q358 NOT_EQUAL, gpt-4-32k card

The question

What is the border color of card "Ancestor's Chosen"?

the hint the set supplies: name of card = 'Ancestor''s Chosen' ;

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 DISTINCT borderColor FROM cards WHERE name = 'Ancestor''s Chosen'

this statement states no ordering of its own

sha256:44b8638749207abe4201a8f1d9819038c3ee80b0f0f1c9f0fb6c519b1a6d3dff

second

SELECT borderColor 
FROM cards 
WHERE name = "Ancestor's Chosen"

this statement states no ordering of its own

sha256:3888b3bad45f80ce3944e62abd81307e2747a780fc59ee8b4d0f7868f7503e88

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	borderColorTEXT
no rows

in the prediction, not in gold, 3 rows

from counterexample.json, 3 rows, up to 25 shown per side, 1 on this page

side	times	borderColorTEXT
second	3	black

What the benchmark would have said

BIRD's own check: 1

set(second_rows) == set(gold_rows), REAL cells as Python float as sqlite3 returns them, so Python equality holds 1 == 1.0 == True as the benchmark's own scorer does

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

gold_rows: 1
second_rows: 4
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 SQLite's as sqlite3 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: 1
second_rows: 4
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 1 rows and the prediction 4. 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, 1 row

from counterexample.json, 1 row

borderColorTEXT
black

second, 4 rows

from counterexample.json, 4 rows

borderColorTEXT
black
black
black
black

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": "sha256:44b8638749207abe4201a8f1d9819038c3ee80b0f0f1c9f0fb6c519b1a6d3dff",
  "baseline_result": {
    "columns": [
      {
        "name": "borderColor",
        "declared_type": "TEXT"
      }
    ],
    "row_count": 1,
    "truncated": false,
    "rows_shown": 1,
    "rows": [
      [
        {
          "type": "str",
          "value": "black"
        }
      ]
    ],
    "result_hash": "sha256:44b8638749207abe4201a8f1d9819038c3ee80b0f0f1c9f0fb6c519b1a6d3dff"
  },
  "planner_statistics": {},
  "shuffle": {
    "seed": "1",
    "row_limit": 300000,
    "tables": [
      "cards"
    ],
    "tables_not_shuffled": [],
    "tables_skipped_for_size": {
      "legalities": 427907
    },
    "tables_not_reached_by_a_copy": {}
  },
  "shuffled_copies": {
    "run": true,
    "verdict": "equal",
    "differs": false,
    "result_hash": "sha256:44b8638749207abe4201a8f1d9819038c3ee80b0f0f1c9f0fb6c519b1a6d3dff",
    "result": {
      "columns": [
        {
          "name": "borderColor",
          "declared_type": "TEXT"
        }
      ],
      "row_count": 1,
      "truncated": false,
      "rows_shown": 1,
      "rows": [
        [
          {
            "type": "str",
            "value": "black"
          }
        ]
      ],
      "result_hash": "sha256:44b8638749207abe4201a8f1d9819038c3ee80b0f0f1c9f0fb6c519b1a6d3dff"
    }
  },
  "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": 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 borderColor FROM cards WHERE name = 'Ancestor''s Chosen'

statement read from: data/questions/mini_dev_sqlite.json
digest: sha256:4ba5fa8de55856222f484d380d2ba872b380bf79d825de70478e2120cb0fc43b
origin: https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_sqlite.json, 2024-06-19

result_hash sha256:44b8638749207abe4201a8f1d9819038c3ee80b0f0f1c9f0fb6c519b1a6d3dff recomputed from this JSON: match

record_hash sha256:5cce170337f2cf12090dd4fcfb065ef7f6a032275269d1b92cf7f3de562710da recomputed from this JSON: match

the result this record holds, 1 row

from evidence-gold.json, 1 row

borderColorTEXT
black

what ran, and where

run: audit-5ad59ebf-9f00-4ebb-8010-ae0200d479ef
executed at: 2026-09-14T11:07:30.414522+00:00
data as of: 2026-09-14T10:52:54.872414+00:00
backend at checkout: SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/minidev/dev_databases/card_games/card_games.sqlite | size=261820416
backend that answered: SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/minidev/dev_databases/card_games/card_games.sqlite | size=261820416
database role: file
replay rule: R-SET
question set version: sha256:4ba5fa8de55856222f484d380d2ba872b380bf79d825de70478e2120cb0fc43b
validator: audit:sqlglot-sqlite-parse
checks run: parses_as_exactly_one_statement, the_one_statement_is_a_select, no_placeholder_without_a_bound_parameter
statement timeout: 30000 ms
rows: 1 row

