q900005 EQUAL, sandbox demo

The question

What are the tags, lightest first?

the hint the set supplies: the mass refers to main.y.mass

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 tag FROM main.y ORDER BY mass ASC

mass: ascending, nulls first

sha256:a62cb2d57d7399658fa87921cd0ba954a94549f8d58516c676e0948391b3ec11

second

SELECT t.tag FROM main.y AS t ORDER BY t.mass ASC

t.mass: ascending, nulls first

sha256:a62cb2d57d7399658fa87921cd0ba954a94549f8d58516c676e0948391b3ec11

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	tagTEXT
no rows

in the prediction, not in gold, 0 rows

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

side	tagTEXT
no rows

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: 3
second_rows: 3
gold_distinct_rows: 3
second_distinct_rows: 3

the test-suite check: 1

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: true
gold_rows: 3
second_rows: 3
gold_columns: 1
second_columns: 1

The results

gold, 3 rows

from counterexample.json, 3 rows

tagTEXT
lead
zinc
iron

second, 3 rows

from counterexample.json, 3 rows

tagTEXT
lead
zinc
iron

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 fired

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

from smells.json, 3 rows

lead

zinc

iron

what it measured

{
  "heuristic": true,
  "keys": [
    {
      "key": "mass",
      "column": "main.y.mass",
      "declared_type": "TEXT",
      "not_applicable": null,
      "census": {
        "rows": 3,
        "nulls": 0,
        "empty_strings": 0,
        "non_numeric": 0,
        "pattern": "^-?[0-9]+(\\.[0-9]+)?$"
      },
      "every_value_is_numeric": true,
      "cast_sql": "SELECT tag FROM main.y ORDER BY CAST(mass AS REAL) ASC",
      "verdict": "not_equal",
      "gold_result": {
        "columns": [
          {
            "name": "tag",
            "declared_type": "TEXT"
          }
        ],
        "row_count": 3,
        "truncated": false,
        "rows_shown": 3,
        "rows": [
          [
            {
              "type": "str",
              "value": "lead"
            }
          ],
          [
            {
              "type": "str",
              "value": "zinc"
            }
          ],
          [
            {
              "type": "str",
              "value": "iron"
            }
          ]
        ],
        "result_hash": "sha256:a62cb2d57d7399658fa87921cd0ba954a94549f8d58516c676e0948391b3ec11"
      },
      "cast_result": {
        "columns": [
          {
            "name": "tag",
            "declared_type": "TEXT"
          }
        ],
        "row_count": 3,
        "truncated": false,
        "rows_shown": 3,
        "rows": [
          [
            {
              "type": "str",
              "value": "iron"
            }
          ],
          [
            {
              "type": "str",
              "value": "lead"
            }
          ],
          [
            {
              "type": "str",
              "value": "zinc"
            }
          ]
        ],
        "result_hash": "sha256:1a66ab0ca97f310fad5b8658fedf77579f85c06a8d67bd0fa2ac89d51c5a27c9"
      }
    }
  ]
}

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 not applicable

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-ORD",
  "baseline_result_hash": "sha256:a62cb2d57d7399658fa87921cd0ba954a94549f8d58516c676e0948391b3ec11",
  "baseline_result": {
    "columns": [
      {
        "name": "tag",
        "declared_type": "TEXT"
      }
    ],
    "row_count": 3,
    "truncated": false,
    "rows_shown": 3,
    "rows": [
      [
        {
          "type": "str",
          "value": "lead"
        }
      ],
      [
        {
          "type": "str",
          "value": "zinc"
        }
      ],
      [
        {
          "type": "str",
          "value": "iron"
        }
      ]
    ],
    "result_hash": "sha256:a62cb2d57d7399658fa87921cd0ba954a94549f8d58516c676e0948391b3ec11"
  },
  "planner_statistics": {},
  "shuffle": {
    "seed": "1",
    "row_limit": 300000,
    "tables": [
      "main.y"
    ],
    "tables_not_shuffled": [
      "main.y"
    ],
    "tables_skipped_for_size": {},
    "tables_not_reached_by_a_copy": {
      "main.y": "the statement names this table's schema, and a name that states its schema is read from that schema whatever TEMP holds, so the rerun reads this table and not a copy of it"
    }
  },
  "shuffled_copies": {
    "run": false,
    "reason": "the shuffle reached no table this statement reads, so a rerun would read the same rows in the same order"
  },
  "plan_variant": {
    "run": false,
    "reason": "the plan variant was not asked for"
  }
}

duplicate-full-row quiet

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": 3,
  "distinct_rows": 3,
  "repeated_rows": 0,
  "largest_repeat": 1,
  "result_bounded": false,
  "distinct_stated": false,
  "set_operation": false
}

