R-ORD GOLD-ONLY arbitrary-cut
student_club · mini_dev_postgresql from https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json
Which event has the lowest cost?
the hint the set supplies: event refers to event_name; lowest cost means MIN(cost)
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.event_name FROM event AS T1 INNER JOIN budget AS T2 ON T1.event_id = T2.link_to_event INNER JOIN expense AS T3 ON T2.budget_id = T3.link_to_budget ORDER BY T3.cost NULLS FIRST LIMIT 1sha256:56406324bb087daab39eca2d80eb40a285f0ba16585dc9ae96e7e4c82cf0b7c5
from evidence-gold.json, 1 row
| event_nametext |
|---|
| November Speaker |
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": "t3.cost",
"column": "expense.cost",
"declared_type": "real",
"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
from smells.json, 3 rows
| September Speaker | 6 |
| November Speaker | 6 |
| October Speaker | 6 |
{
"heuristic": true,
"cut": 1,
"offset": 0,
"distinct_kept": false,
"unbounded_sql": "SELECT t1.event_name, t3.cost AS attestql_ordering_key_0 FROM event t1 JOIN budget t2 ON t1.event_id = t2.link_to_event JOIN expense t3 ON t2.budget_id = t3.link_to_budget ORDER BY t3.cost NULLS FIRST",
"unbounded_rows": 32,
"projected_columns": [
"event_name"
],
"ordering_key_columns": [
"attestql_ordering_key_0"
],
"ordering_keys": [
{
"key": "t3.cost",
"direction": "asc",
"nulls": "first",
"nulls_first_in_effect": true,
"returned_rows_null_in_this_key": 0,
"fires": false
}
],
"tied_at_the_cut": {
"positions": [
0,
1,
2
],
"tied_rows": 3,
"distinct_projected_answers": 3,
"rows": [
[
{
"type": "str",
"value": "September Speaker"
}
],
[
{
"type": "str",
"value": "November Speaker"
}
],
[
{
"type": "str",
"value": "October Speaker"
}
]
]
},
"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": "sha256:56406324bb087daab39eca2d80eb40a285f0ba16585dc9ae96e7e4c82cf0b7c5",
"baseline_result": {
"columns": [
{
"name": "event_name",
"declared_type": "text"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "str",
"value": "November Speaker"
}
]
],
"result_hash": "sha256:56406324bb087daab39eca2d80eb40a285f0ba16585dc9ae96e7e4c82cf0b7c5"
},
"planner_statistics": {
"expense": {
"last_analyze": null,
"last_autoanalyze": null,
"n_mod_since_analyze": 32
},
"event": {
"last_analyze": null,
"last_autoanalyze": null,
"n_mod_since_analyze": 42
},
"budget": {
"last_analyze": null,
"last_autoanalyze": null,
"n_mod_since_analyze": 52
}
},
"shuffle": {
"seed": "1",
"row_limit": 300000,
"tables": [
"expense",
"event",
"budget"
],
"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": "sha256:56406324bb087daab39eca2d80eb40a285f0ba16585dc9ae96e7e4c82cf0b7c5",
"result": {
"columns": [
{
"name": "event_name",
"declared_type": "text"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "str",
"value": "November Speaker"
}
]
],
"result_hash": "sha256:56406324bb087daab39eca2d80eb40a285f0ba16585dc9ae96e7e4c82cf0b7c5"
}
},
"plan_variant": {
"run": false,
"reason": "the plan variant was not asked for"
}
}SELECT T1.event_name FROM event AS T1 INNER JOIN budget AS T2 ON T1.event_id = T2.link_to_event INNER JOIN expense AS T3 ON T2.budget_id = T3.link_to_budget ORDER BY T3.cost NULLS FIRST LIMIT 1result_hash sha256:56406324bb087daab39eca2d80eb40a285f0ba16585dc9ae96e7e4c82cf0b7c5 recomputed from this JSON: match
record_hash sha256:e4867b646f254cf7a8a78334e2c593f9fdf0dd7f853eda6c16188814e4ed63c4 recomputed from this JSON: match
from evidence-gold.json, 1 row
| event_nametext |
|---|
| November Speaker |
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