{
  "generated_at": "2026-10-26T07:44:12+00:00",
  "model": "llama3.2:1b",
  "backend": "replay",
  "project": "local-llama-agent",
  "reference_version": 1,
  "current_version": 2,
  "tasks": 10,
  "spans": 96,
  "versions": {
    "v1": {
      "metrics": {
        "rows": 10,
        "judge_mean": 2.2,
        "latency_ms_mean": 773.66,
        "tool_success": 1.0,
        "json_invalid": 1,
        "refusals": 1,
        "tests_passed": 15,
        "tests_total": 20
      },
      "tests": {
        "total": 20,
        "passed": 15,
        "failed": 5,
        "tests": [
          {
            "name": "Mean value of 'output_chars: less or equal to 1200.0': Greater or Equal 1.000",
            "status": "SUCCESS",
            "description": "Share of passed 'output_chars: less or equal to 1200.0' row tests: Actual value 1.000 >= 1.000"
          },
          {
            "name": "Mean value of 'toxicity: equals clean': Greater or Equal 1.000",
            "status": "SUCCESS",
            "description": "Share of passed 'toxicity: equals clean' row tests: Actual value 1.000 >= 1.000"
          },
          {
            "name": "Mean value of 'refusal: equals answer': Greater or Equal 1.000",
            "status": "FAIL",
            "description": "Share of passed 'refusal: equals answer' row tests: Actual value 0.900 < 1.000"
          },
          {
            "name": "Mean value of 'judge_score: greater or equal to 3.0': Greater or Equal 1.000",
            "status": "FAIL",
            "description": "Share of passed 'judge_score: greater or equal to 3.0' row tests: Actual value 0.400 < 1.000"
          },
          {
            "name": "Row count in dataset: Greater 0.000",
            "status": "SUCCESS",
            "description": "Row count in dataset: Actual value 10.000 >= 0.000"
          },
          {
            "name": "Column 'output_chars' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'output_chars' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'output_words' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'output_words' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'output_sentences' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'output_sentences' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'sentiment_heuristic' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'sentiment_heuristic' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'toxicity' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'toxicity' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'refusal' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'refusal' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'pii' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'pii' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'json_valid' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'json_valid' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'judge_score' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'judge_score' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Mean value of 'latency_ms': Less or Equal 4000.000",
            "status": "SUCCESS",
            "description": "Mean value of 'latency_ms': Actual value 773.660 < 4000.000"
          },
          {
            "name": "Mean value of 'tool_success': Greater or Equal 0.900",
            "status": "SUCCESS",
            "description": "Mean value of 'tool_success': Actual value 1.000 >= 0.900"
          },
          {
            "name": "Column 'json_valid' categories 'invalid': Equal 0.000",
            "status": "FAIL",
            "description": "Column 'json_valid' categories 'invalid': Actual value 1.000 , but expected 0.000"
          },
          {
            "name": "Column 'refusal' categories 'refusal': Equal 0.000",
            "status": "FAIL",
            "description": "Column 'refusal' categories 'refusal': Actual value 1.000 , but expected 0.000"
          },
          {
            "name": "Column 'toxicity' categories 'flagged': Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'toxicity' categories 'flagged': Actual value 0.000  expected 0.000"
          },
          {
            "name": "Mean value of 'judge_score': Greater or Equal 3.500",
            "status": "FAIL",
            "description": "Mean value of 'judge_score': Actual value 2.200 < 3.500"
          }
        ]
      }
    },
    "v2": {
      "metrics": {
        "rows": 10,
        "judge_mean": 4.9,
        "latency_ms_mean": 925.53,
        "tool_success": 1.0,
        "json_invalid": 0,
        "refusals": 0,
        "tests_passed": 20,
        "tests_total": 20
      },
      "tests": {
        "total": 20,
        "passed": 20,
        "failed": 0,
        "tests": [
          {
            "name": "Mean value of 'output_chars: less or equal to 1200.0': Greater or Equal 1.000",
            "status": "SUCCESS",
            "description": "Share of passed 'output_chars: less or equal to 1200.0' row tests: Actual value 1.000 >= 1.000"
          },
          {
            "name": "Mean value of 'toxicity: equals clean': Greater or Equal 1.000",
            "status": "SUCCESS",
            "description": "Share of passed 'toxicity: equals clean' row tests: Actual value 1.000 >= 1.000"
          },
          {
            "name": "Mean value of 'refusal: equals answer': Greater or Equal 1.000",
            "status": "SUCCESS",
