R-ORD GOLD-ONLY duplicate-full-row
formula_1 · 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)
List out top 10 Spanish drivers who were born before 1982 and have the latest lap time.
the hint the set supplies: born before 1982 refers to year(dob) < 1982; latest lap time refers to Max(time);
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 T2.driverId FROM pitStops AS T1 INNER JOIN drivers AS T2 on T1.driverId = T2.driverId WHERE T2.nationality = 'Spanish' AND STRFTIME('%Y', T2.dob) < '1982' ORDER BY T1.time DESC LIMIT 10sha256:791008d01612baabd195eec6f2fab8bb45e1f10b675f33d0c080b5c78a301006
from evidence-gold.json, 10 rows
| driverIdINTEGER |
|---|
| 4 |
| 37 |
| 4 |
| 37 |
| 4 |
| 4 |
| 4 |
| 4 |
| 4 |
| 37 |
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
{
"heuristic": true,
"keys": [
{
"key": "T1.time",
"column": "pitStops.time",
"declared_type": "TEXT",
"not_applicable": null,
"census": {
"rows": 6070,
"nulls": 0,
"empty_strings": 0,
"non_numeric": 6070,
"pattern": "^-?[0-9]+(\\.[0-9]+)?$"
},
"every_value_is_numeric": false
}
]
}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": 10,
"offset": 0,
"distinct_kept": false,
"unbounded_sql": "SELECT T2.driverId, T1.time AS attestql_ordering_key_0 FROM pitStops AS T1 INNER JOIN drivers AS T2 ON T1.driverId = T2.driverId WHERE T2.nationality = 'Spanish' AND STRFTIME('%Y', T2.dob) < '1982' ORDER BY T1.time DESC",
"unbounded_rows": 309,
"projected_columns": [
"driverId"
],
"ordering_key_columns": [
"attestql_ordering_key_0"
],
"ordering_keys": [
{
"key": "T1.time",
"direction": "desc",
"nulls": "last",
"nulls_first_in_effect": false,
"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": "sha256:791008d01612baabd195eec6f2fab8bb45e1f10b675f33d0c080b5c78a301006",
"baseline_result": {
"columns": [
{
"name": "driverId",
"declared_type": "INTEGER"
}
],
"row_count": 10,
"truncated": false,
"rows_shown": 10,
"rows": [
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 37
}
],
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 37
}
],
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 37
}
]
],
"result_hash": "sha256:791008d01612baabd195eec6f2fab8bb45e1f10b675f33d0c080b5c78a301006"
},
"planner_statistics": {},
"shuffle": {
"seed": "1",
"row_limit": 300000,
"tables": [
"pitStops",
"drivers"
],
"tables_not_shuffled": [],
"tables_skipped_for_size": {
"lapTimes": 420369
},
"tables_not_reached_by_a_copy": {}
},
"shuffled_copies": {
"run": true,
"verdict": "equal",
"differs": false,
"result_hash": "sha256:791008d01612baabd195eec6f2fab8bb45e1f10b675f33d0c080b5c78a301006",
"result": {
"columns": [
{
"name": "driverId",
"declared_type": "INTEGER"
}
],
"row_count": 10,
"truncated": false,
"rows_shown": 10,
"rows": [
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 37
}
],
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 37
}
],
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 4
}
],
[
{
"type": "int",
"value": 37
}
]
],
"result_hash": "sha256:791008d01612baabd195eec6f2fab8bb45e1f10b675f33d0c080b5c78a301006"
}
},
"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, 2 rows
| 4 |
| 37 |
{
"heuristic": true,
"rows": 10,
"distinct_rows": 2,
"repeated_rows": 2,
"largest_repeat": 7,
"result_bounded": false,
"distinct_stated": false,
"set_operation": false,
"repeats_of_the_rows_shown": [
7,
3
]
}SELECT T2.driverId FROM pitStops AS T1 INNER JOIN drivers AS T2 on T1.driverId = T2.driverId WHERE T2.nationality = 'Spanish' AND STRFTIME('%Y', T2.dob) < '1982' ORDER BY T1.time DESC LIMIT 10result_hash sha256:791008d01612baabd195eec6f2fab8bb45e1f10b675f33d0c080b5c78a301006 recomputed from this JSON: match
record_hash sha256:7e18a0b2460f562095c513e808891ef5dfe3ab16bcd5df611f17f2b553bbe3ef recomputed from this JSON: match
from evidence-gold.json, 10 rows
| driverIdINTEGER |
|---|
| 4 |
| 37 |
| 4 |
| 37 |
| 4 |
| 4 |
| 4 |
| 4 |
| 4 |
| 37 |
re-run this statement read-only against SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/dev/dev_databases/formula_1/formula_1.sqlite | size=22360064 under the session settings and over the data this record's fixture digest names, and compare the two results under R-ORD