R-ORD GOLD-ONLY duplicate-full-row
european_football_2 · dev_20251106-00000-of-00001 from https://huggingface.co/datasets/birdsql/bird_sql_dev_20251106/resolve/3c11fb193e5439b338e23677fa0aae11e8b85db9/data/dev_20251106-00000-of-00001.json (commit 3c11fb19, downloaded 2026-09-07)
What are the speeds at which attacks are put together for the top 4 teams with the highest build Up Play Speed?
the hint the set supplies: speeds at 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 DESC, t1.team_api_id ASC LIMIT 4sha256:13555ee5996a99cf2ee0271ef2d1ff762e4e5ec4d386910efeb27635dedbf405
from evidence-gold.json, 4 rows
| buildUpPlaySpeedINTEGER |
|---|
| 80 |
| 78 |
| 78 |
| 77 |
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": "INTEGER",
"not_applicable": "the column is not declared as text"
},
{
"key": "t1.team_api_id",
"column": "Team_Attributes.team_api_id",
"declared_type": "INTEGER",
"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, t1.team_api_id AS attestql_ordering_key_1 FROM Team_Attributes AS t1 INNER JOIN Team AS t2 ON t1.team_api_id = t2.team_api_id ORDER BY t1.buildUpPlaySpeed DESC, t1.team_api_id ASC",
"unbounded_rows": 1458,
"projected_columns": [
"buildUpPlaySpeed"
],
"ordering_key_columns": [
"attestql_ordering_key_0",
"attestql_ordering_key_1"
],
"ordering_keys": [
{
"key": "t1.buildUpPlaySpeed",
"direction": "desc",
"nulls": "last",
"nulls_first_in_effect": false,
"returned_rows_null_in_this_key": 0,
"fires": false
},
{
"key": "t1.team_api_id",
"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": "sha256:13555ee5996a99cf2ee0271ef2d1ff762e4e5ec4d386910efeb27635dedbf405",
"baseline_result": {
"columns": [
{
"name": "buildUpPlaySpeed",
"declared_type": "INTEGER"
}
],
"row_count": 4,
"truncated": false,
"rows_shown": 4,
"rows": [
[
{
"type": "int",
"value": 80
}
],
[
{
"type": "int",
"value": 78
}
],
[
{
"type": "int",
"value": 78
}
],
[
{
"type": "int",
"value": 77
}
]
],
"result_hash": "sha256:13555ee5996a99cf2ee0271ef2d1ff762e4e5ec4d386910efeb27635dedbf405"
},
"planner_statistics": {},
"shuffle": {
"seed": "1",
"row_limit": 300000,
"tables": [
"Team_Attributes",
"Team"
],
"tables_not_shuffled": [],
"tables_skipped_for_size": {},
"tables_not_reached_by_a_copy": {}
},
"shuffled_copies": {
"run": true,
"verdict": "equal",
"differs": false,
"result_hash": "sha256:13555ee5996a99cf2ee0271ef2d1ff762e4e5ec4d386910efeb27635dedbf405",
"result": {
"columns": [
{
"name": "buildUpPlaySpeed",
"declared_type": "INTEGER"
}
],
"row_count": 4,
"truncated": false,
"rows_shown": 4,
"rows": [
[
{
"type": "int",
"value": 80
}
],
[
{
"type": "int",
"value": 78
}
],
[
{
"type": "int",
"value": 78
}
],
[
{
"type": "int",
"value": 77
}
]
],
"result_hash": "sha256:13555ee5996a99cf2ee0271ef2d1ff762e4e5ec4d386910efeb27635dedbf405"
}
},
"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
| 78 |
{
"heuristic": true,
"rows": 4,
"distinct_rows": 3,
"repeated_rows": 1,
"largest_repeat": 2,
"result_bounded": false,
"distinct_stated": false,
"set_operation": false,
"repeats_of_the_rows_shown": [
2
]
}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 DESC, t1.team_api_id ASC LIMIT 4result_hash sha256:13555ee5996a99cf2ee0271ef2d1ff762e4e5ec4d386910efeb27635dedbf405 recomputed from this JSON: match
record_hash sha256:97e2f6d767332d097a7560a147fa12f64eb0d58f3b4d29c6f8a2e835a312148d recomputed from this JSON: match
from evidence-gold.json, 4 rows
| buildUpPlaySpeedINTEGER |
|---|
| 80 |
| 78 |
| 78 |
| 77 |
re-run this statement read-only against SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/dev/dev_databases/european_football_2/european_football_2.sqlite | size=597754880 under the session settings and over the data this record's fixture digest names, and compare the two results under R-ORD