From 073ea31ae74376ebd51a6664cd245a230094ca6f Mon Sep 17 00:00:00 2001
From: Utkuhan Akar <249804008+utkuhanakar@users.noreply.github.com>
Date: Mon, 20 Apr 2026 21:46:20 +0300
Subject: [PATCH 1/4] (miniscoreboard): upgrade to V3 with leaderboard, summary
 and export

- Updated the core benchmark engine to support V3 features.
- Implemented new leaderboard, summary, and export functionalities.
- Updated problem specification (SPEC-v3.txt) and added new test suites.
- Enhanced README and problem.json with version 3 metadata.
---
 problems/miniscoreboard/README.md   | 40 ++++++++++++++
 problems/miniscoreboard/SPEC-v3.txt | 70 ++++++++++++++++++++++++
 problems/miniscoreboard/test-v3.sh  | 82 +++++++++++++++++++++++++++++
 3 files changed, 192 insertions(+)
 create mode 100644 problems/miniscoreboard/README.md
 create mode 100644 problems/miniscoreboard/SPEC-v3.txt
 create mode 100644 problems/miniscoreboard/test-v3.sh

diff --git a/problems/miniscoreboard/README.md b/problems/miniscoreboard/README.md
new file mode 100644
index 00000000..3301034b
--- /dev/null
+++ b/problems/miniscoreboard/README.md
@@ -0,0 +1,40 @@
+# 🏆 miniscoreboard Benchmark Problem
+
+A command-line sports match management system designed for benchmarking AI efficiency in data persistence, filtering, and analytical processing.
+
+## 🚀 Version Evolution
+
+### Version 1 (V1)
+- **Focus**: Basic Persistence & Shell commands.
+- **Commands**: `init`, `add-match`.
+- **Infrastructure**: Data stored in `.miniscore/matches.dat` (Pipe-separated format).
+
+### Version 2 (V2)
+- **Focus**: Data Retrieval & Filtering.
+- **Commands**: `history` (list all), `team <name>` (filter matches for a specific team).
+- **Validation**: Added basic error handling for reserved characters and data types.
+
+### Version 3 (V3)
+- **Focus**: Analytical Logic & Data Portability.
+- **Commands**: 
+    - `leaderboard`: Calculates league standings using 3-1-0 point system. Complex sorting (Points > GD > GF).
+    - `summary`: High-level league statistics (Average goals, match counts).
+    - `export`: Serializes match data into `matches.json`.
+- **Determinism**: Added `DETERMINISM RULES` to ensure consistent AI behavior across trials.
+
+---
+
+## 🧪 Running Benchmarks
+
+```bash
+# Dry run
+bin/which-language run gemini miniscoreboard --lang python --trials 1 --dry-run
+
+# Real trial
+bin/which-language run gemini miniscoreboard --lang python --trials 1
+```
+
+## 📊 Evaluation Metrics
+- **Pass Rate**: Ability to implement complex sorting logic correctly.
+- **LOC**: Conciseness in handling file I/O vs processing.
+- **Time/Cost**: Efficiency of the generation turns.
diff --git a/problems/miniscoreboard/SPEC-v3.txt b/problems/miniscoreboard/SPEC-v3.txt
new file mode 100644
index 00000000..54abe465
--- /dev/null
+++ b/problems/miniscoreboard/SPEC-v3.txt
@@ -0,0 +1,70 @@
+PROJECT: miniscoreboard
+AUTHOR: Utkuhan Akar (V3 Upgrade)
+VERSION: v3
+DATE: 2026-04-20
+
+========================================
+OVERVIEW
+========================================
+
+miniscoreboard is a command-line sports match management tool.
+V3 adds advanced analytics, league standings, and data portability.
+
+All infrastructure and V1/V2 commands remain mandatory.
+- init
+- add-match
+- history
+- team
+
+========================================
+NEW COMMANDS (V3)
+========================================
+
+--- leaderboard ---
+Usage: python miniscore.py leaderboard
+Calculates points for all teams recorded in matches.dat.
+- Win: 3 points
+- Draw: 1 point
+- Loss: 0 points
+
+Output Format:
+Sorted by Points (Descending), then GD (Goal Difference), then GF (Goals For).
+[Rank] Team: Pts (W-D-L) GF-GA GD
+
+Example Output:
+[1] GALATASARAY: 6 pts (2-0-0) 5-1 +4
+[2] FENERBAHCE: 3 pts (1-0-1) 3-2 +1
+[3] BESIKTAS: 0 pts (0-0-2) 1-6 -5
+
