q391 NOT_EQUAL

The question

Among the Artifact cards, which are black color and comes with foreign languague translation?

the hint the set supplies: Artifact card refers to originalType = 'Artifact'; black color refers to colors = 'B'; foreign language refers to language in foreign_data

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 8 names; the prediction returns 80

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 T1.name FROM cards AS T1 INNER JOIN foreign_data AS T2 ON T1.uuid = T2.uuid WHERE T1.originalType = 'Artifact' AND T1.colors = 'B'

this statement states no ordering of its own

sha256:4ad873a2af3f3250499f57160503b0fffc347d4d01b1c3351acbffe709c6e40f

second

SELECT cards.name
FROM cards
JOIN foreign_data ON cards.uuid = foreign_data.uuid
WHERE cards.originaltype = 'Artifact' AND cards.colors = 'B' AND foreign_data.language IS NOT NULL

this statement states no ordering of its own

sha256:01e9a4e2a1c8f9375cb17f87529bfa214446a0d74e4b921fe927f8a27a7d5f7f

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	nametext
no rows

in the prediction, not in gold, 72 rows

from counterexample.json, 72 rows, up to 25 shown per side, 8 on this page

side	times	nametext
second	18	Executioner's Capsule
second	9	Witch's Cauldron
second	9	Bloodsoaked Altar
second	9	Wishclaw Talisman
second	7	Immortal Coil
second	7	Onyx Goblet
second	7	Scepter of Fugue
second	6	Netherborn Altar

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: 8
second_rows: 80
gold_distinct_rows: 8
second_distinct_rows: 8

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: 8
second_rows: 80
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 8 rows and the prediction 80. 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, 8 rows

from counterexample.json, 8 rows

nametext
Bloodsoaked Altar
Executioner's Capsule
Immortal Coil
Netherborn Altar
Onyx Goblet
Scepter of Fugue
Wishclaw Talisman
Witch's Cauldron

second, 80 rows

from counterexample.json, 80 rows, 25 on this page

nametext
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Witch's Cauldron
Witch's Cauldron
Witch's Cauldron
Witch's Cauldron
Witch's Cauldron

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": "sha256:4ad873a2af3f3250499f57160503b0fffc347d4d01b1c3351acbffe709c6e40f",
  "baseline_result": {
    "columns": [
      {
        "name": "name",
        "declared_type": "text"
      }
    ],
    "row_count": 8,
    "truncated": false,
    "rows_shown": 8,
    "rows": [
      [
        {
          "type": "str",
          "value": "Bloodsoaked Altar"
        }
      ],
      [
        {
          "type": "str",
          "value": "Executioner's Capsule"
        }
      ],
      [
        {
          "type": "str",
          "value": "Immortal Coil"
        }
      ],
      [
        {
          "type": "str",
          "value": "Netherborn Altar"
        }
      ],
      [
        {
          "type": "str",
          "value": "Onyx Goblet"
        }
      ],
      [
        {
          "type": "str",
          "value": "Scepter of Fugue"
        }
      ],
      [
        {
          "type": "str",
          "value": "Wishclaw Talisman"
        }
      ],
      [
        {
          "type": "str",
          "value": "Witch's Cauldron"
        }
      ]
    ],
    "result_hash": "sha256:4ad873a2af3f3250499f57160503b0fffc347d4d01b1c3351acbffe709c6e40f"
  },
  "planner_statistics": {
    "cards": {
      "last_analyze": null,
      "last_autoanalyze": "2026-09-08 05:19:16.814042+00",
      "n_mod_since_analyze": 0
    },
    "foreign_data": {
      "last_analyze": null,
      "last_autoanalyze": "2026-09-08 05:19:24.359437+00",
      "n_mod_since_analyze": 0
    }
  },
  "shuffle": {
    "seed": "1",
    "row_limit": 300000,
    "tables": [
      "cards",
      "foreign_data"
    ],
    "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": "sha256:4ad873a2af3f3250499f57160503b0fffc347d4d01b1c3351acbffe709c6e40f",
    "result": {
      "columns": [
        {
          "name": "name",
          "declared_type": "text"
        }
      ],
      "row_count": 8,
      "truncated": false,
      "rows_shown": 8,
      "rows": [
        [
          {
            "type": "str",
            "value": "Bloodsoaked Altar"
          }
        ],
        [
          {
            "type": "str",
            "value": "Executioner's Capsule"
          }
        ],
        [
          {
            "type": "str",
            "value": "Immortal Coil"
          }
        ],
        [
          {
            "type": "str",
            "value": "Netherborn Altar"
          }
        ],
        [
          {
            "type": "str",
            "value": "Onyx Goblet"
          }
        ],
        [
          {
            "type": "str",
            "value": "Scepter of Fugue"
          }
        ],
        [
          {
            "type": "str",
            "value": "Wishclaw Talisman"
          }
        ],
        [
          {
            "type": "str",
            "value": "Witch's Cauldron"
          }
        ]
      ],
      "result_hash": "sha256:4ad873a2af3f3250499f57160503b0fffc347d4d01b1c3351acbffe709c6e40f"
    }
  },
  "plan_variant": {
    "run": false,
    "reason": "the plan variant was not asked for"
  }
}

