q1035

R-SET NOT_EQUAL

european_football_2 · 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

The question

Give the team_fifa_api_id of teams with more than 50 but less than 60 build-up play speed.

the hint the set supplies: teams with more than 50 but less than 60 build-up play speed refers to buildUpPlaySpeed >50 AND buildUpPlaySpeed <60;

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: A a wrong answer the benchmark credited: another table or projection; a scalar repeated per row of an unrelated table; a list at least twice the answer's length where the question asks for the things, not the rows

gold DISTINCT over 161 ids; the prediction returns 356, so the count of teams is misstated

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 DISTINCT team_fifa_api_id FROM Team_Attributes WHERE buildUpPlaySpeed > 50 AND buildUpPlaySpeed < 60

this statement states no ordering of its own

sha256:1f7a83843d78e06ee35755d20fc3ce45b6c89aaf7eac10e855f720532e328e6b

second

SELECT team_fifa_api_id 
FROM Team_Attributes 
WHERE buildUpPlaySpeed > 50 AND buildUpPlaySpeed < 60

this statement states no ordering of its own

sha256:1d5fb5460cba8d3b98439e43146df64c792a0e1c0f82b8cf5e922b2b48ba88c2

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, 0 rows

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

side team_fifa_api_idint8
no rows

in the prediction, not in gold, 195 rows

from counterexample.json, 195 rows, up to 25 shown per side, 25 on this page

sidetimes team_fifa_api_idint8
second4 110569
second4 13
second4 15005
second4 1715
second4 242
second4 31
second4 4
second4 462
second4 900
second3 100879
second3 110329
second3 110724
second3 110832
second3 111239
second3 15
second3 165
second3 1832
second3 203
second3 229
second3 232
second3 237
second3 449
second3 450
second3 459
second3 468

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
161
second_rows
356
gold_distinct_rows
161
second_distinct_rows
161

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
161
second_rows
356
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.

how many rows each result holds, and how many rows both hold, from evidence-gold.json and evidence-second.json161 gold356 prediction161 rows both results hold
The gold returned 161 rows and the prediction 356. 161 rows occur in both results at least once.
gold_types
["int8"]
second_types
["int8"]
multiset_equal
false
set_equal
true
order_equal
false
shorter_result_is_a_prefix
false

The results

gold, 161 rows

from counterexample.json, 161 rows, 25 on this page

team_fifa_api_idint8
485
110744
477
71
1889
68
229
481
52
70
80
1971
112225
1861
378
874
450
10030
1799
900
110745
1750
462
237
69
second, 356 rows

from counterexample.json, 356 rows, 25 on this page

team_fifa_api_idint8
434
77
77
77
614
614
614
614
1901
1901
650
650
650
1861
229
229
229
229
111989
1
1
240
240
100409
100409

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": "sha256:1f7a83843d78e06ee35755d20fc3ce45b6c89aaf7eac10e855f720532e328e6b",
  "baseline_result": {
    "columns": [
      {
        "name": "team_fifa_api_id",
        "declared_type": "int8"
      }
    ],
    "row_count": 161,
    "truncated": false,
    "rows_shown": 10,
    "rows": [
      [
        {
          "type": "int",
          "value": 485
        }
      ],
      [
        {
          "type": "int",
          "value": 110744
        }
      ],
      [
        {
          "type": "int",
          "value": 477
        }
      ],
      [
        {
          "type": "int",
          "value": 71
        }
      ],
      [
        {
          "type": "int",
          "value": 1889
        }
      ],
      [
        {
          "type": "int",
          "value": 68
        }
      ],
      [
        {
          "type": "int",
          "value": 229
        }
      ],
      [
        {
          "type": "int",
          "value": 481
        }
      ],
      [
        {
          "type": "int",
          "value": 52
        }
      ],
      [
        {
          "type": "int",
          "value": 70
        }
      ]
    ],
    "result_hash": "sha256:1f7a83843d78e06ee35755d20fc3ce45b6c89aaf7eac10e855f720532e328e6b"
  },
  "planner_statistics": {
    "team_attributes": {
      "last_analyze": null,
      "last_autoanalyze": "2026-09-08 05:19:47.099723+00",
      "n_mod_since_analyze": 0
    }
  },
  "shuffle": {
    "seed": "1",
    "row_limit": 300000,
    "tables": [
      "team_attributes"
    ],
    "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:c7fede3477f21b2f77b749c41badaa7465b6edd31397c900e37f5f6da611de83",
    "result": {
      "columns": [
        {
          "name": "team_fifa_api_id",
          "declared_type": "int8"
        }
      ],
      "row_count": 161,
      "truncated": false,
      "rows_shown": 10,
      "rows": [
        [
          {
            "type": "int",
            "value": 1
          }
        ],
        [
          {
            "type": "int",
            "value": 3
          }
        ],
        [
          {
            "type": "int",
            "value": 4
          }
        ],
        [
          {
            "type": "int",
            "value": 7
          }
        ],
        [
          {
            "type": "int",
            "value": 10
          }
        ],
        [
          {
            "type": "int",
            "value": 13
          }
        ],
        [
          {
            "type": "int",
            "value": 15
          }
        ],
        [
          {
            "type": "int",
            "value": 17
          }
        ],
        [
          {
            "type": "int",
            "value": 19
          }
        ],
        [
          {
            "type": "int",
            "value": 21
          }
        ]
      ],
      "result_hash": "sha256:c7fede3477f21b2f77b749c41badaa7465b6edd31397c900e37f5f6da611de83"
    }
  },
  "plan_variant": {
    "run": false,
    "reason": "the plan variant was not asked for"
  }
}

