=0.7), baseline (no text), text_heavy (gate=0.3)

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

scripts/compare_runs.py

@@ -1,9 +1,6 @@
 from __future__ import annotations
 
-"""Compare baseline vs full-caption runs and compute Delta R@1 report.
-
-Reads eval reports produced by src.eval.evaluate.run_evaluation_from_checkpoint
-and produces a markdown + JSON summary.
+"""Compare baseline (no text) vs caption-fused runs. Compute Delta R@1 report.
 
 Usage:
     python -m scripts.compare_runs \
@@ -18,10 +15,8 @@ from pathlib import Path
 
 
 _DIRECTIONS = (
-    "drone_to_sat",
-    "sat_to_drone",
-    "text_to_sat",
-    "text_to_drone",
+    "query_to_gallery",
+    "gallery_to_query",
 )
 _KS = (1, 5, 10)
 
@@ -33,73 +28,70 @@ def _load_metrics(report_path: Path) -> dict[str, float]:
 
 
 def _format_row(name: str, baseline: dict[str, float], full: dict[str, float]) -> str:
-    """Render one markdown row for a direction across R@1, R@5, R@10."""
     cells = [name]
     for k in _KS:
         key = f"r@{k}_{name}"
         b = baseline.get(key, float("nan"))
         f_ = full.get(key, float("nan"))
-        delta = f_ - b if (b == b and f_ == f_) else float("nan")  # NaN-safe
-        cells.append(f"{b:.4f} → {f_:.4f} (Δ {delta:+.4f})")
+        delta = f_ - b if (b == b and f_ == f_) else float("nan")
+        cells.append(f"{b:.4f} -> {f_:.4f} (D {delta:+.4f})")
     return "| " + " | ".join(cells) + " |"
 
 
 def _interpret_delta(delta: float) -> str:
-    """Human-readable caption-quality verdict."""
     if delta >= 0.03:
-        return "✅ PASS — captions informative (Δ R@1 ≥ +3%)"
+        return "PASS -- captions informative (D R@1 >= +3%)"
     if delta >= 0.01:
-        return "⚠️  MARGINAL — consider VLM refinement (+1% ≤ Δ < +3%)"
+        return "MARGINAL -- consider VLM refinement (+1% <= D < +3%)"
     if delta >= 0:
-        return "❌ WEAK — captions add little signal (< +1%)"
-    return "❌❌ HARMFUL — captions confuse model (Δ < 0)"
+        return "WEAK -- captions add little signal (< +1%)"
+    return "HARMFUL -- captions confuse model (D < 0)"
 
 
 def build_comparison_markdown(
     baseline: dict[str, float],
     full: dict[str, float],
 ) -> str:
-    """Compose markdown comparison report."""
     lines: list[str] = ["# Caption Quality Test: Comparison Report", ""]
 
-    # Headline Δ R@1 on primary direction.
-    primary = "drone_to_sat"
+    primary = "query_to_gallery"
     primary_key = f"r@1_{primary}"
     primary_delta = full.get(primary_key, 0.0) - baseline.get(primary_key, 0.0)
     verdict = _interpret_delta(primary_delta)
 
-    lines.append(f"## Primary metric: Δ R@1 ({primary}) = {primary_delta:+.4f}")
+    lines.append(f"## Primary metric: D R@1 (query->gallery) = {primary_delta:+.4f}")
     lines.append("")
     lines.append(f"**Verdict:** {verdict}")
     lines.append("")
 
-    # Full table.
-    lines.append("## All directions × K")
+    # Gate value.
+    gate = full.get("gate", None)
+    if gate is not None:
+        lines.append(f"**Fusion gate:** {gate:.4f} (1.0 = text ignored, 0.0 = image ignored)")
+        lines.append("")
+
+    lines.append("## All directions x K")
     lines.append("")
-    header = "| Direction | R@1 base → full | R@5 base → full | R@10 base → full |"
+    header = "| Direction | R@1 base -> full | R@5 base -> full | R@10 base -> full |"
     sep = "|---|---|---|---|"
     lines.extend([header, sep])
     for direction in _DIRECTIONS:
-        row = _format_row(direction, baseline, full)
-        lines.append(row)
+        lines.append(_format_row(direction, baseline, full))
     lines.append("")
 
-    # Decision rule recap.
     lines.append("## Decision rule")
     lines.append("")
-    lines.append("- Δ R@1 ≥ +3% → captions pass, proceed to World-UAV generation")
-    lines.append("- +1% ≤ Δ R@1 < +3% → add VLM refinement, re-run")
-    lines.append("- Δ R@1 < +1% → redesign caption pipeline")
-    lines.append("- Δ R@1 < 0 → critical bug, investigate caption/image alignment")
+    lines.append("- D R@1 >= +3% -> captions pass, proceed to production")
+    lines.append("- +1% <= D R@1 < +3% -> add VLM refinement, re-run")
+    lines.append("- D R@1 < +1% -> redesign caption pipeline")
+    lines.append("- D R@1 < 0 -> critical bug, investigate")
     lines.append("")
 
     return "\n".join(lines)
 
 
 def main() -> None:
-    parser = argparse.ArgumentParser(
-        description="Compare baseline vs full-caption runs."
-    )
+    parser = argparse.ArgumentParser(description="Compare baseline vs caption runs.")
     parser.add_argument("--baseline_report", type=Path, required=True)
     parser.add_argument("--full_report", type=Path, required=True)
     parser.add_argument("--output", type=Path, required=True)
@@ -114,7 +106,6 @@ def main() -> None:
     with args.output.open("w", encoding="utf-8") as f:
         f.write(md)
 
-    # Also write machine-readable summary.
     summary = {
         "baseline_metrics": baseline,
         "full_metrics": full,