the session it ran under

engine: sqlite
time_zone: not stated by this engine
date_style: not stated by this engine
interval_style: not stated by this engine
extra_float_digits: not stated by this engine
database_collation: not stated by this engine
work_mem: not stated by this engine
hash_mem_multiplier: not stated by this engine

recorded beside them

sqlite_version: 3.53.4
encoding: UTF-8
reverse_unordered_selects: 0
query_only: 1
journal_mode: wal
data_version: 4
automatic_index: 1
compile_options: ATOMIC_INTRINSICS=1,COMPILER=clang-21.0.0,DEFAULT_AUTOVACUUM,DEFAULT_CACHE_SIZE=-2000,DEFAULT_FILE_FORMAT=4,DEFAULT_JOURNAL_SIZE_LIMIT=-1,DEFAULT_MMAP_SIZE=0,DEFAULT_PAGE_SIZE=4096,DEFAULT_PCACHE_INITSZ=20,DEFAULT_RECURSIVE_TRIGGERS,DEFAULT_SECTOR_SIZE=4096,DEFAULT_SYNCHRONOUS=2,DEFAULT_WAL_AUTOCHECKPOINT=1000,DEFAULT_WAL_SYNCHRONOUS=2,DEFAULT_WORKER_THREADS=0,DIRECT_OVERFLOW_READ,ENABLE_API_ARMOR,ENABLE_COLUMN_METADATA,ENABLE_DBSTAT_VTAB,ENABLE_FTS3,ENABLE_FTS3_PARENTHESIS,ENABLE_FTS5,ENABLE_GEOPOLY,ENABLE_MATH_FUNCTIONS,ENABLE_MEMORY_MANAGEMENT,ENABLE_PERCENTILE,ENABLE_PREUPDATE_HOOK,ENABLE_RTREE,ENABLE_SESSION,ENABLE_STAT4,ENABLE_UNLOCK_NOTIFY,MALLOC_SOFT_LIMIT=1024,MAX_ATTACHED=10,MAX_COLUMN=2000,MAX_COMPOUND_SELECT=500,MAX_DEFAULT_PAGE_SIZE=8192,MAX_EXPR_DEPTH=1000,MAX_FUNCTION_ARG=1000,MAX_LENGTH=1000000000,MAX_LIKE_PATTERN_LENGTH=50000,MAX_MMAP_SIZE=0x7fff0000,MAX_PAGE_COUNT=0xfffffffe,MAX_PAGE_SIZE=65536,MAX_SQL_LENGTH=1000000000,MAX_TRIGGER_DEPTH=1000,MAX_VARIABLE_NUMBER=250000,MAX_VDBE_OP=250000000,MAX_WORKER_THREADS=8,MUTEX_PTHREADS,SYSTEM_MALLOC,TEMP_STORE=1,THREADSAFE=1,USE_URI
collation_list: RTRIM,NOCASE,BINARY
case_sensitive_like: 0

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:cad4fa10a67ffced218e7362544d718459a124f4f941637c89385447f24f1821
source file sha256: sha256:c98bdb57fe7474da798b407785544b9af0daaad5d61fd21e2a73309493bc1227
rows in main.cards: 56822

second: evidence-second.json

SELECT borderColor 
FROM cards 
WHERE name = "Ancestor's Chosen"

statement read from: data/preds-sqlite/predict_mini_dev_gpt-4-32k_sqlite.json
digest: sha256:7ee53fcc67b9eaca363efb53ddb94dabd61526dafc09d835d832989e4911a1ca
origin: https://raw.githubusercontent.com/bird-bench/mini_dev/b3d4bcbbae9a96934ad812551eb400c7a3b23c12/llm/exp_result/sql_output_kg/predict_mini_dev_gpt-4-32k_sqlite.json, 2024-06-19

result_hash sha256:3888b3bad45f80ce3944e62abd81307e2747a780fc59ee8b4d0f7868f7503e88 recomputed from this JSON: match

record_hash sha256:a2fc33e4c0170a272e76dbbe96a45301b01cfcc96ced6aa3387f5f91c11c4a8a recomputed from this JSON: match