The evidence records

gold: evidence-gold.json

SELECT tag FROM main.y ORDER BY mass ASC

statement read from: demo/questions.json
digest: sha256:7ad58addc070b425cabfc9d67bbd9c95840253160cf3b73d672e9aeb4897f5ff
origin: the run was told none

result_hash sha256:a62cb2d57d7399658fa87921cd0ba954a94549f8d58516c676e0948391b3ec11 recomputed from this JSON: match

record_hash sha256:6ac6e29520c984a8082ee73f4c7189fdbe1f81d2de71a16df31d715451bb1b9e recomputed from this JSON: match

the result this record holds, 3 rows

from evidence-gold.json, 3 rows

tagTEXT
lead
zinc
iron

what ran, and where

run: audit-abdcc660-cce4-4f7a-a477-0b444aef6d1d
executed at: 2026-09-14T13:13:54.088298+00:00
data as of: 2026-09-14T13:13:54.071205+00:00
backend at checkout: SQLite 3.53.1 | file=/tmp/attestql-site-sandbox/demo/fixture.sqlite | size=69632
backend that answered: SQLite 3.53.1 | file=/tmp/attestql-site-sandbox/demo/fixture.sqlite | size=69632
database role: file
replay rule: R-ORD
question set version: sha256:7ad58addc070b425cabfc9d67bbd9c95840253160cf3b73d672e9aeb4897f5ff
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: 3 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: 3.53.1
encoding: UTF-8
reverse_unordered_selects: 0
query_only: 1
journal_mode: delete
data_version: 1
automatic_index: 1
compile_options: ATOMIC_INTRINSICS=1,COMPILER=clang-22.1.3,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_DBSTAT_VTAB,ENABLE_FTS3,ENABLE_FTS3_PARENTHESIS,ENABLE_FTS4,ENABLE_FTS5,ENABLE_GEOPOLY,ENABLE_MATH_FUNCTIONS,ENABLE_PERCENTILE,ENABLE_RTREE,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=32766,MAX_VDBE_OP=250000000,MAX_WORKER_THREADS=8,MUTEX_PTHREADS,SYSTEM_MALLOC,TEMP_STORE=1,THREADSAFE=1
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: sha256:51532f4381a4be11c44924a6d2d8176c661f8809afc0ebcc98e5f59be6f596f6
source file sha256
rows in main.y: 3

second: evidence-second.json

SELECT t.tag FROM main.y AS t ORDER BY t.mass ASC

statement read from: demo/predictions.json
digest: sha256:497ab56b10daa81359a51f3be419fe16e5b796b0cc33cb1aff6c24c9aa853780
origin: the run was told none

result_hash sha256:a62cb2d57d7399658fa87921cd0ba954a94549f8d58516c676e0948391b3ec11 recomputed from this JSON: match

record_hash sha256:451cb4c56d38aeb7029792a4615c998b5693b0cec83f84d977b58a0e15736f21 recomputed from this JSON: match

the result this record holds, 3 rows

from evidence-second.json, 3 rows

tagTEXT
lead
zinc
iron

what ran, and where

run: audit-abdcc660-cce4-4f7a-a477-0b444aef6d1d
executed at: 2026-09-14T13:13:54.088374+00:00
data as of: 2026-09-14T13:13:54.071205+00:00
backend at checkout: SQLite 3.53.1 | file=/tmp/attestql-site-sandbox/demo/fixture.sqlite | size=69632
backend that answered: SQLite 3.53.1 | file=/tmp/attestql-site-sandbox/demo/fixture.sqlite | size=69632
database role: file
replay rule: R-ORD
question set version: sha256:7ad58addc070b425cabfc9d67bbd9c95840253160cf3b73d672e9aeb4897f5ff
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: 3 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: 3.53.1
encoding: UTF-8
reverse_unordered_selects: 0
query_only: 1
journal_mode: delete
data_version: 1
automatic_index: 1
compile_options: ATOMIC_INTRINSICS=1,COMPILER=clang-22.1.3,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_DBSTAT_VTAB,ENABLE_FTS3,ENABLE_FTS3_PARENTHESIS,ENABLE_FTS4,ENABLE_FTS5,ENABLE_GEOPOLY,ENABLE_MATH_FUNCTIONS,ENABLE_PERCENTILE,ENABLE_RTREE,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=32766,MAX_VDBE_OP=250000000,MAX_WORKER_THREADS=8,MUTEX_PTHREADS,SYSTEM_MALLOC,TEMP_STORE=1,THREADSAFE=1
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: sha256:51532f4381a4be11c44924a6d2d8176c661f8809afc0ebcc98e5f59be6f596f6
source file sha256
rows in main.y: 3

Running these again

gold

re-run this statement read-only against SQLite 3.53.1 | file=/tmp/attestql-site-sandbox/demo/fixture.sqlite | size=69632 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-abdcc660-cce4-4f7a-a477-0b444aef6d1d
server: SQLite 3.53.1 | file=/tmp/attestql-site-sandbox/demo/fixture.sqlite | size=69632
question set: questions
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, 0 rows

in the prediction, not in gold, 0 rows

What the benchmark would have said

BIRD's own check: 1

the test-suite check: 1

The results

The probes

ordering-over-numeric-text fired

arbitrary-cut not applicable

not-a-function-of-the-data not applicable

duplicate-full-row 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