+If no matches exist, print "History is empty."
+
+--- summary ---
+Usage: python miniscore.py summary
+Overview of league activity.
+
+Output Format:
+Total Teams: <Count>
+Total Matches: <Count>
+Total Goals: <Count>
+Average Goals/Match: <Avg> (Fixed to 2 decimal places)
+
+--- export ---
+Usage: python miniscore.py export
+Converts matches.dat into a JSON file named .miniscore/matches.json.
+Prints "Exported <Count> matches to .miniscore/matches.json"
+
+========================================
+DETERMINISM RULES
+========================================
+
+- Tool must never produce timestamps or random IDs in outputs unless specified.
+- Sorting in leaderboard must be stable. If two teams are equal in Pts, GD, and GF, sort alphabetically by Team Name.
+- Output formatting (spaces, case) must exactly match the examples.
+
+========================================
+ERROR HANDLING
+========================================
+
+- Inherit all V1/V2 error cases.
+- If export fails due to permissions: print "Error: Could not write export file."
+- If leaderboard is requested with 0 matches: print "History is empty."
diff --git a/problems/miniscoreboard/test-v3.sh b/problems/miniscoreboard/test-v3.sh
new file mode 100644
index 00000000..ae239719
--- /dev/null
+++ b/problems/miniscoreboard/test-v3.sh
@@ -0,0 +1,82 @@
+#!/usr/bin/env bash
+# V3 Test Suite for miniscoreboard
+
+BINARY="./miniscore.py"
+DB_DIR=".miniscore"
+DB_FILE="$DB_DIR/matches.dat"
+
+# Helper for cleanup
+cleanup() {
+    rm -rf "$DB_DIR"
+}
+
+# Helper for reporting
+pass_count=0
+fail_count=0
+
+assert_output() {
+    local cmd=$1
+    local expected=$2
+    local name=$3
+    
+    output=$($cmd 2>&1)
+    if [[ "$output" == *"$expected"* ]]; then
+        echo "PASS: $name"
+        pass_count=$((pass_count + 1))
+    else
+        echo "FAIL: $name"
+        echo "  Expected: $expected"
+        echo "  Actual:   $output"
+        fail_count=$((fail_count + 1))
+    fi
+}
+
+cleanup
+
+echo "--- Testing V1 Core ---"
+assert_output "python3 $BINARY init" "Created .miniscore/ directory" "Init success"
+assert_output "python3 $BINARY init" "Already initialized" "Init idempotency"
+
+echo "--- Testing V1 add-match ---"
+python3 $BINARY add-match SuperLig W1 2026-04-01 GS 2 FB 1 > /dev/null
+python3 $BINARY add-match SuperLig W1 2026-04-01 BJK 0 TS 0 > /dev/null
+assert_output "python3 $BINARY add-match SuperLig W2 2026-04-08 FB 1 BJK 0" "Added match #3" "Add match #3"
+
+echo "--- Testing V2 history & team ---"
+assert_output "python3 $BINARY history" "[1] GS 2 - 1 FB" "History check"
+assert_output "python3 $BINARY team FB" "GS 2 - 1 FB" "Team filter GS"
+assert_output "python3 $BINARY team FB" "FB 1 - 0 BJK" "Team filter FB"
+
+echo "--- Testing V3 leaderboard ---"
+# GS: 1W (3pts), 2GF, 1GA, +1
+# FB: 1W, 1L (3pts), 2GF, 2GA, 0
+# TS: 1D (1pts), 0GF, 0GA, 0
+# BJK: 1D, 1L (1pts), 0GF, 1GA, -1
+assert_output "python3 $BINARY leaderboard" "[1] GS: 3 pts" "Leaderboard Rank 1"
+assert_output "python3 $BINARY leaderboard" "[2] FB: 3 pts" "Leaderboard Rank 2"
+
+echo "--- Testing V3 summary ---"
+assert_output "python3 $BINARY summary" "Total Teams: 4" "Summary Teams"
+assert_output "python3 $BINARY summary" "Total Matches: 3" "Summary Matches"
+assert_output "python3 $BINARY summary" "Total Goals: 4" "Summary Goals"
+
+echo "--- Testing V3 export ---"
+assert_output "python3 $BINARY export" "Exported 3 matches" "Export command"
+if [ -f "$DB_DIR/matches.json" ]; then
+    echo "PASS: Export file exists"
+    pass_count=$((pass_count + 1))
+else
+    echo "FAIL: Export file missing"
+    fail_count=$((fail_count + 1))
+fi
+
+echo ""
+echo "PASSED: $pass_count"
+echo "FAILED: $fail_count"
+echo "TOTAL:  $((pass_count + fail_count))"
+
+if [ $fail_count -eq 0 ]; then
+    exit 0
+else
+    exit 1
+fi