The evidence records

gold: evidence-gold.json

SELECT DISTINCT team_fifa_api_id FROM Team_Attributes WHERE buildUpPlaySpeed > 50 AND buildUpPlaySpeed < 60
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 sha256:1f7a83843d78e06ee35755d20fc3ce45b6c89aaf7eac10e855f720532e328e6b recomputed from this JSON: match

record_hash sha256:64867de833fb54d2d1784a27acb20326d86df1d25d36eb5e74541dc5675346ef recomputed from this JSON: match

the result this record holds, 161 rows

from evidence-gold.json, 161 rows

team_fifa_api_idint8
485
110744
477
71
1889
68
229
481
52
70
80
1971
112225
1861
378
874
450
10030
1799
900
110745
1750
462
237
69
1824
1905
236
680
59
1848
1862
1844
100632
110374
665
452
200
682
674
44
88
100879
100087
82
111083
286
240
480
100741
1908
111989
650
15
48
457
1906
100805
19
81
244
160
232
77
1915
111087
21
468
3
17
1738
28
242
1796
111271
1832
456
165
1896
110502
100409
4
34
181
681
1747
1943
10020
10
673
1819
111974
472
86
110636
1913
144
1914
1904
1790
219
175
36
1739
31
1746
110329
109
873
13
1871
110569
459
62
246
1901
243
166
112512
206
46
110832
32
7
15005
247
1909
260
38
110749
479
1917
78
573
614
453
217
25
234
434
1902
111239
1867
1952
182
675
1860
1
106
449
1715
1853
110
110724
110747
100804
23
435
1907
898
203
what ran, and where
run
audit-eacac37d-7cc4-4d44-9121-67cecbf29b75
executed at
2026-09-08T05:21:57.951758+00:00
data as of
2026-09-08T05:21:47.344133+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
161 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
search_path
"$user", public
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
datlocprovider
c
daticulocale
datcollversion
2.41
the rendering and the data
version
attestql/audit/2
numeric_scale
6
timestamp_format
%Y-%m-%dT%H:%M:%S.%fZ
timezone
UTC
null_rendering
NULL
encoding
utf-8
schema digest
sha256:98bc0cba85d167faa0d5bb8e4db8801339559c93568b09cfd7c9a911f2c12123
source file sha256
sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.team_attributes
1458

second: evidence-second.json

SELECT team_fifa_api_id 
FROM Team_Attributes 
WHERE buildUpPlaySpeed > 50 AND buildUpPlaySpeed < 60
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 sha256:1d5fb5460cba8d3b98439e43146df64c792a0e1c0f82b8cf5e922b2b48ba88c2 recomputed from this JSON: match

record_hash sha256:3b107386040ad8ac098ebbf7535cad0b028d5651b16ff96d1147385d3ed95eb5 recomputed from this JSON: match

the result this record holds, 356 rows

from evidence-second.json, 356 rows

team_fifa_api_idint8
434
77
77
77
614
614
614
614
1901
1901
650
650
650
1861
229
229
229
229
111989
1
1
240
240
100409
100409
1906
1906
1848
1848
1848
32
21
675
1889
1889
234
88
88
88
88
3
3
3
160
4
4
4
4
4
59
23
1943
1896
1896
1896
378
378
378
1796
1796
450
450
450
450
78
78
1750
1750
1750
1867
110747
1799
1799
110502
242
242
242
242
242
110569
110569
110569
110569
110569
181
182
1824
1824
468
468
468
468
1746
452
10020
7
7
111271
111271
111271
1971
31
31
31
31
31
1915
1915
236
236
236
286
246
110374
110636
25
25
25
144
144
144
673
673
673
673
674
1860
110744
110744
110744
100632
100632
110832
110832
110832
110832
165
165
165
165
62
62
28
485
485
80
80
80
100879
100879
100879
100879
166
81
81
1952
1952
111239
111239
111239
111239
44
44
44
110745
110745
1832
1832
1832
1832
82
82
82
111083
110724
110724
110724
110724
472
1862
46
1738
1739
1739
873
1871
1871
1853
1853
1853
1844
1844
1844
217
573
453
453
10
10
219
219
219
68
68
69
69
69
69
1747
70
70
70
70
1904
71
13
13
13
13
13
112225
112225
477
682
682
479
100087
100087
100087
10030
1914
100741
200
111087
111087
1790
1790
247
15
15
15
15
456
86
86
480
449
449
449
449
243
243
457
203
203
203
203
1905
1902
52
874
874
874
1819
1819
111974
111974
111974
1913
1913
34
481
17
17
237
237
237
237
459
459
459
459
48
898
898
898
100805
110329
110329
110329
110329
100804
100804
680
680
232
232
232
232
106
106
260
260
260
1715
1715
1715
1715
1715
1908
462
462
462
462
462
206
206
36
36
36
1909
1909
665
665
665
665
38
38
109
109
19
681
681
1917
1917
1907
175
175
175
110
435
900
900
900
900
900
110749
110749
244
112512
112512
15005
15005
15005
15005
15005
what ran, and where
run
audit-eacac37d-7cc4-4d44-9121-67cecbf29b75
executed at
2026-09-08T05:21:57.954527+00:00
data as of
2026-09-08T05:21:47.344133+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
356 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
search_path
"$user", public
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
datlocprovider
c
daticulocale
datcollversion
2.41
the rendering and the data
version
attestql/audit/2
numeric_scale
6
timestamp_format
%Y-%m-%dT%H:%M:%S.%fZ
timezone
UTC
null_rendering
NULL
encoding
utf-8
schema digest
sha256:98bc0cba85d167faa0d5bb8e4db8801339559c93568b09cfd7c9a911f2c12123
source file sha256
sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.team_attributes
1458

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

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

This question's run

run
audit-eacac37d-7cc4-4d44-9121-67cecbf29b75
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