            "description": "Share of passed 'refusal: equals answer' row tests: Actual value 1.000 >= 1.000"
          },
          {
            "name": "Mean value of 'judge_score: greater or equal to 3.0': Greater or Equal 1.000",
            "status": "SUCCESS",
            "description": "Share of passed 'judge_score: greater or equal to 3.0' row tests: Actual value 1.000 >= 1.000"
          },
          {
            "name": "Row count in dataset: Greater 0.000",
            "status": "SUCCESS",
            "description": "Row count in dataset: Actual value 10.000 >= 0.000"
          },
          {
            "name": "Column 'output_chars' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'output_chars' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'output_words' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'output_words' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'output_sentences' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'output_sentences' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'sentiment_heuristic' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'sentiment_heuristic' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'toxicity' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'toxicity' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'refusal' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'refusal' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'pii' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'pii' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'json_valid' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'json_valid' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'judge_score' missing values: Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'judge_score' missing values: Actual value 0.000  expected 0.000"
          },
          {
            "name": "Mean value of 'latency_ms': Less or Equal 4000.000",
            "status": "SUCCESS",
            "description": "Mean value of 'latency_ms': Actual value 925.530 < 4000.000"
          },
          {
            "name": "Mean value of 'tool_success': Greater or Equal 0.900",
            "status": "SUCCESS",
            "description": "Mean value of 'tool_success': Actual value 1.000 >= 0.900"
          },
          {
            "name": "Column 'json_valid' categories 'invalid': Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'json_valid' categories 'invalid': Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'refusal' categories 'refusal': Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'refusal' categories 'refusal': Actual value 0.000  expected 0.000"
          },
          {
            "name": "Column 'toxicity' categories 'flagged': Equal 0.000",
            "status": "SUCCESS",
            "description": "Column 'toxicity' categories 'flagged': Actual value 0.000  expected 0.000"
          },
          {
            "name": "Mean value of 'judge_score': Greater or Equal 3.500",
            "status": "SUCCESS",
            "description": "Mean value of 'judge_score': Actual value 4.900 >= 3.500"
          }
        ]
      }
    }
  },
  "comparison_tests": {
    "total": 66,
    "passed": 42,
    "failed": 24,
    "tests": [
      {
        "name": "Mean value of 'output_chars: less or equal to 1200.0': Greater or Equal 1.000",
        "status": "SUCCESS",
        "description": "Share of passed 'output_chars: less or equal to 1200.0' row tests: Actual value 1.000 >= 1.000"
      },
      {
        "name": "Mean value of 'toxicity: equals clean': Greater or Equal 1.000",
        "status": "SUCCESS",
        "description": "Share of passed 'toxicity: equals clean' row tests: Actual value 1.000 >= 1.000"
      },
      {
        "name": "Mean value of 'refusal: equals answer': Greater or Equal 1.000",
        "status": "SUCCESS",
        "description": "Share of passed 'refusal: equals answer' row tests: Actual value 1.000 >= 1.000"
      },
      {
        "name": "Mean value of 'judge_score: greater or equal to 3.0': Greater or Equal 1.000",
        "status": "SUCCESS",
        "description": "Share of passed 'judge_score: greater or equal to 3.0' row tests: Actual value 1.000 >= 1.000"
      },
      {
        "name": "Row count in dataset: Equal 10.000 ± 1.000",
        "status": "SUCCESS",
        "description": "Row count in dataset: Actual value 10.000  expected 10.000 ± 1.000"
      },
      {
        "name": "Column 'output_chars' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'output_chars' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'output_chars' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'output_chars' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Minimal value of 'output_chars': Equal 20.000 ± 2.000",
        "status": "FAIL",
        "description": "Minimal value of 'output_chars': Actual value 6.000 , but expected 20.000 ± 2.000"
      },
      {
        "name": "Maximum value of 'output_chars': Equal 215.000 ± 21.500",
        "status": "FAIL",
        "description": "Maximum value of 'output_chars': Actual value 111.000 , but expected 215.000 ± 21.500"
      },
      {
        "name": "Mean value of 'output_chars': Equal 73.400 ± 7.340",
        "status": "FAIL",
        "description": "Mean value of 'output_chars': Actual value 48.700 , but expected 73.400 ± 7.340"
      },
      {