the result this record holds, 4 rows

from evidence-second.json, 4 rows

borderColorTEXT
black
black
black
black

what ran, and where

run: audit-5ad59ebf-9f00-4ebb-8010-ae0200d479ef
executed at: 2026-09-14T11:07:30.481470+00:00
data as of: 2026-09-14T10:52:54.872414+00:00
backend at checkout: SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/minidev/dev_databases/card_games/card_games.sqlite | size=261820416
backend that answered: SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/minidev/dev_databases/card_games/card_games.sqlite | size=261820416
database role: file
replay rule: R-SET
question set version: sha256:4ba5fa8de55856222f484d380d2ba872b380bf79d825de70478e2120cb0fc43b
validator: audit:sqlglot-sqlite-parse
checks run: parses_as_exactly_one_statement, the_one_statement_is_a_select, no_placeholder_without_a_bound_parameter
statement timeout: 30000 ms
rows: 4 rows

the session it ran under

engine: sqlite
time_zone: not stated by this engine
date_style: not stated by this engine
interval_style: not stated by this engine
extra_float_digits: not stated by this engine
database_collation: not stated by this engine
work_mem: not stated by this engine
hash_mem_multiplier: not stated by this engine

recorded beside them

sqlite_version: 3.53.4
encoding: UTF-8
reverse_unordered_selects: 0
query_only: 1
journal_mode: wal
data_version: 4
automatic_index: 1
compile_options: ATOMIC_INTRINSICS=1,COMPILER=clang-21.0.0,DEFAULT_AUTOVACUUM,DEFAULT_CACHE_SIZE=-2000,DEFAULT_FILE_FORMAT=4,DEFAULT_JOURNAL_SIZE_LIMIT=-1,DEFAULT_MMAP_SIZE=0,DEFAULT_PAGE_SIZE=4096,DEFAULT_PCACHE_INITSZ=20,DEFAULT_RECURSIVE_TRIGGERS,DEFAULT_SECTOR_SIZE=4096,DEFAULT_SYNCHRONOUS=2,DEFAULT_WAL_AUTOCHECKPOINT=1000,DEFAULT_WAL_SYNCHRONOUS=2,DEFAULT_WORKER_THREADS=0,DIRECT_OVERFLOW_READ,ENABLE_API_ARMOR,ENABLE_COLUMN_METADATA,ENABLE_DBSTAT_VTAB,ENABLE_FTS3,ENABLE_FTS3_PARENTHESIS,ENABLE_FTS5,ENABLE_GEOPOLY,ENABLE_MATH_FUNCTIONS,ENABLE_MEMORY_MANAGEMENT,ENABLE_PERCENTILE,ENABLE_PREUPDATE_HOOK,ENABLE_RTREE,ENABLE_SESSION,ENABLE_STAT4,ENABLE_UNLOCK_NOTIFY,MALLOC_SOFT_LIMIT=1024,MAX_ATTACHED=10,MAX_COLUMN=2000,MAX_COMPOUND_SELECT=500,MAX_DEFAULT_PAGE_SIZE=8192,MAX_EXPR_DEPTH=1000,MAX_FUNCTION_ARG=1000,MAX_LENGTH=1000000000,MAX_LIKE_PATTERN_LENGTH=50000,MAX_MMAP_SIZE=0x7fff0000,MAX_PAGE_COUNT=0xfffffffe,MAX_PAGE_SIZE=65536,MAX_SQL_LENGTH=1000000000,MAX_TRIGGER_DEPTH=1000,MAX_VARIABLE_NUMBER=250000,MAX_VDBE_OP=250000000,MAX_WORKER_THREADS=8,MUTEX_PTHREADS,SYSTEM_MALLOC,TEMP_STORE=1,THREADSAFE=1,USE_URI
collation_list: RTRIM,NOCASE,BINARY
case_sensitive_like: 0

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:cad4fa10a67ffced218e7362544d718459a124f4f941637c89385447f24f1821
source file sha256: sha256:c98bdb57fe7474da798b407785544b9af0daaad5d61fd21e2a73309493bc1227
rows in main.cards: 56822

Running these again

gold

re-run this statement read-only against SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/minidev/dev_databases/card_games/card_games.sqlite | size=261820416 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-5ad59ebf-9f00-4ebb-8010-ae0200d479ef
server: SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/minidev/dev_databases/card_games/card_games.sqlite | size=261820416
question set: mini_dev_sqlite from https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_sqlite.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, 3 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 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