q1506

R-SET NOT_EQUAL

debit_card_specializing · 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

Please list the product descriptions of the transactions taken place in the gas stations in the Czech Republic.

the hint the set supplies: Czech Republic can be represented as the Country value in the gasstations table is 'CZE';

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 21 descriptions; the prediction returns 933

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 T3.Description FROM transactions_1k AS T1 INNER JOIN gasstations AS T2 ON T1.GasStationID = T2.GasStationID INNER JOIN products AS T3 ON T1.ProductID = T3.ProductID WHERE T2.Country = 'CZE'

this statement states no ordering of its own

sha256:3178e55fd6255473ea58802a9494725a7de45b2b2f216a3199f2ae61c6a2ea07

second

SELECT products.description
FROM transactions_1k
JOIN gasstations ON transactions_1k.gasstationid = gasstations.gasstationid
JOIN products ON transactions_1k.productid = products.productid
WHERE gasstations.country = 'CZE'

this statement states no ordering of its own

sha256:ff8f1a6d3a297b84677d6ab904e6939ad35a6d6373b8d7bbe5685bb1ba95c9f0

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 descriptiontext
no rows

in the prediction, not in gold, 912 rows

from counterexample.json, 912 rows, up to 25 shown per side, 19 on this page

sidetimes descriptiontext
second522 Nafta
second238 Natural
second40 Mytí vozidel
second26 Diesel +
second17 Nemrz.kapal.
second17 Provoz.nápl.
second11 Nafta Plus
second6 Autokosmet.
second6 Oleje,tuky
second5 Autoprísluš.
second5 Natural Plus
second3 Dalnic.popl.
second3 LPG
second3 Natural Spec
second3 Potraviny
second3 Zpr.nakupu
second2 Natural +
second1 Obcerstvení
second1 Zboží nesp.

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
21
second_rows
933
gold_distinct_rows
21
second_distinct_rows
21

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
21
second_rows
933
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.json21 gold933 prediction8 rows both results hold
The gold returned 21 rows and the prediction 933. 8 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
false

The results

gold, 21 rows

from counterexample.json, 21 rows

descriptiontext
Dalnic.popl.
Zpr.nakupu
Autoprísluš.
Zboží nesp.
Diesel +
Obcerstvení
Nemrz.kapal.
Nafta
Natural Plus
Autokosmet.
Natural
Natural +
Knihy,nov.
Provoz.nápl.
Oleje,tuky
Potraviny
Mytí vozidel
LPG
Additivum
Natural Spec
Nafta Plus
second, 933 rows

from counterexample.json, 933 rows, 25 on this page

descriptiontext
Nafta
Nafta
Provoz.nápl.
Natural
Nafta
Natural
Natural
Nemrz.kapal.
Nafta
Nafta
Nafta
Nafta
Natural
Natural
Oleje,tuky
Nafta
Nafta
Nafta
Nafta
Nafta
Nafta
Natural
Natural
Nafta
Natural

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": "sha256:3178e55fd6255473ea58802a9494725a7de45b2b2f216a3199f2ae61c6a2ea07",
  "baseline_result": {
    "columns": [
      {
        "name": "description",
        "declared_type": "text"
      }
    ],
    "row_count": 21,
    "truncated": false,
    "rows_shown": 10,
    "rows": [
      [
        {
          "type": "str",
          "value": "Dalnic.popl."
        }
      ],
      [
        {
          "type": "str",
          "value": "Zpr.nakupu"
        }
      ],
      [
        {
          "type": "str",
          "value": "Autoprísluš."
        }
      ],
      [
        {
          "type": "str",
          "value": "Zboží nesp."
        }
      ],
      [
        {
          "type": "str",
          "value": "Diesel +"
        }
      ],
      [
        {
          "type": "str",
          "value": "Obcerstvení"
        }
      ],
      [
        {
          "type": "str",
          "value": "Nemrz.kapal."
        }
      ],
      [
        {
          "type": "str",
          "value": "Nafta"
        }
      ],
      [
        {
          "type": "str",
          "value": "Natural Plus"
        }
      ],
      [
        {
          "type": "str",
          "value": "Autokosmet."
        }
      ]
    ],
    "result_hash": "sha256:3178e55fd6255473ea58802a9494725a7de45b2b2f216a3199f2ae61c6a2ea07"
  },
  "planner_statistics": {
    "products": {
      "last_analyze": "2026-09-14 12:51:04.229594+00",
      "last_autoanalyze": null,
      "n_mod_since_analyze": 0
    },
    "transactions_1k": {
      "last_analyze": "2026-09-14 12:51:04.722305+00",
      "last_autoanalyze": null,
      "n_mod_since_analyze": 0
    },
    "gasstations": {
      "last_analyze": "2026-09-14 12:51:02.743904+00",
      "last_autoanalyze": null,
      "n_mod_since_analyze": 0
    }
  },
  "shuffle": {
    "seed": "1",
    "row_limit": 300000,
    "tables": [
      "products",
      "transactions_1k",
      "gasstations"
    ],
    "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": "sha256:2af5e6651d84d6dbb31656f44f8d1ede2d4e2e1b99bd349e4c530357202f59df",
    "result": {
      "columns": [
        {
          "name": "description",
          "declared_type": "text"
        }
      ],
      "row_count": 21,
      "truncated": false,
      "rows_shown": 10,
      "rows": [
        [
          {
            "type": "str",
            "value": "Provoz.nápl."
          }
        ],
        [
          {
            "type": "str",
            "value": "Oleje,tuky"
          }
        ],
        [
          {
            "type": "str",
            "value": "Nemrz.kapal."
          }
        ],
        [
          {
            "type": "str",
            "value": "Potraviny"
          }
        ],
        [
          {
            "type": "str",
            "value": "Nafta"
          }
        ],
        [
          {
            "type": "str",
            "value": "Dalnic.popl."
          }
        ],
        [
          {
            "type": "str",
            "value": "Zpr.nakupu"
          }
        ],
        [
          {
            "type": "str",
            "value": "Autoprísluš."
          }
        ],
        [
          {
            "type": "str",
            "value": "Mytí vozidel"
          }
        ],
        [
          {
            "type": "str",
            "value": "LPG"
          }
        ]
      ],
      "result_hash": "sha256:2af5e6651d84d6dbb31656f44f8d1ede2d4e2e1b99bd349e4c530357202f59df"
    }
  },
  "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": 21,
  "distinct_rows": 21,
  "repeated_rows": 0,
  "largest_repeat": 1,
  "result_bounded": false,
  "distinct_stated": true,
  "set_operation": false,
  "not_applicable": "the statement states DISTINCT, so it cannot repeat a row"
}