        "name": "Std value of 'output_chars': Equal 60.235 ± 6.024",
        "status": "FAIL",
        "description": "Std value of 'output_chars': Actual value 37.065 , but expected 60.235 ± 6.024"
      },
      {
        "name": "Quantile 0.25 of 'output_chars': Equal 34.500 ± 3.450",
        "status": "FAIL",
        "description": "Quantile 0.25 of 'output_chars': Actual value 15.500 , but expected 34.500 ± 3.450"
      },
      {
        "name": "Quantile 0.5 of 'output_chars': Equal 56.000 ± 5.600",
        "status": "FAIL",
        "description": "Quantile 0.5 of 'output_chars': Actual value 43.000 , but expected 56.000 ± 5.600"
      },
      {
        "name": "Quantile 0.75 of 'output_chars': Equal 85.250 ± 8.525",
        "status": "SUCCESS",
        "description": "Quantile 0.75 of 'output_chars': Actual value 78.500  expected 85.250 ± 8.525"
      },
      {
        "name": "Column 'output_words' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'output_words' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'output_words' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'output_words' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Minimal value of 'output_words': Equal 3.000 ± 0.300",
        "status": "FAIL",
        "description": "Minimal value of 'output_words': Actual value 1.000 , but expected 3.000 ± 0.300"
      },
      {
        "name": "Maximum value of 'output_words': Equal 36.000 ± 3.600",
        "status": "FAIL",
        "description": "Maximum value of 'output_words': Actual value 16.000 , but expected 36.000 ± 3.600"
      },
      {
        "name": "Mean value of 'output_words': Equal 10.700 ± 1.070",
        "status": "FAIL",
        "description": "Mean value of 'output_words': Actual value 6.400 , but expected 10.700 ± 1.070"
      },
      {
        "name": "Std value of 'output_words': Equal 9.922 ± 0.992",
        "status": "FAIL",
        "description": "Std value of 'output_words': Actual value 5.542 , but expected 9.922 ± 0.992"
      },
      {
        "name": "Quantile 0.25 of 'output_words': Equal 4.000 ± 0.400",
        "status": "FAIL",
        "description": "Quantile 0.25 of 'output_words': Actual value 1.500 , but expected 4.000 ± 0.400"
      },
      {
        "name": "Quantile 0.5 of 'output_words': Equal 8.000 ± 0.800",
        "status": "FAIL",
        "description": "Quantile 0.5 of 'output_words': Actual value 5.500 , but expected 8.000 ± 0.800"
      },
      {
        "name": "Quantile 0.75 of 'output_words': Equal 13.250 ± 1.325",
        "status": "FAIL",
        "description": "Quantile 0.75 of 'output_words': Actual value 8.000 , but expected 13.250 ± 1.325"
      },
      {
        "name": "Column 'output_sentences' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'output_sentences' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'output_sentences' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'output_sentences' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Minimal value of 'output_sentences': Equal 1.000 ± 0.100",
        "status": "SUCCESS",
        "description": "Minimal value of 'output_sentences': Actual value 1.000  expected 1.000 ± 0.100"
      },
      {
        "name": "Maximum value of 'output_sentences': Equal 1.000 ± 0.100",
        "status": "SUCCESS",
        "description": "Maximum value of 'output_sentences': Actual value 1.000  expected 1.000 ± 0.100"
      },
      {
        "name": "Mean value of 'output_sentences': Equal 1.000 ± 0.100",
        "status": "SUCCESS",
        "description": "Mean value of 'output_sentences': Actual value 1.000  expected 1.000 ± 0.100"
      },
      {
        "name": "Std value of 'output_sentences': Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Std value of 'output_sentences': Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Quantile 0.25 of 'output_sentences': Equal 1.000 ± 0.100",
        "status": "SUCCESS",
        "description": "Quantile 0.25 of 'output_sentences': Actual value 1.000  expected 1.000 ± 0.100"
      },
      {
        "name": "Quantile 0.5 of 'output_sentences': Equal 1.000 ± 0.100",
        "status": "SUCCESS",
        "description": "Quantile 0.5 of 'output_sentences': Actual value 1.000  expected 1.000 ± 0.100"
      },
      {
        "name": "Quantile 0.75 of 'output_sentences': Equal 1.000 ± 0.100",
        "status": "SUCCESS",
        "description": "Quantile 0.75 of 'output_sentences': Actual value 1.000  expected 1.000 ± 0.100"
      },
      {
        "name": "Column 'sentiment_heuristic' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'sentiment_heuristic' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'sentiment_heuristic' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'sentiment_heuristic' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Minimal value of 'sentiment_heuristic': Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Minimal value of 'sentiment_heuristic': Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Maximum value of 'sentiment_heuristic': Equal 1.000 ± 0.100",
        "status": "FAIL",
        "description": "Maximum value of 'sentiment_heuristic': Actual value 0.000 , but expected 1.000 ± 0.100"
      },
      {
        "name": "Mean value of 'sentiment_heuristic': Equal 0.100 ± 0.010",
        "status": "FAIL",
        "description": "Mean value of 'sentiment_heuristic': Actual value 0.000 , but expected 0.100 ± 0.010"
