q82 NOT_EQUAL, minidev-pg gpt-35-turbo

The question

What is the grade span offered in the school with the highest longitude?

the hint the set supplies: the highest longitude refers to the school with the maximum absolute longitude value.

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

The statements

gold

SELECT GSoffered FROM schools ORDER BY ABS(longitude) DESC NULLS LAST LIMIT 1

abs(longitude): descending, nulls last

sha256:d4d87fb991696c450e12529c6c599b392de69debe7b966d28ef8cccdb2210f15

second

SELECT schools.gsoffered
FROM schools
WHERE schools.longitude = (SELECT MAX(ABS(longitude)) FROM schools)

this statement states no ordering of its own

sha256:456e207fb6209dc2a7f54ce893f690a0066209033394a69baaa8b528446b72d9

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, 1 row

from counterexample.json, 1 row, up to 25 shown per side

side	gsofferedtext
gold	K-8

in the prediction, not in gold, 0 rows

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

side	gsofferedtext
no rows

What the benchmark would have said

BIRD's own check: 0

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: 1
second_rows: 0
gold_distinct_rows: 1
second_distinct_rows: 0

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: true
gold_rows: 1
second_rows: 0
gold_columns: 1
second_columns: 1

the class: other

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.

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

The results

gold, 1 row

from counterexample.json, 1 row

gsofferedtext
K-8

second, 0 rows

from counterexample.json, 0 rows

gsofferedtext
no rows

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

no ORDER BY key resolves to a text column

what it measured

{
  "heuristic": true,
  "reason": "no ORDER BY key resolves to a text column",
  "keys": [
    {
      "key": "abs(longitude)",
      "not_applicable": "the key is an expression and not a column"
    }
  ]
}

arbitrary-cut fired

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

from smells.json, 2 rows

NULL null	124.28481
K-8 str	124.28481

what it measured

{
  "heuristic": true,
  "cut": 1,
  "offset": 0,
  "distinct_kept": false,
  "unbounded_sql": "SELECT gsoffered, abs(longitude) AS attestql_ordering_key_0 FROM schools ORDER BY abs(longitude) DESC NULLS LAST",
  "unbounded_rows": 17686,
  "projected_columns": [
    "gsoffered"
  ],
  "ordering_key_columns": [
    "attestql_ordering_key_0"
  ],
  "ordering_keys": [
    {
      "key": "abs(longitude)",
      "direction": "desc",
      "nulls": "last",
      "nulls_first_in_effect": false,
      "returned_rows_null_in_this_key": 0,
      "fires": false
    }
  ],
  "tied_at_the_cut": {
    "positions": [
      0,
      1
    ],
    "tied_rows": 2,
    "distinct_projected_answers": 2,
    "rows": [
      [
        {
          "type": "null",
          "value": null
        }
      ],
      [
        {
          "type": "str",
          "value": "K-8"
        }
      ]
    ]
  },
  "case": "tie-at-the-cut"
}

not-a-function-of-the-data fired

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

from smells.json, 1 row

NULL

what it measured

{
  "heuristic": true,
  "rule": "R-ORD",
  "baseline_result_hash": "sha256:d4d87fb991696c450e12529c6c599b392de69debe7b966d28ef8cccdb2210f15",
  "baseline_result": {
    "columns": [
      {
        "name": "gsoffered",
        "declared_type": "text"
      }
    ],
    "row_count": 1,
    "truncated": false,
    "rows_shown": 1,
    "rows": [
      [
        {
          "type": "str",
          "value": "K-8"
        }
      ]
    ],
    "result_hash": "sha256:d4d87fb991696c450e12529c6c599b392de69debe7b966d28ef8cccdb2210f15"
  },
  "planner_statistics": {
    "schools": {
      "last_analyze": "2026-09-14 12:51:05.006896+00",
      "last_autoanalyze": null,
      "n_mod_since_analyze": 0
    }
  },
  "shuffle": {
    "seed": "1",
    "row_limit": 300000,
    "tables": [
      "schools"
    ],
    "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": "not_equal",
    "differs": true,
    "result_hash": "sha256:ad3cdf827326e0095f8ec41c8da708e1998813bd07b0af516c415d3f697cd2ce",
    "result": {
      "columns": [
        {
          "name": "gsoffered",
          "declared_type": "text"
        }
      ],
      "row_count": 1,
      "truncated": false,
      "rows_shown": 1,
      "rows": [
        [
          {
            "type": "null",
            "value": null
          }
        ]
      ],
      "result_hash": "sha256:ad3cdf827326e0095f8ec41c8da708e1998813bd07b0af516c415d3f697cd2ce"
    }
  },
  "plan_variant": {
    "run": false,
    "reason": "the plan variant was not asked for"
  }
}

