q149 NOT_EQUAL, minidev-pg gpt-4-32k

The question

Please list the account types that are not eligible for loans, and the average income of residents in the district where the account is located exceeds $8000 but is no more than $9000.

the hint the set supplies: A11 represents the average salary; Salary and income share the similar meanings; when the account type = 'OWNER', it's eligible for loans

NOT_EQUAL states that these two statements disagree on this data under this rule. It does not state which of them is wrong.

read by hand, 2026-09-04: B harmless: one distinct row repeated; DISTINCT added by the prediction; a list under twice the answer with every row present

the prediction adds DISTINCT (1 row) where the gold repeats DISPONENT 461 times; the prediction is the cleaner answer

a maintainer's reading of this question, out of classification.json, copied from plans/reports/prediction-mode-260904-real-predictions/classification.json. It is not a verdict and nothing above it was computed from it.

The statements

gold

SELECT T3.type FROM district AS T1 INNER JOIN account AS T2 ON T1.district_id = T2.district_id INNER JOIN disp AS T3 ON T2.account_id = T3.account_id WHERE T3.type <> 'OWNER' AND T1.A11 BETWEEN 8000 AND 9000

this statement states no ordering of its own

sha256:e9359276e5948d4c18e2b5e34fc2efea767b70620a9cae29878a4941427d1721

second

SELECT DISTINCT disp.type
FROM disp
JOIN account ON disp.account_id = account.account_id
JOIN district ON account.district_id = district.district_id
WHERE disp.type != 'OWNER' AND district.a11 > 8000 AND district.a11 <= 9000

this statement states no ordering of its own

sha256:4ef3101dabd1d0857473f7c8809eb01c9f636d11fb95bb9707af6e25c9995299

The marked tokens are where the two texts differ. Two statements that differ everywhere can return the same rows, and two that differ in one token can return other rows; the verdict above is read off the results.

The rows they differ in

in gold, not in the prediction, 460 rows

from counterexample.json, 460 rows, up to 25 shown per side, 1 on this page

side	times	typetext
gold	460	DISPONENT

in the prediction, not in gold, 0 rows

from counterexample.json, 0 rows, up to 25 shown per side

side	typetext
no rows

What the benchmark would have said

BIRD's own check: 1

set(second_rows) == set(gold_rows), float4/float8 cells as Python float as psycopg2 returns them, numeric as Decimal

https://github.com/bird-bench/mini_dev/blob/main/evaluation/evaluation_ex.py

gold_rows: 461
second_rows: 1
gold_distinct_rows: 1
second_distinct_rows: 1

the test-suite check: 0

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

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: 461
second_rows: 1
gold_columns: 1
second_columns: 1

the class: multiplicity

The class states what makes these two results unequal under this rule, read off the two results and nothing else. It does not state which of the two statements is wrong.

The gold returned 461 rows and the prediction 1. 1 rows occur in both results at least once.

gold_types: ["text"]
second_types: ["text"]
multiset_equal: false
set_equal: true
order_equal: false
shorter_result_is_a_prefix: true

The results

gold, 461 rows

from counterexample.json, 461 rows, 25 on this page

typetext
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT

second, 1 row

from counterexample.json, 1 row

typetext
DISPONENT

The probes

A smell is a mechanical reason to read this gold statement again. It is a heuristic: it does not state that the statement is wrong, and a maintainer decides.

ordering-over-numeric-text not applicable

this statement orders by a text column holding only numbers, and ordering it as a number gives a different answer, so the gold may be sorting 9.5 above 10

the statement states no top level ORDER BY

what it measured

{
  "heuristic": true,
  "reason": "the statement states no top level ORDER BY"
}

arbitrary-cut not applicable

this statement cuts its result at a LIMIT that does not decide which rows come back, so a different but equally correct statement can return other rows and score zero

the statement states no LIMIT

what it measured

{
  "heuristic": true,
  "reason": "the statement states no LIMIT"
}

not-a-function-of-the-data quiet

rerun over the same rows in another physical order this statement gives another answer, so its result depends on how the rows are stored and not only on the data