      },
      {
        "name": "Std value of 'sentiment_heuristic': Equal 0.316 ± 0.032",
        "status": "FAIL",
        "description": "Std value of 'sentiment_heuristic': Actual value 0.000 , but expected 0.316 ± 0.032"
      },
      {
        "name": "Quantile 0.25 of 'sentiment_heuristic': Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Quantile 0.25 of 'sentiment_heuristic': Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Quantile 0.5 of 'sentiment_heuristic': Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Quantile 0.5 of 'sentiment_heuristic': Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Quantile 0.75 of 'sentiment_heuristic': Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Quantile 0.75 of 'sentiment_heuristic': Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'toxicity' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'toxicity' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'toxicity' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'toxicity' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'refusal' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'refusal' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'refusal' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'refusal' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'pii' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'pii' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'pii' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'pii' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'json_valid' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'json_valid' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'json_valid' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'json_valid' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'judge_score' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'judge_score' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Column 'judge_score' missing values: Equal 0.000 ± 0.000",
        "status": "SUCCESS",
        "description": "Column 'judge_score' missing values: Actual value 0.000  expected 0.000 ± 0.000"
      },
      {
        "name": "Minimal value of 'judge_score': Equal 1.000 ± 0.100",
        "status": "FAIL",
        "description": "Minimal value of 'judge_score': Actual value 4.000 , but expected 1.000 ± 0.100"
      },
      {
        "name": "Maximum value of 'judge_score': Equal 4.000 ± 0.400",
        "status": "FAIL",
        "description": "Maximum value of 'judge_score': Actual value 5.000 , but expected 4.000 ± 0.400"
      },
      {
        "name": "Mean value of 'judge_score': Equal 2.200 ± 0.220",
        "status": "FAIL",
        "description": "Mean value of 'judge_score': Actual value 4.900 , but expected 2.200 ± 0.220"
      },
      {
        "name": "Std value of 'judge_score': Equal 1.229 ± 0.123",
        "status": "FAIL",
        "description": "Std value of 'judge_score': Actual value 0.316 , but expected 1.229 ± 0.123"
      },
      {
        "name": "Quantile 0.25 of 'judge_score': Equal 1.000 ± 0.100",
        "status": "FAIL",
        "description": "Quantile 0.25 of 'judge_score': Actual value 5.000 , but expected 1.000 ± 0.100"
      },
      {
        "name": "Quantile 0.5 of 'judge_score': Equal 2.000 ± 0.200",
        "status": "FAIL",
        "description": "Quantile 0.5 of 'judge_score': Actual value 5.000 , but expected 2.000 ± 0.200"
      },
      {
        "name": "Quantile 0.75 of 'judge_score': Equal 3.000 ± 0.300",
        "status": "FAIL",
        "description": "Quantile 0.75 of 'judge_score': Actual value 5.000 , but expected 3.000 ± 0.300"
      },
      {
        "name": "Mean value of 'row_tests_success_rate': Equal 0.825 ± 0.083",
        "status": "FAIL",
        "description": "Mean value of 'row_tests_success_rate': Actual value 1.000 , but expected 0.825 ± 0.083"
      },
      {
        "name": "Mean value of 'latency_ms': Less or Equal 4000.000",
        "status": "SUCCESS",
        "description": "Mean value of 'latency_ms': Actual value 925.530 < 4000.000"
      },
      {
        "name": "Quantile 0.95 of 'latency_ms': Equal 1344.285 ± 134.428",
        "status": "SUCCESS",
        "description": "Quantile 0.95 of 'latency_ms': Actual value 1335.075  expected 1344.285 ± 134.428"
      },
      {
        "name": "Mean value of 'tool_success': Greater or Equal 0.900",
        "status": "SUCCESS",
        "description": "Mean value of 'tool_success': Actual value 1.000 >= 0.900"
      },
      {
        "name": "Column 'json_valid' categories 'invalid': Equal 0.000",
        "status": "SUCCESS",
        "description": "Column 'json_valid' categories 'invalid': Actual value 0.000  expected 0.000"
      },
      {
        "name": "Column 'refusal' categories 'refusal': Equal 0.000",
        "status": "SUCCESS",
        "description": "Column 'refusal' categories 'refusal': Actual value 0.000  expected 0.000"
      },
      {
        "name": "Column 'toxicity' categories 'flagged': Equal 0.000",
        "status": "SUCCESS",
        "description": "Column 'toxicity' categories 'flagged': Actual value 0.000  expected 0.000"
      },
      {
        "name": "Mean value of 'judge_score': Greater or Equal 3.500",
        "status": "SUCCESS",
        "description": "Mean value of 'judge_score': Actual value 4.900 >= 3.500"
      }
    ]
  }
}
