Statistics Summary for op agent (mean ± std):
==================================================
accuracy: 0.0000 ± 0.0000
total_entries: 136.0000 ± 0.0000
correct_matches: 0.0000 ± 0.0000
average_execution_time: 7.6466 ± 0.0119
metrics_by_complexity:
  simple:
    count: 116.0000 ± 0.0000
    full_matches: 0.0000 ± 0.0000
    exact_code_matches: 0.0000 ± 0.0000
    exact_code_match_rate: 0.0000 ± 0.0000
    pv_exact_matched: 0.0000 ± 0.0000
    pv_exact_mismatched: 116.0000 ± 0.0000
    pv_exact_match_rate: 0.0000 ± 0.0000
    average_pv_match_rate: 0.0000 ± 0.0000
    average_pv_mismatch_rate: 100.0000 ± 0.0000
    timing_matched: 0.0000 ± 0.0000
    timing_mismatched: 116.0000 ± 0.0000
    timing_match_rate: 0.0000 ± 0.0000
    temp_matched: 0.0000 ± 0.0000
    temp_mismatched: 0.0000 ± 0.0000
    temp_match_rate: 0.0000 ± 0.0000
    full_matched: 0.0000 ± 0.0000
    full_mismatched: 116.0000 ± 0.0000
    full_match_rate: 0.0000 ± 0.0000
    accuracy: 0.0000 ± 0.0000
    average_timing_score: 0.0000 ± 0.0000
    average_temp_score: 1.0000 ± 0.0000
    average_full_score: 0.0000 ± 0.0000
    average_best_codebleu:
      average_CodeBLEU: 0.3059 ± 0.0000
      comb_7_CodeBLEU: 0.4894 ± 0.0000
      dataflow_match_score: 0.2759 ± 0.0000
      ngram_match_score: 0.0000 ± 0.0000
      syntax_match_score: 0.2235 ± 0.0000
      weighted_ngram_match_score: 0.0000 ± 0.0000
    average_best_levenshtein: 1092.9368 ± 8.7250
    average_best_normalized_levenshtein: 0.9644 ± 0.0002
    average_inference_time: 6.5531 ± 0.0101
  complex:
    count: 20.0000 ± 0.0000
    full_matches: 0.0000 ± 0.0000
    exact_code_matches: 0.0000 ± 0.0000
    exact_code_match_rate: 0.0000 ± 0.0000
    pv_exact_matched: 0.0000 ± 0.0000
    pv_exact_mismatched: 20.0000 ± 0.0000
    pv_exact_match_rate: 0.0000 ± 0.0000
    average_pv_match_rate: 0.0000 ± 0.0000
    average_pv_mismatch_rate: 100.0000 ± 0.0000
    timing_matched: 0.0000 ± 0.0000
    timing_mismatched: 20.0000 ± 0.0000
    timing_match_rate: 0.0000 ± 0.0000
    temp_matched: 0.0000 ± 0.0000
    temp_mismatched: 9.0000 ± 0.0000
    temp_match_rate: 0.0000 ± 0.0000
    full_matched: 0.0000 ± 0.0000
    full_mismatched: 20.0000 ± 0.0000
    full_match_rate: 0.0000 ± 0.0000
    accuracy: 0.0000 ± 0.0000
    average_timing_score: 0.0000 ± 0.0000
    average_temp_score: 0.5500 ± 0.0000
    average_full_score: 0.0000 ± 0.0000
    average_best_codebleu:
      average_CodeBLEU: 0.2513 ± 0.0000
      comb_7_CodeBLEU: 0.3836 ± 0.0000
      dataflow_match_score: 0.6310 ± 0.0000
      ngram_match_score: 0.0052 ± 0.0000
      syntax_match_score: 0.2125 ± 0.0000
      weighted_ngram_match_score: 0.0565 ± 0.0000
    average_best_levenshtein: 1777.6000 ± 0.0000
    average_best_normalized_levenshtein: 0.8919 ± 0.0000
    average_inference_time: 13.9890 ± 0.1178
==================================================