duplicate-full-row not applicable

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

what it measured

{
  "heuristic": true,
  "rows": 1,
  "distinct_rows": 1,
  "repeated_rows": 0,
  "largest_repeat": 1,
  "result_bounded": false,
  "distinct_stated": false,
  "set_operation": false,
  "not_applicable": "a result of fewer than two rows has nothing to repeat"
}

The evidence records

gold: evidence-gold.json

SELECT GSoffered FROM schools ORDER BY ABS(longitude) DESC NULLS LAST LIMIT 1

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:d4d87fb991696c450e12529c6c599b392de69debe7b966d28ef8cccdb2210f15 recomputed from this JSON: match

record_hash sha256:59940c9bdd7f8ae961adb77ec6f6f62b662e2a0b57ca030a11bb5ba1bac5df4c recomputed from this JSON: match

the result this record holds, 1 row

from evidence-gold.json, 1 row

gsofferedtext
K-8

what ran, and where

run: audit-1c5c4146-3c91-4f05-b723-3cd43ed41d51
executed at: 2026-09-14T12:52:57.880928+00:00
data as of: 2026-09-14T12:52:24.461204+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-ORD
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: sha256:963c1162a015f21c6d18a54986e1b1822019b80a17de1cb3c10394c9ac75852c
source file sha256: sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.schools: 17686

second: evidence-second.json

SELECT schools.gsoffered
FROM schools
WHERE schools.longitude = (SELECT MAX(ABS(longitude)) FROM schools)

statement read from: data/preds-pg/predict_mini_dev_gpt-35-turbo_postgresql.json
digest: sha256:fa363fe3c3fc45d97cb47e6ec15133b291acccd750e5136b6e7b4d1c8d13a4be
origin: https://raw.githubusercontent.com/bird-bench/mini_dev/b3d4bcbbae9a96934ad812551eb400c7a3b23c12/llm/exp_result/sql_output_kg/predict_mini_dev_gpt-35-turbo_postgresql.json, 2024-06-19

result_hash sha256:456e207fb6209dc2a7f54ce893f690a0066209033394a69baaa8b528446b72d9 recomputed from this JSON: match

record_hash sha256:56b423f01b4f5186f2345cab4af49d1692251b0fbd90ca5ef8213513a25fe908 recomputed from this JSON: match

the result this record holds, 0 rows

from evidence-second.json, 0 rows

gsofferedtext
no rows

what ran, and where

run: audit-1c5c4146-3c91-4f05-b723-3cd43ed41d51
executed at: 2026-09-14T12:52:57.895240+00:00
data as of: 2026-09-14T12:52:24.461204+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-ORD
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: 0 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: sha256:963c1162a015f21c6d18a54986e1b1822019b80a17de1cb3c10394c9ac75852c
source file sha256: sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.schools: 17686

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-ORD

second

This question's run

run: audit-1c5c4146-3c91-4f05-b723-3cd43ed41d51
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-ORD

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, 1 row

in the prediction, not in gold, 0 rows

What the benchmark would have said

BIRD's own check: 0

the test-suite check: 0

the class: other

The results

The probes

ordering-over-numeric-text not applicable

arbitrary-cut fired

not-a-function-of-the-data fired

duplicate-full-row not applicable

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