test_cases = [ { 'generations': ['[150, 0]'], 'golds': [183, 177, 146, 85, 70, 78, 55, 17, 0, -1, -1], "result": {'precision': [4.0], 'recall': [344.0], 'macro-mean': [174.0], 'median macro-mean': 174.0} } ]