R-ORD GOLD-ONLY duplicate-full-row
european_football_2 · mini_dev_pg-00000-of-00001 from https://huggingface.co/datasets/birdsql/bird_mini_dev/resolve/f65faf4ae3b638c1fa6df1d3370c8d92c8366301/data/mini_dev_pg-00000-of-00001.json (commit f65faf4a, downloaded 2026-09-14)
What are the speed in which attacks are put together of the top 4 teams with the highest build Up Play Speed?
the hint the set supplies: speed in which attacks are put together refers to buildUpPlaySpeed;highest build up play speed refers to MAX(buildUpPlaySpeed)
This question was audited without a prediction beside it, so there is nothing to compare the gold with. The probes below read the gold alone.
SELECT t1.buildUpPlaySpeed FROM Team_Attributes AS t1 INNER JOIN Team AS t2 ON t1.team_api_id = t2.team_api_id ORDER BY t1.buildUpPlaySpeed ASC NULLS FIRST LIMIT 4sha256:968697dc8a2a01aac97b21860225d57dd94715eea7fddc4a67f60868fb702372
from evidence-gold.json, 4 rows
| buildupplayspeedint8 |
|---|
| 20 |
| 20 |
| 20 |
| 23 |
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.
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
no ORDER BY key resolves to a text column
{
"heuristic": true,
"reason": "no ORDER BY key resolves to a text column",
"keys": [
{
"key": "t1.buildupplayspeed",
"column": "team_attributes.buildupplayspeed",
"declared_type": "bigint",
"not_applicable": "the column is not declared as text"
}
]
}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
{
"heuristic": true,
"cut": 4,
"offset": 0,
"distinct_kept": false,
"unbounded_sql": "SELECT t1.buildupplayspeed, t1.buildupplayspeed AS attestql_ordering_key_0 FROM team_attributes t1 JOIN team t2 ON t1.team_api_id = t2.team_api_id ORDER BY t1.buildupplayspeed ASC NULLS FIRST",
"unbounded_rows": 1458,
"projected_columns": [
"buildupplayspeed"
],
"ordering_key_columns": [
"attestql_ordering_key_0"
],
"ordering_keys": [
{
"key": "t1.buildupplayspeed",
"direction": "asc",
"nulls": "first",
"nulls_first_in_effect": true,
"returned_rows_null_in_this_key": 0,
"fires": false
}
],
"case": null
}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
{
"heuristic": true,
"rule": "R-ORD",
"baseline_result_hash": "sha256:968697dc8a2a01aac97b21860225d57dd94715eea7fddc4a67f60868fb702372",
"baseline_result": {
"columns": [
{
"name": "buildupplayspeed",
"declared_type": "int8"
}
],
"row_count": 4,
"truncated": false,
"rows_shown": 4,
"rows": [
[
{
"type": "int",
"value": 20
}
],
[
{
"type": "int",
"value": 20
}
],
[
{
"type": "int",
"value": 20
}
],
[
{
"type": "int",
"value": 23
}
]
],
"result_hash": "sha256:968697dc8a2a01aac97b21860225d57dd94715eea7fddc4a67f60868fb702372"
},
"planner_statistics": {
"team_attributes": {
"last_analyze": "2026-09-14 12:51:04.628002+00",
"last_autoanalyze": null,
"n_mod_since_analyze": 0
},
"team": {
"last_analyze": "2026-09-14 12:51:04.719781+00",
"last_autoanalyze": null,
"n_mod_since_analyze": 0
}
},
"shuffle": {
"seed": "1",
"row_limit": 300000,
"tables": [
"team_attributes",
"team"
],
"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": "sha256:968697dc8a2a01aac97b21860225d57dd94715eea7fddc4a67f60868fb702372",
"result": {
"columns": [
{
"name": "buildupplayspeed",
"declared_type": "int8"
}
],
"row_count": 4,
"truncated": false,
"rows_shown": 4,
"rows": [
[
{
"type": "int",
"value": 20
}
],
[
{
"type": "int",
"value": 20
}
],
[
{
"type": "int",
"value": 20
}
],
[
{
"type": "int",
"value": 23
}
]
],
"result_hash": "sha256:968697dc8a2a01aac97b21860225d57dd94715eea7fddc4a67f60868fb702372"
}
},
"plan_variant": {
"run": false,
"reason": "the plan variant was not asked for"
}
}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
from smells.json, 1 row
| 20 |
{
"heuristic": true,
"rows": 4,
"distinct_rows": 2,
"repeated_rows": 1,
"largest_repeat": 3,
"result_bounded": false,
"distinct_stated": false,
"set_operation": false,
"repeats_of_the_rows_shown": [
3
]
}SELECT t1.buildUpPlaySpeed FROM Team_Attributes AS t1 INNER JOIN Team AS t2 ON t1.team_api_id = t2.team_api_id ORDER BY t1.buildUpPlaySpeed ASC NULLS FIRST LIMIT 4result_hash sha256:968697dc8a2a01aac97b21860225d57dd94715eea7fddc4a67f60868fb702372 recomputed from this JSON: match
record_hash sha256:e03b43c2a472fe721f178cba63e9b6b47068f0f2d2b1b3e9713663bc55b76c3d recomputed from this JSON: match
from evidence-gold.json, 4 rows
| buildupplayspeedint8 |
|---|
| 20 |
| 20 |
| 20 |
| 23 |
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-ORD