what it measured

{
  "heuristic": true,
  "rule": "R-SET",
  "baseline_result_hash": "sha256:e9359276e5948d4c18e2b5e34fc2efea767b70620a9cae29878a4941427d1721",
  "baseline_result": {
    "columns": [
      {
        "name": "type",
        "declared_type": "text"
      }
    ],
    "row_count": 461,
    "truncated": false,
    "rows_shown": 10,
    "rows": [
      [
        {
          "type": "str",
          "value": "DISPONENT"
        }
      ],
      [
        {
          "type": "str",
          "value": "DISPONENT"
        }
      ],
      [
        {
          "type": "str",
          "value": "DISPONENT"
        }
      ],
      [
        {
          "type": "str",
          "value": "DISPONENT"
        }
      ],
      [
        {
          "type": "str",
          "value": "DISPONENT"
        }
      ],
      [
        {
          "type": "str",
          "value": "DISPONENT"
        }
      ],
      [
        {
          "type": "str",
          "value": "DISPONENT"
        }
      ],
      [
        {
          "type": "str",
          "value": "DISPONENT"
        }
      ],
      [
        {
          "type": "str",
          "value": "DISPONENT"
        }
      ],
      [
        {
          "type": "str",
          "value": "DISPONENT"
        }
      ]
    ],
    "result_hash": "sha256:e9359276e5948d4c18e2b5e34fc2efea767b70620a9cae29878a4941427d1721"
  },
  "planner_statistics": {
    "disp": {
      "last_analyze": "2026-09-14 12:50:59.481321+00",
      "last_autoanalyze": null,
      "n_mod_since_analyze": 0
    },
    "district": {
      "last_analyze": "2026-09-14 12:51:02.741239+00",
      "last_autoanalyze": null,
      "n_mod_since_analyze": 0
    },
    "account": {
      "last_analyze": "2026-09-14 12:50:59.337624+00",
      "last_autoanalyze": null,
      "n_mod_since_analyze": 0
    }
  },
  "shuffle": {
    "seed": "1",
    "row_limit": 300000,
    "tables": [
      "disp",
      "district",
      "account"
    ],
    "tables_not_shuffled": [],
    "tables_skipped_for_size": {
      "laptimes": 400524,
      "legalities": 427907,
      "posthistory": 303155,
      "trans": 1056320,
      "yearmonth": 383282
    },
    "tables_not_reached_by_a_copy": {}
  },
  "shuffled_copies": {
    "run": true,
    "verdict": "equal",
    "differs": false,
    "result_hash": "sha256:e9359276e5948d4c18e2b5e34fc2efea767b70620a9cae29878a4941427d1721",
    "result": {
      "columns": [
        {
          "name": "type",
          "declared_type": "text"
        }
      ],
      "row_count": 461,
      "truncated": false,
      "rows_shown": 10,
      "rows": [
        [
          {
            "type": "str",
            "value": "DISPONENT"
          }
        ],
        [
          {
            "type": "str",
            "value": "DISPONENT"
          }
        ],
        [
          {
            "type": "str",
            "value": "DISPONENT"
          }
        ],
        [
          {
            "type": "str",
            "value": "DISPONENT"
          }
        ],
        [
          {
            "type": "str",
            "value": "DISPONENT"
          }
        ],
        [
          {
            "type": "str",
            "value": "DISPONENT"
          }
        ],
        [
          {
            "type": "str",
            "value": "DISPONENT"
          }
        ],
        [
          {
            "type": "str",
            "value": "DISPONENT"
          }
        ],
        [
          {
            "type": "str",
            "value": "DISPONENT"
          }
        ],
        [
          {
            "type": "str",
            "value": "DISPONENT"
          }
        ]
      ],
      "result_hash": "sha256:e9359276e5948d4c18e2b5e34fc2efea767b70620a9cae29878a4941427d1721"
    }
  },
  "plan_variant": {
    "run": false,
    "reason": "the plan variant was not asked for"
  }
}

duplicate-full-row fired

this statement returns the same whole row more than once and never says DISTINCT, so a statement answering the same question once per row disagrees on multiplicity alone

from smells.json, 1 row

DISPONENT

what it measured

{
  "heuristic": true,
  "rows": 461,
  "distinct_rows": 1,
  "repeated_rows": 1,
  "largest_repeat": 461,
  "result_bounded": false,
  "distinct_stated": false,
  "set_operation": false,
  "repeats_of_the_rows_shown": [
    461
  ]
}

The evidence records

gold: evidence-gold.json

SELECT T3.type FROM district AS T1 INNER JOIN account AS T2 ON T1.district_id = T2.district_id INNER JOIN disp AS T3 ON T2.account_id = T3.account_id WHERE T3.type <> 'OWNER' AND T1.A11 BETWEEN 8000 AND 9000

statement read from: 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, 2024-06-19

result_hash sha256:e9359276e5948d4c18e2b5e34fc2efea767b70620a9cae29878a4941427d1721 recomputed from this JSON: match

record_hash sha256:c6d18a2bb482f5fbd079730076430967fb2b1b9b8d6fec4cfe47136467be74e1 recomputed from this JSON: match

the result this record holds, 461 rows, 50 of them here

from evidence-gold.json, 461 rows, 50 on this page

typetext
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT
DISPONENT

The whole result is in evidence-gold.json, beside this page.

