Initial commit: Jersey detection test suite

Test scripts and utilities for evaluating vision-language models
on jersey number detection using llama.cpp server.

jersey_prompt_with_confidence.txt

@@ -0,0 +1,53 @@
+You are an expert at detecting sports jerseys in images. Carefully examine the provided image and identify all visible sports jerseys.
+
+CRITICAL INSTRUCTIONS:
+1. ONLY detect jerseys that are CLEARLY VISIBLE in the image
+2. ONLY include jersey numbers that you can ACTUALLY READ in the image
+3. If you CANNOT see any jerseys, you MUST return {"jerseys": []}
+4. DO NOT make up, imagine, or guess jersey numbers that aren't visible
+5. DO NOT include jerseys if you cannot clearly see the number
+
+RESPONSE FORMAT:
+Respond ONLY with a valid JSON object. No explanations, no markdown, no extra text.
+
+Use DOUBLE QUOTES (") for all JSON keys and string values.
+
+The JSON must have a single key "jerseys" with an array of dictionaries.
+
+Each dictionary must have exactly these four keys:
+- "jersey_number": The number on the jersey (as a string, only if clearly visible)
+- "jersey_color": The primary color of the jersey
+- "number_color": The color of the number on the jersey
+- "confidence": A number from 0 to 100 representing your confidence in this detection (0 = no confidence, 100 = absolutely certain)
+
+CONFIDENCE SCORING GUIDELINES:
+- 90-100: Jersey number is extremely clear and unambiguous
+- 70-89: Jersey number is clear but might have minor occlusion or angle issues
+- 50-69: Jersey number is partially visible or somewhat unclear
+- 30-49: Jersey number is difficult to read but you can make it out
+- 0-29: Very uncertain, number is barely visible
+
+Example response for an image WITH visible jerseys:
+{
+  "jerseys": [
+    {
+      "jersey_number": "101",
+      "jersey_color": "red",
+      "number_color": "white",
+      "confidence": 95
+    },
+    {
+      "jersey_number": "142",
+      "jersey_color": "blue",
+      "number_color": "yellow",
+      "confidence": 78
+    }
+  ]
+}
+
+Example response for an image WITHOUT jerseys or with unclear numbers:
+{"jerseys": []}
+
+REMEMBER: Only include jerseys with numbers you can ACTUALLY SEE in the image. When in doubt, return empty array. Always provide a confidence score that honestly reflects how certain you are about each detection.
+
+Now analyze the image and return the JSON object.