R-SET NOT_EQUAL
toxicology · mini_dev_sqlite from https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_sqlite.json
What are the elements for bond id TR001_10_11?
the hint the set supplies: TR001_10_11 is the bond id;
NOT_EQUAL states that these two statements disagree on this data under this rule. It does not state which of them is wrong.
SELECT T2.element FROM connected AS T1 INNER JOIN atom AS T2 ON T1.atom_id = T2.atom_id WHERE T1.bond_id = 'TR001_10_11'this statement states no ordering of its own
sha256:9d2e4c969dafd20791a3829f3bbd056403b619bcedd6a6105e58228c98fa2bee
SELECT a.element
FROM atom a
JOIN connected c ON a.atom_id = c.atom_id OR a.atom_id = c.atom_id2
WHERE c.bond_id = 'TR001_10_11'this statement states no ordering of its own
sha256:6bbe179f680db87d846b65091f10cf2a3da6505593f1995dad7e13826bdaa8db
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 | elementTEXT |
|---|---|
| no rows |
from counterexample.json, 2 rows, up to 25 shown per side
| side | elementTEXT |
|---|---|
| second | c |
| second | o |
set(second_rows) == set(gold_rows), REAL cells as Python float as sqlite3 returns them, so Python equality holds 1 == 1.0 == True as the benchmark's own scorer does
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 SQLite's as sqlite3 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
| elementTEXT |
|---|
| c |
| o |
from counterexample.json, 4 rows
| elementTEXT |
|---|
| c |
| o |
| c |
| o |
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": "sha256:9d2e4c969dafd20791a3829f3bbd056403b619bcedd6a6105e58228c98fa2bee",
"baseline_result": {
"columns": [
{
"name": "element",
"declared_type": "TEXT"
}
],
"row_count": 2,
"truncated": false,
"rows_shown": 2,
"rows": [
[
{
"type": "str",
"value": "c"
}
],
[
{
"type": "str",
"value": "o"
}
]
],
"result_hash": "sha256:9d2e4c969dafd20791a3829f3bbd056403b619bcedd6a6105e58228c98fa2bee"
},
"planner_statistics": {},
"shuffle": {
"seed": "1",
"row_limit": 300000,
"tables": [
"connected",
"atom"
],
"tables_not_shuffled": [],
"tables_skipped_for_size": {},
"tables_not_reached_by_a_copy": {}
},
"shuffled_copies": {
"run": true,
"verdict": "equal",
"differs": false,
"result_hash": "sha256:e08439f8bdc028e320ee715606e797c8593e7739722eacc329cef102b98146f7",
"result": {
"columns": [
{
"name": "element",
"declared_type": "TEXT"
}
],
"row_count": 2,
"truncated": false,
"rows_shown": 2,
"rows": [
[
{
"type": "str",
"value": "o"
}
],
[
{
"type": "str",
"value": "c"
}
]
],
"result_hash": "sha256:e08439f8bdc028e320ee715606e797c8593e7739722eacc329cef102b98146f7"
}
},
"plan_variant": {
"run": false,
"reason": "the plan variant was not asked for"
}
}SELECT T2.element FROM connected AS T1 INNER JOIN atom AS T2 ON T1.atom_id = T2.atom_id WHERE T1.bond_id = 'TR001_10_11'result_hash sha256:9d2e4c969dafd20791a3829f3bbd056403b619bcedd6a6105e58228c98fa2bee recomputed from this JSON: match
record_hash sha256:94232d0bb7b4899dbfb58dc05c1ab0446bf689e7a4d680c76ab6c8ab1334d614 recomputed from this JSON: match
from evidence-gold.json, 2 rows
| elementTEXT |
|---|
| c |
| o |
SELECT a.element
FROM atom a
JOIN connected c ON a.atom_id = c.atom_id OR a.atom_id = c.atom_id2
WHERE c.bond_id = 'TR001_10_11'result_hash sha256:6bbe179f680db87d846b65091f10cf2a3da6505593f1995dad7e13826bdaa8db recomputed from this JSON: match
record_hash sha256:ded95f99dcfb37089525cae90d5bf10d0d8077e036148e308347554cf5fc7a87 recomputed from this JSON: match
from evidence-second.json, 4 rows
| elementTEXT |
|---|
| c |
| o |
| c |
| o |
re-run this statement read-only against SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/minidev/dev_databases/toxicology/toxicology.sqlite | size=2678784 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 SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/minidev/dev_databases/toxicology/toxicology.sqlite | size=2678784 under the session settings and over the data this record's fixture digest names, and compare the two results under R-SET