{
  "format": "attestql/audit/counterexample/2",
  "question": {
    "question_id": "1340",
    "question_set": "mini_dev_postgresql from https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json",
    "question_text": "Calculate the difference of the total amount spent in all events by the Student_Club in year 2019 and 2020.",
    "evidence_text": "The first 4 strings of the event_date values in the event table can represent year; The difference of the total amount spent = SUBTRACT(spent where YEAR(event_date) = 2019, spent where YEAR(event_date) = 2020)"
  },
  "question_set_version": "sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab",
  "sources": {
    "gold": {
      "path": "data/questions/mini_dev_postgresql.json",
      "digest": "sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab",
      "origin": "https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json",
      "date": "2024-06-19"
    },
    "second": {
      "path": "data/preds-pg/predict_mini_dev_gpt-4-turbo_postgresql.json",
      "digest": "sha256:428fd115a67a76d6312ea205aab64764b5a09444587588eda442a94cfee65211",
      "origin": "https://raw.githubusercontent.com/bird-bench/mini_dev/b3d4bcbbae9a96934ad812551eb400c7a3b23c12/llm/exp_result/sql_output_kg/predict_mini_dev_gpt-4-turbo_postgresql.json",
      "date": "2024-06-19"
    }
  },
  "replay_rule": "R-SET",
  "verdict": {
    "result": "equal",
    "mismatched": [],
    "reading": "NOT_EQUAL states that these two statements disagree on this data under this rule. It does not state which of them is wrong."
  },
  "projection_names_differ": {
    "gold": [
      "num"
    ],
    "second": [
      "difference"
    ],
    "reading": "The two statements name their result columns differently. A projection is compared by position and declared type, so these names did not decide the verdict. They are part of the canonical rendering each result is hashed under, so the two result hashes differ with them."
  },
  "bird_ex": {
    "value": 1,
    "equal": true,
    "method": "set(second_rows) == set(gold_rows), float4/float8 cells as Python float as psycopg2 returns them, numeric as Decimal",
    "source": "https://github.com/bird-bench/mini_dev/blob/main/evaluation/evaluation_ex.py",
    "gold_rows": 1,
    "second_rows": 1,
    "gold_distinct_rows": 1,
    "second_distinct_rows": 1
  },
  "test_suite_ex": {
    "value": 1,
    "equal": true,
    "method": "result_eq: equal row counts and equal column counts, each row unordered as a quick rejection, then the two equal as a list when the gold text holds ORDER BY and as a multiset otherwise, under some permutation of the columns; DISTINCT is not stripped and re-executed, and the cells are PostgreSQL's as psycopg2 returns them",
    "source": "ruiqi-zhong/test-suite-sql-eval, exec_eval.py, result_eq, at commit 48cb78ec: https://github.com/ruiqi-zhong/test-suite-sql-eval/blob/48cb78ecf7f610620206283846c76751b18a1326/exec_eval.py",
    "order_matters": false,
    "gold_rows": 1,
    "second_rows": 1,
    "gold_columns": 1,
    "second_columns": 1
  },
  "mechanism": null,
  "gold": {
    "executed_sql": "SELECT SUM(CASE WHEN SUBSTR(T1.event_date, 1, 4) = '2019' THEN T2.spent ELSE 0 END) - SUM(CASE WHEN SUBSTR(T1.event_date, 1, 4) = '2020' THEN T2.spent ELSE 0 END) AS num FROM event AS T1 INNER JOIN budget AS T2 ON T1.event_id = T2.link_to_event",
    "own_ordering": [],
    "result": {
      "columns": [
        {
          "name": "num",
          "declared_type": "float4"
        }
      ],
      "row_count": 1,
      "truncated": false,
      "rows_shown": 1,
      "rows": [
        [
          {
            "type": "dec",
            "value": "2086.05"
          }
        ]
      ],
      "result_hash": "sha256:8ec9642f1f2d773f23ac5c701909c24d0e993619408c86f4e3ea41ebf18e2bca"
    },
    "record": "evidence-gold.json"
  },
  "second": {
    "executed_sql": "SELECT (SUM(CASE WHEN EXTRACT(YEAR FROM event_date::DATE) = 2019 THEN spent ELSE 0 END) - \n SUM(CASE WHEN EXTRACT(YEAR FROM event_date::DATE) = 2020 THEN spent ELSE 0 END)) AS difference\nFROM budget\nJOIN event ON budget.link_to_event = event.event_id",
    "own_ordering": [],
    "result": {
      "columns": [
        {
          "name": "difference",
          "declared_type": "float4"
        }
      ],
      "row_count": 1,
      "truncated": false,
      "rows_shown": 1,
      "rows": [
        [
          {
            "type": "dec",
            "value": "2086.05"
          }
        ]
      ],
      "result_hash": "sha256:db62f883ad92b5e987cbd313fa034b707da884c05015e4fe20aa8b1ad6360b5e"
    },
    "record": "evidence-second.json"
  },
  "canonical_ordering": [],
  "differing_rows": {
    "in_gold_not_in_second": [],
    "in_gold_not_in_second_total": 0,
    "in_second_not_in_gold": [],
    "in_second_not_in_gold_total": 0,
    "rows_shown_per_side": 25
  },
  "result_hashes": {
    "gold": "sha256:8ec9642f1f2d773f23ac5c701909c24d0e993619408c86f4e3ea41ebf18e2bca",
    "second": "sha256:db62f883ad92b5e987cbd313fa034b707da884c05015e4fe20aa8b1ad6360b5e"
  },
  "backend_identity": "PostgreSQL 16.15 (Debian 16.15-1.pgdg13+2) on aarch64-unknown-linux-gnu, compiled by gcc (Debian 14.2.0-19) 14.2.0, 64-bit | server=172.17.0.2/32:5432 | database=bird",
  "fixture": {
    "schema_digest": "sha256:06d01f2c3acde8cafe2e3f5e90d35a10d703b2b0d96962a645dd9c14b6769af0",
    "row_counts": {
      "public.budget": 52,
      "public.event": 42
    },
    "content_digests": {},
    "source_file_sha256": "sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec"
  },
  "run_id": "audit-7912134a-3f9b-4113-a6b6-ebaf8b6a2bc0"
}