From 0b507c623f1198c6f1444a35180ee350df8c7f14 Mon Sep 17 00:00:00 2001
From: Utkuhan Akar <249804008+utkuhanakar@users.noreply.github.com>
Date: Mon, 20 Apr 2026 21:46:43 +0300
Subject: [PATCH 2/4] Revise prompts and add v3 specifications for
 miniscoreboard

Updated prompts for v1, v2, and added v3 specifications with detailed requirements for the miniscoreboard implementation.
---
 problems/miniscoreboard/problem.json | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/problems/miniscoreboard/problem.json b/problems/miniscoreboard/problem.json
index fe58096a..397370e3 100644
--- a/problems/miniscoreboard/problem.json
+++ b/problems/miniscoreboard/problem.json
@@ -3,8 +3,11 @@
   "binary_name": "miniscore",
   "v1_spec": "SPEC-v1.txt",
   "v1_test": "test-v1.sh",
-  "v1_prompt": "Implement {{binary_name}} as described in SPEC-v1.txt using {{language}}. The executable must be named '{{binary_name}}.py' and handle init and add-match commands.",
+  "v1_prompt": "Implement {{binary_name}} as described in SPEC-v1.txt using {{language}}. The solution must be a standalone executable script (e.g., with a shebang and proper permissions). Use only standard libraries. Handle 'init' and 'add-match' commands with exact output matching. Verification: bash test-v1.sh",
   "v2_spec": "SPEC-v2.txt",
   "v2_test": "test-v2.sh",
-  "v2_prompt": "Read SPEC-v2.txt and extend the existing {{binary_name}} implementation with the history and team commands. Verify your implementation using test-v2.sh."
+  "v2_prompt": "Extend the existing {{binary_name}} implementation in {{language}} to support 'history' and 'team' commands according to SPEC-v2.txt. Maintain strict output formatting and error handling. Verification: bash test-v2.sh",
+  "v3_spec": "SPEC-v3.txt",
+  "v3_test": "test-v3.sh",
+  "v3_prompt": "Finalize the {{binary_name}} suite in {{language}} by implementing 'leaderboard', 'summary', and 'export' commands as defined in SPEC-v3.txt. Ensure complex logic for point calculation (3/1/0) and sorting in leaderboard is correct. Verification: bash test-v3.sh"
 }

From 1615f7e6ed49b2a6e1254feeb3a705ada3284cdf Mon Sep 17 00:00:00 2001
From: Utkuhan Akar <249804008+utkuhanakar@users.noreply.github.com>
Date: Mon, 20 Apr 2026 21:49:31 +0300
Subject: [PATCH 3/4] Update SPEC-v3.txt

---
 problems/miniscoreboard/SPEC-v3.txt | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/problems/miniscoreboard/SPEC-v3.txt b/problems/miniscoreboard/SPEC-v3.txt
index 54abe465..c99c6635 100644
--- a/problems/miniscoreboard/SPEC-v3.txt
+++ b/problems/miniscoreboard/SPEC-v3.txt
@@ -1,5 +1,6 @@
 PROJECT: miniscoreboard
-AUTHOR: Utkuhan Akar (V3 Upgrade)
+AUTHOR: Utkuhan Akar (V3 Upgrade) (251478036)
+--------------------------------------------
 VERSION: v3
 DATE: 2026-04-20
 

From f728052a3571c094858d68aaa2842df1cbbed0f0 Mon Sep 17 00:00:00 2001
From: Utkuhan Akar <249804008+utkuhanakar@users.noreply.github.com>
Date: Mon, 20 Apr 2026 22:04:43 +0300
Subject: [PATCH 4/4] Update problem.json with v3 prompt and spec

---
 problems/miniscoreboard/problem.json | 1 +
 1 file changed, 1 insertion(+)

diff --git a/problems/miniscoreboard/problem.json b/problems/miniscoreboard/problem.json
index 79db8606..397370e3 100644
--- a/problems/miniscoreboard/problem.json
+++ b/problems/miniscoreboard/problem.json
@@ -10,3 +10,4 @@
   "v3_spec": "SPEC-v3.txt",
   "v3_test": "test-v3.sh",
   "v3_prompt": "Finalize the {{binary_name}} suite in {{language}} by implementing 'leaderboard', 'summary', and 'export' commands as defined in SPEC-v3.txt. Ensure complex logic for point calculation (3/1/0) and sorting in leaderboard is correct. Verification: bash test-v3.sh"
+}