The evidence records

gold: evidence-gold.json

SELECT DISTINCT T3.Description FROM transactions_1k AS T1 INNER JOIN gasstations AS T2 ON T1.GasStationID = T2.GasStationID INNER JOIN products AS T3 ON T1.ProductID = T3.ProductID WHERE T2.Country = 'CZE'
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 sha256:3178e55fd6255473ea58802a9494725a7de45b2b2f216a3199f2ae61c6a2ea07 recomputed from this JSON: match

record_hash sha256:0268088f53ea9659b364f6e8d749a2e48624588a55b1230625d4481a644e65fd recomputed from this JSON: match

the result this record holds, 21 rows

from evidence-gold.json, 21 rows

descriptiontext
Dalnic.popl.
Zpr.nakupu
Autoprísluš.
Zboží nesp.
Diesel +
Obcerstvení
Nemrz.kapal.
Nafta
Natural Plus
Autokosmet.
Natural
Natural +
Knihy,nov.
Provoz.nápl.
Oleje,tuky
Potraviny
Mytí vozidel
LPG
Additivum
Natural Spec
Nafta Plus
what ran, and where
run
audit-1c5c4146-3c91-4f05-b723-3cd43ed41d51
executed at
2026-09-14T12:52:31.733244+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-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
21 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:e38de47890e707d52287f419604502dc89a2bf6852fac9024c95a83b8f4207ac
source file sha256
sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.gasstations
5716
rows in public.products
591
rows in public.transactions_1k
1000

second: evidence-second.json

SELECT products.description
FROM transactions_1k
JOIN gasstations ON transactions_1k.gasstationid = gasstations.gasstationid
JOIN products ON transactions_1k.productid = products.productid
WHERE gasstations.country = 'CZE'
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:ff8f1a6d3a297b84677d6ab904e6939ad35a6d6373b8d7bbe5685bb1ba95c9f0 recomputed from this JSON: match

record_hash sha256:bba9ed9d2910ccc7f3252e42f32ad9ee4473dea1632c0b11b8517c5a7fb06e14 recomputed from this JSON: match

the result this record holds, 933 rows, 50 of them here

from evidence-second.json, 933 rows, 50 on this page

descriptiontext
Nafta
Nafta
Provoz.nápl.
Natural
Nafta
Natural
Natural
Nemrz.kapal.
Nafta
Nafta
Nafta
Nafta
Natural
Natural
Oleje,tuky
Nafta
Nafta
Nafta
Nafta
Nafta
Nafta
Natural
Natural
Nafta
Natural
Nafta
Provoz.nápl.
Nafta
Nafta
Diesel +
Nafta
Nafta
Natural
Nafta
Nafta
Natural
Nafta
Nafta
Natural
Nafta
Nafta
Nafta
Nafta
Nafta
LPG
Nafta
Nafta
Nafta
Mytí vozidel
Natural

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

what ran, and where
run
audit-1c5c4146-3c91-4f05-b723-3cd43ed41d51
executed at
2026-09-14T12:52:31.736991+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-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
933 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:e38de47890e707d52287f419604502dc89a2bf6852fac9024c95a83b8f4207ac
source file sha256
sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.gasstations
5716
rows in public.products
591
rows in public.transactions_1k
1000

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-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-SET

the run this question belongs to

The JSON this page was rendered from