R-ORD GOLD-ONLY arbitrary-cut
formula_1 · 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 2026-09-08)
What is the surname of the driver with the best lap time in race number 19 in the second qualifying period?
the hint the set supplies: race number refers to raceId; second qualifying period refers to q2; best lap time refers to MIN(q2);
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.surname FROM qualifying AS T1 INNER JOIN drivers AS T2 ON T2.driverId = T1.driverId WHERE T1.raceId = 19 ORDER BY T1.q2 ASC NULLS FIRST LIMIT 1sha256:d59eb77c2f24c993fe26e83c88535e8193aa710e94a81ed438c648ec0bda4379
from evidence-gold.json, 1 row
| surnametext |
|---|
| Nakajima |
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.q2",
"column": "qualifying.q2",
"declared_type": "text",
"not_applicable": null,
"census": {
"rows": 6967,
"nulls": 3577,
"empty_strings": 23,
"non_numeric": 3367,
"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
from smells.json, 6 rows
| Bourdais | NULL |
| Sutil | NULL |
| Fisichella | NULL |
| Sato | NULL |
| Davidson | NULL |
| Nakajima | NULL |
{
"heuristic": true,
"cut": 1,
"offset": 0,
"distinct_kept": false,
"unbounded_sql": "SELECT t2.surname, t1.q2 AS attestql_ordering_key_0 FROM qualifying t1 JOIN drivers t2 ON t2.driverid = t1.driverid WHERE t1.raceid = 19 ORDER BY t1.q2 ASC NULLS FIRST",
"unbounded_rows": 22,
"projected_columns": [
"surname"
],
"ordering_key_columns": [
"attestql_ordering_key_0"
],
"ordering_keys": [
{
"key": "t1.q2",
"direction": "asc",
"nulls": "first",
"nulls_first_in_effect": true,
"returned_rows_null_in_this_key": 1,
"fires": true
}
],
"returned_rows_with_a_null_key": [
[
{
"type": "str",
"value": "Bourdais"
}
]
],
"tied_at_the_cut": {
"positions": [
0,
1,
2,
3,
4,
5
],
"tied_rows": 6,
"distinct_projected_answers": 6,
"rows": [
[
{
"type": "str",
"value": "Bourdais"
}
],
[
{
"type": "str",
"value": "Sutil"
}
],
[
{
"type": "str",
"value": "Fisichella"
}
],
[
{
"type": "str",
"value": "Sato"
}
],
[
{
"type": "str",
"value": "Davidson"
}
],
[
{
"type": "str",
"value": "Nakajima"
}
]
]
},
"case": "tie-at-the-cut, null-first"
}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:d59eb77c2f24c993fe26e83c88535e8193aa710e94a81ed438c648ec0bda4379",
"baseline_result": {
"columns": [
{
"name": "surname",
"declared_type": "text"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "str",
"value": "Nakajima"
}
]
],
"result_hash": "sha256:d59eb77c2f24c993fe26e83c88535e8193aa710e94a81ed438c648ec0bda4379"
},
"planner_statistics": {
"qualifying": {
"last_analyze": null,
"last_autoanalyze": null,
"n_mod_since_analyze": 6967
},
"drivers": {
"last_analyze": null,
"last_autoanalyze": null,
"n_mod_since_analyze": 840
}
},
"shuffle": {
"seed": "1",
"row_limit": 300000,
"tables": [
"qualifying",
"drivers"
],
"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:d59eb77c2f24c993fe26e83c88535e8193aa710e94a81ed438c648ec0bda4379",
"result": {
"columns": [
{
"name": "surname",
"declared_type": "text"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "str",
"value": "Nakajima"
}
]
],
"result_hash": "sha256:d59eb77c2f24c993fe26e83c88535e8193aa710e94a81ed438c648ec0bda4379"
}
},
"plan_variant": {
"run": false,
"reason": "the plan variant was not asked for"
}
}SELECT T2.surname FROM qualifying AS T1 INNER JOIN drivers AS T2 ON T2.driverId = T1.driverId WHERE T1.raceId = 19 ORDER BY T1.q2 ASC NULLS FIRST LIMIT 1result_hash sha256:d59eb77c2f24c993fe26e83c88535e8193aa710e94a81ed438c648ec0bda4379 recomputed from this JSON: match
record_hash sha256:e2182825f7dbe28e6cadb65ebf5d144900644699192f50e0f8ae285fc65d2c38 recomputed from this JSON: match
from evidence-gold.json, 1 row
| surnametext |
|---|
| Nakajima |
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