what ran, and where

run: audit-6eb5069c-cd44-4dd7-9159-45303f9cfcba
executed at: 2026-09-14T12:53:32.317531+00:00
data as of: 2026-09-14T12:53:00.424166+00:00
backend at checkout: 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
backend that answered: 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
database role: auditor
replay rule: R-SET
question set version: sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
validator: audit:libpg_query-parse
checks run: parses_as_exactly_one_statement, the_one_statement_is_a_select, no_placeholder_without_a_bound_parameter
statement timeout: 120000 ms
rows: 461 rows

the session it ran under

engine: postgresql
time_zone: Etc/UTC
date_style: ISO, MDY
interval_style: postgres
extra_float_digits: 1
database_collation: en_US.utf8
work_mem: 4096
hash_mem_multiplier: 2

recorded beside them

statement_timeout: 0
server_version: 16.15 (Debian 16.15-1.pgdg13+2)
server_version_num: 160015
transaction_read_only: on
max_parallel_workers_per_gather: 2
server_encoding: UTF8
search_path: public
datlocprovider: c
daticulocale
datcollversion: 2.41

the rendering and the data

version: attestql/audit/4
numeric_scale: 6
timestamp_format: %Y-%m-%dT%H:%M:%S.%fZ
timezone: UTC
null_rendering: NULL
encoding: utf-8
schema digest: sha256:f949ff6a1ef6c97efe167623b75b738e390fef4f746f6df70c0a8ac212346f0b
source file sha256: sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.account: 4500
rows in public.disp: 5369
rows in public.district: 77

second: evidence-second.json

SELECT DISTINCT disp.type
FROM disp
JOIN account ON disp.account_id = account.account_id
JOIN district ON account.district_id = district.district_id
WHERE disp.type != 'OWNER' AND district.a11 > 8000 AND district.a11 <= 9000

statement read from: data/preds-pg/predict_mini_dev_gpt-4-32k_postgresql.json
digest: sha256:0fba1bfbeb487d641c8ae1e8bb01f762b2d29ddfb7c14dbd94e832f53cc10270
origin: https://raw.githubusercontent.com/bird-bench/mini_dev/b3d4bcbbae9a96934ad812551eb400c7a3b23c12/llm/exp_result/sql_output_kg/predict_mini_dev_gpt-4-32k_postgresql.json, 2024-06-19

result_hash sha256:4ef3101dabd1d0857473f7c8809eb01c9f636d11fb95bb9707af6e25c9995299 recomputed from this JSON: match

record_hash sha256:04082ae0b4091823d99d14a1f2495da9eac2c695407d288eff17483d258b6e91 recomputed from this JSON: match

the result this record holds, 1 row

from evidence-second.json, 1 row

typetext
DISPONENT

what ran, and where

run: audit-6eb5069c-cd44-4dd7-9159-45303f9cfcba
executed at: 2026-09-14T12:53:32.320653+00:00
data as of: 2026-09-14T12:53:00.424166+00:00
backend at checkout: 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
backend that answered: 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
database role: auditor
replay rule: R-SET
question set version: sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
validator: audit:libpg_query-parse
checks run: parses_as_exactly_one_statement, the_one_statement_is_a_select, no_placeholder_without_a_bound_parameter
statement timeout: 120000 ms
rows: 1 row

the session it ran under

engine: postgresql
time_zone: Etc/UTC
date_style: ISO, MDY
interval_style: postgres
extra_float_digits: 1
database_collation: en_US.utf8
work_mem: 4096
hash_mem_multiplier: 2

recorded beside them

statement_timeout: 0
server_version: 16.15 (Debian 16.15-1.pgdg13+2)
server_version_num: 160015
transaction_read_only: on
max_parallel_workers_per_gather: 2
server_encoding: UTF8
search_path: public
datlocprovider: c
daticulocale
datcollversion: 2.41

the rendering and the data

version: attestql/audit/4
numeric_scale: 6
timestamp_format: %Y-%m-%dT%H:%M:%S.%fZ
timezone: UTC
null_rendering: NULL
encoding: utf-8
schema digest: sha256:f949ff6a1ef6c97efe167623b75b738e390fef4f746f6df70c0a8ac212346f0b
source file sha256: sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.account: 4500
rows in public.disp: 5369
rows in public.district: 77

Running these again

gold

re-run this statement read-only against 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 under the session settings and over the data this record's fixture digest names, and compare the two results under R-SET

second

This question's run

run: audit-6eb5069c-cd44-4dd7-9159-45303f9cfcba
server: 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
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
replay rule: R-SET

the run this question belongs to

The JSON this page was rendered from

counterexample.json attestql/audit/counterexample/2
evidence-gold.json the gold's evidence record
evidence-second.json the prediction's evidence record
smells.json attestql/audit/smells/2

The question

The statements

◀ gold

▶ second

The rows they differ in

in gold, not in the prediction, 460 rows

in the prediction, not in gold, 0 rows

What the benchmark would have said

BIRD's own check: 1

the test-suite check: 0

the class: multiplicity

The results

The probes

ordering-over-numeric-text not applicable

arbitrary-cut not applicable

not-a-function-of-the-data quiet

duplicate-full-row fired

The evidence records

gold: evidence-gold.json

recorded beside them

second: evidence-second.json

recorded beside them

Running these again

gold

second

This question's run

The JSON this page was rendered from

gold

second