R-SET NOT_EQUAL
toxicology · 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
Find the triple-bonded molecules which are carcinogenic.
the hint the set supplies: triple-bonded molecules refers to bond_type = '#'; carcinogenic refers to label = '+'
NOT_EQUAL states that these two statements disagree on this data under this rule. It does not state which of them is wrong.
read by hand, 2026-09-04: A a wrong answer the benchmark credited: another table or projection; a scalar repeated per row of an unrelated table; a list at least twice the answer's length where the question asks for the things, not the rows
gold DISTINCT over 2 molecule ids; the prediction joins atoms and bonds and returns 12 rows
a maintainer's reading of this question, out of classification.json, copied from plans/reports/prediction-mode-260904-real-predictions/classification.json. It is not a verdict and nothing above it was computed from it.
SELECT DISTINCT T2.molecule_id FROM bond AS T1 INNER JOIN molecule AS T2 ON T1.molecule_id = T2.molecule_id WHERE T1.bond_type = '#' AND T2.label = '+'this statement states no ordering of its own
sha256:880b5132c72a66c3008a48d0fd5e750bcdfc3c1870746ff182e6753ab08be121
SELECT m.molecule_id
FROM molecule m
JOIN atom a ON m.molecule_id = a.molecule_id
JOIN connected c ON a.atom_id = c.atom_id OR a.atom_id = c.atom_id2
JOIN bond b ON c.bond_id = b.bond_id
WHERE b.bond_type = '#' AND m.label = '+';this statement states no ordering of its own
sha256:7e7fa4f2248aaff6a6a187dea69c5f7a6cbcf5f4950b60bb8cf030b477c13484
The marked tokens are where the two texts differ. Two statements that differ everywhere can return the same rows, and two that differ in one token can return other rows; the verdict above is read off the results.
from counterexample.json, 0 rows, up to 25 shown per side
| side | molecule_idtext |
|---|---|
| no rows |
from counterexample.json, 10 rows, up to 25 shown per side, 2 on this page
| side | times | molecule_idtext |
|---|---|---|
| second | 7 | TR041 |
| second | 3 | TR499 |
set(second_rows) == set(gold_rows), float4/float8 cells as Python float as psycopg2 returns them, numeric as Decimal
https://github.com/bird-bench/mini_dev/blob/main/evaluation/evaluation_ex.py
result_eq: equal row counts and equal column counts, each row unordered as a quick rejection, then the two equal as a list when the gold text holds ORDER BY and as a multiset otherwise, under some permutation of the columns; DISTINCT is not stripped and re-executed, and the cells are PostgreSQL's as psycopg2 returns them
ruiqi-zhong/test-suite-sql-eval, exec_eval.py, result_eq, at commit 48cb78ec: https://github.com/ruiqi-zhong/test-suite-sql-eval/blob/48cb78ecf7f610620206283846c76751b18a1326/exec_eval.py
The class states what makes these two results unequal under this rule, read off the two results and nothing else. It does not state which of the two statements is wrong.
from counterexample.json, 2 rows
| molecule_idtext |
|---|
| TR041 |
| TR499 |
from counterexample.json, 12 rows
| molecule_idtext |
|---|
| TR041 |
| TR041 |
| TR041 |
| TR041 |
| TR041 |
| TR041 |
| TR041 |
| TR041 |
| TR499 |
| TR499 |
| TR499 |
| TR499 |
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
the statement states no top level ORDER BY
{
"heuristic": true,
"reason": "the statement states no top level ORDER BY"
}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
the statement states no LIMIT
{
"heuristic": true,
"reason": "the statement states no LIMIT"
}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-SET",
"baseline_result_hash": "sha256:880b5132c72a66c3008a48d0fd5e750bcdfc3c1870746ff182e6753ab08be121",
"baseline_result": {
"columns": [
{
"name": "molecule_id",
"declared_type": "text"
}
],
"row_count": 2,
"truncated": false,
"rows_shown": 2,
"rows": [
[
{
"type": "str",
"value": "TR041"
}
],
[
{
"type": "str",
"value": "TR499"
}
]
],
"result_hash": "sha256:880b5132c72a66c3008a48d0fd5e750bcdfc3c1870746ff182e6753ab08be121"
},
"planner_statistics": {
"bond": {
"last_analyze": null,
"last_autoanalyze": "2026-09-08 05:19:12.802916+00",
"n_mod_since_analyze": 0
},
"molecule": {
"last_analyze": null,
"last_autoanalyze": "2026-09-08 05:19:30.558409+00",
"n_mod_since_analyze": 0
}
},
"shuffle": {
"seed": "1",
"row_limit": 300000,
"tables": [
"bond",
"molecule"
],
"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": "sha256:880b5132c72a66c3008a48d0fd5e750bcdfc3c1870746ff182e6753ab08be121",
"result": {
"columns": [
{
"name": "molecule_id",
"declared_type": "text"
}
],
"row_count": 2,
"truncated": false,
"rows_shown": 2,
"rows": [
[
{
"type": "str",
"value": "TR041"
}
],
[
{
"type": "str",
"value": "TR499"
}
]
],
"result_hash": "sha256:880b5132c72a66c3008a48d0fd5e750bcdfc3c1870746ff182e6753ab08be121"
}
},
"plan_variant": {
"run": false,
"reason": "the plan variant was not asked for"
}
}SELECT DISTINCT T2.molecule_id FROM bond AS T1 INNER JOIN molecule AS T2 ON T1.molecule_id = T2.molecule_id WHERE T1.bond_type = '#' AND T2.label = '+'result_hash sha256:880b5132c72a66c3008a48d0fd5e750bcdfc3c1870746ff182e6753ab08be121 recomputed from this JSON: match
record_hash sha256:0994ebc7cbfc4c37bfc58416ffe97b775cb36d1bef59479ce44bd743d7eb06da recomputed from this JSON: match
from evidence-gold.json, 2 rows
| molecule_idtext |
|---|
| TR041 |
| TR499 |
SELECT m.molecule_id
FROM molecule m
JOIN atom a ON m.molecule_id = a.molecule_id
JOIN connected c ON a.atom_id = c.atom_id OR a.atom_id = c.atom_id2
JOIN bond b ON c.bond_id = b.bond_id
WHERE b.bond_type = '#' AND m.label = '+';result_hash sha256:7e7fa4f2248aaff6a6a187dea69c5f7a6cbcf5f4950b60bb8cf030b477c13484 recomputed from this JSON: match
record_hash sha256:756bfab80f0e7fc215a1fdfe1412f4fc6cb456ddf0224aa8600c4226c37123f8 recomputed from this JSON: match
from evidence-second.json, 12 rows
| molecule_idtext |
|---|
| TR041 |
| TR041 |
| TR041 |
| TR041 |
| TR041 |
| TR041 |
| TR041 |
| TR041 |
| TR499 |
| TR499 |
| TR499 |
| TR499 |
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-SET
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-SET