The evidence records

gold: evidence-gold.json

SELECT DISTINCT T1.name FROM cards AS T1 INNER JOIN foreign_data AS T2 ON T1.uuid = T2.uuid WHERE T1.originalType = 'Artifact' AND T1.colors = 'B'

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 sha256:4ad873a2af3f3250499f57160503b0fffc347d4d01b1c3351acbffe709c6e40f recomputed from this JSON: match

record_hash sha256:64a6a37495e41e34f8733c36a9d7d5be840b01903dc08182ac8c2836d4422088 recomputed from this JSON: match

the result this record holds, 8 rows

from evidence-gold.json, 8 rows

nametext
Bloodsoaked Altar
Executioner's Capsule
Immortal Coil
Netherborn Altar
Onyx Goblet
Scepter of Fugue
Wishclaw Talisman
Witch's Cauldron

what ran, and where

run: audit-a7e6b760-f8ad-479a-b956-9cd88ea91e18
executed at: 2026-09-08T05:21:33.243834+00:00
data as of: 2026-09-08T05:21:06.155844+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: 8 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: sha256:477eb72c0054cd8a05ed11d2e6c797effac5281aa1bc1ca22ad10880287698e7
source file sha256: sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.cards: 56822
rows in public.foreign_data: 229186

second: evidence-second.json

SELECT cards.name
FROM cards
JOIN foreign_data ON cards.uuid = foreign_data.uuid
WHERE cards.originaltype = 'Artifact' AND cards.colors = 'B' AND foreign_data.language IS NOT NULL

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 sha256:01e9a4e2a1c8f9375cb17f87529bfa214446a0d74e4b921fe927f8a27a7d5f7f recomputed from this JSON: match

record_hash sha256:4c49e5830d8538fa5b625c6a14345e3e2ca8038915d6df0ca8fee03621ab84a7 recomputed from this JSON: match

the result this record holds, 80 rows

from evidence-second.json, 80 rows

nametext
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Wishclaw Talisman
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Bloodsoaked Altar
Witch's Cauldron
Witch's Cauldron
Witch's Cauldron
Witch's Cauldron
Witch's Cauldron
Witch's Cauldron
Witch's Cauldron
Witch's Cauldron
Witch's Cauldron
Witch's Cauldron
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Immortal Coil
Immortal Coil
Immortal Coil
Immortal Coil
Immortal Coil
Immortal Coil
Immortal Coil
Immortal Coil
Onyx Goblet
Onyx Goblet
Onyx Goblet
Onyx Goblet
Onyx Goblet
Onyx Goblet
Onyx Goblet
Onyx Goblet
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Executioner's Capsule
Netherborn Altar
Netherborn Altar
Netherborn Altar
Netherborn Altar
Netherborn Altar
Netherborn Altar
Netherborn Altar
Scepter of Fugue
Scepter of Fugue
Scepter of Fugue
Scepter of Fugue
Scepter of Fugue
Scepter of Fugue
Scepter of Fugue
Scepter of Fugue

what ran, and where

run: audit-a7e6b760-f8ad-479a-b956-9cd88ea91e18
executed at: 2026-09-08T05:21:33.294641+00:00
data as of: 2026-09-08T05:21:06.155844+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: 80 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: sha256:477eb72c0054cd8a05ed11d2e6c797effac5281aa1bc1ca22ad10880287698e7
source file sha256: sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.cards: 56822
rows in public.foreign_data: 229186

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-a7e6b760-f8ad-479a-b956-9cd88ea91e18
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, 0 rows

in the prediction, not in gold, 72 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

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