R-ORD GOLD-ONLY arbitrary-cut
student_club · 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)
Which students manage to generate the highest income. State his/her full name along with the income source.
the hint the set supplies: full name refers to first_name, last_name; generate the highest income refers to the total income amount
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.first_name, T1.last_name, T2.source FROM member AS T1 INNER JOIN income AS T2 ON T1.member_id = T2.link_to_member GROUP BY T1.first_name, T1.last_name, T2.source ORDER BY SUM(T2.amount) DESC LIMIT 1sha256:c746a9491a920ab97d2da8eb378f92a9210fcd6867bef59d8778e7d58932abfa
from evidence-gold.json, 1 row
| first_nameTEXT | last_nameTEXT | sourceTEXT |
|---|---|---|
| Connor | Hilton | Dues |
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": "SUM(T2.amount)",
"not_applicable": "the key is an expression and not a column"
}
]
}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, 2 rows
| Connor | Hilton | Dues | 100 |
| Sacha | Harrison | Dues | 100 |
{
"heuristic": true,
"cut": 1,
"offset": 0,
"distinct_kept": false,
"unbounded_sql": "SELECT T1.first_name, T1.last_name, T2.source, SUM(T2.amount) AS attestql_ordering_key_0 FROM member AS T1 INNER JOIN income AS T2 ON T1.member_id = T2.link_to_member GROUP BY T1.first_name, T1.last_name, T2.source ORDER BY SUM(T2.amount) DESC",
"unbounded_rows": 31,
"projected_columns": [
"first_name",
"last_name",
"source"
],
"ordering_key_columns": [
"attestql_ordering_key_0"
],
"ordering_keys": [
{
"key": "SUM(T2.amount)",
"direction": "desc",
"nulls": "last",
"nulls_first_in_effect": false,
"returned_rows_null_in_this_key": 0,
"fires": false
}
],
"tied_at_the_cut": {
"positions": [
0,
1
],
"tied_rows": 2,
"distinct_projected_answers": 2,
"rows": [
[
{
"type": "str",
"value": "Connor"
},
{
"type": "str",
"value": "Hilton"
},
{
"type": "str",
"value": "Dues"
}
],
[
{
"type": "str",
"value": "Sacha"
},
{
"type": "str",
"value": "Harrison"
},
{
"type": "str",
"value": "Dues"
}
]
]
},
"case": "tie-at-the-cut"
}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:c746a9491a920ab97d2da8eb378f92a9210fcd6867bef59d8778e7d58932abfa",
"baseline_result": {
"columns": [
{
"name": "first_name",
"declared_type": "TEXT"
},
{
"name": "last_name",
"declared_type": "TEXT"
},
{
"name": "source",
"declared_type": "TEXT"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "str",
"value": "Connor"
},
{
"type": "str",
"value": "Hilton"
},
{
"type": "str",
"value": "Dues"
}
]
],
"result_hash": "sha256:c746a9491a920ab97d2da8eb378f92a9210fcd6867bef59d8778e7d58932abfa"
},
"planner_statistics": {},
"shuffle": {
"seed": "1",
"row_limit": 300000,
"tables": [
"member",
"income"
],
"tables_not_shuffled": [],
"tables_skipped_for_size": {},
"tables_not_reached_by_a_copy": {}
},
"shuffled_copies": {
"run": true,
"verdict": "equal",
"differs": false,
"result_hash": "sha256:c746a9491a920ab97d2da8eb378f92a9210fcd6867bef59d8778e7d58932abfa",
"result": {
"columns": [
{
"name": "first_name",
"declared_type": "TEXT"
},
{
"name": "last_name",
"declared_type": "TEXT"
},
{
"name": "source",
"declared_type": "TEXT"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "str",
"value": "Connor"
},
{
"type": "str",
"value": "Hilton"
},
{
"type": "str",
"value": "Dues"
}
]
],
"result_hash": "sha256:c746a9491a920ab97d2da8eb378f92a9210fcd6867bef59d8778e7d58932abfa"
}
},
"plan_variant": {
"run": false,
"reason": "the plan variant was not asked for"
}
}SELECT T1.first_name, T1.last_name, T2.source FROM member AS T1 INNER JOIN income AS T2 ON T1.member_id = T2.link_to_member GROUP BY T1.first_name, T1.last_name, T2.source ORDER BY SUM(T2.amount) DESC LIMIT 1result_hash sha256:c746a9491a920ab97d2da8eb378f92a9210fcd6867bef59d8778e7d58932abfa recomputed from this JSON: match
record_hash sha256:bbc4786d5cde0c1a78f4e9dfaecde9c64fc3aa34e81087d2be95a30197d58023 recomputed from this JSON: match
from evidence-gold.json, 1 row
| first_nameTEXT | last_nameTEXT | sourceTEXT |
|---|---|---|
| Connor | Hilton | Dues |
re-run this statement read-only against SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/dev/dev_databases/student_club/student_club.sqlite | size=2641920 under the session settings and over the data this record's fixture digest names, and compare the two results under R-ORD