R-SET GOLD-ONLY duplicate-full-row
codebase_community · 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)
Write all the comments left by users who edited the post titled 'Why square the difference instead of taking the absolute value in standard deviation?'
the hint the set supplies: "Why square the difference instead of taking the absolute value in standard deviation?" is the Title of post;
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.Comment FROM posts AS T1 INNER JOIN postHistory AS T2 ON T1.Id = T2.PostId WHERE T1.Title = 'Why square the difference instead of taking the absolute value in standard deviation?'this statement states no ordering of its own
sha256:82c66035e59a7892f44746ee924406034f953c7da179a36ee96072a5eebe3b0e
from evidence-gold.json, 8 rows
| CommentTEXT |
|---|
| edited title |
| TeXified the formulas. |
| deleted 5 characters in body; edited title |
| deleted 5 characters in body; edited title |
| edited title |
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": "sha256:82c66035e59a7892f44746ee924406034f953c7da179a36ee96072a5eebe3b0e",
"baseline_result": {
"columns": [
{
"name": "Comment",
"declared_type": "TEXT"
}
],
"row_count": 8,
"truncated": false,
"rows_shown": 8,
"rows": [
[
{
"type": "str",
"value": ""
}
],
[
{
"type": "str",
"value": ""
}
],
[
{
"type": "str",
"value": ""
}
],
[
{
"type": "str",
"value": "edited title"
}
],
[
{
"type": "str",
"value": "TeXified the formulas."
}
],
[
{
"type": "str",
"value": "deleted 5 characters in body; edited title"
}
],
[
{
"type": "str",
"value": "deleted 5 characters in body; edited title"
}
],
[
{
"type": "str",
"value": "edited title"
}
]
],
"result_hash": "sha256:82c66035e59a7892f44746ee924406034f953c7da179a36ee96072a5eebe3b0e"
},
"planner_statistics": {},
"shuffle": {
"seed": "1",
"row_limit": 300000,
"tables": [
"posts",
"postHistory"
],
"tables_not_shuffled": [
"postHistory"
],
"tables_skipped_for_size": {
"postHistory": 303155
},
"tables_not_reached_by_a_copy": {}
},
"shuffled_copies": {
"run": true,
"verdict": "equal",
"differs": false,
"result_hash": "sha256:167f3fc40fb292da00f02f22c7b30b619eb070e5b8f029f7a39f31b0bc9532bd",
"result": {
"columns": [
{
"name": "Comment",
"declared_type": "TEXT"
}
],
"row_count": 8,
"truncated": false,
"rows_shown": 8,
"rows": [
[
{
"type": "str",
"value": ""
}
],
[
{
"type": "str",
"value": ""
}
],
[
{
"type": "str",
"value": ""
}
],
[
{
"type": "str",
"value": "TeXified the formulas."
}
],
[
{
"type": "str",
"value": "deleted 5 characters in body; edited title"
}
],
[
{
"type": "str",
"value": "deleted 5 characters in body; edited title"
}
],
[
{
"type": "str",
"value": "edited title"
}
],
[
{
"type": "str",
"value": "edited title"
}
]
],
"result_hash": "sha256:167f3fc40fb292da00f02f22c7b30b619eb070e5b8f029f7a39f31b0bc9532bd"
}
},
"plan_variant": {
"run": false,
"reason": "the plan variant was not asked for"
}
}this statement returns the same whole row more than once and never says DISTINCT, so a statement answering the same question once per row disagrees on multiplicity alone
from smells.json, 3 rows
| edited title |
| deleted 5 characters in body; edited title |
{
"heuristic": true,
"rows": 8,
"distinct_rows": 4,
"repeated_rows": 3,
"largest_repeat": 3,
"result_bounded": false,
"distinct_stated": false,
"set_operation": false,
"repeats_of_the_rows_shown": [
3,
2,
2
]
}SELECT T2.Comment FROM posts AS T1 INNER JOIN postHistory AS T2 ON T1.Id = T2.PostId WHERE T1.Title = 'Why square the difference instead of taking the absolute value in standard deviation?'result_hash sha256:82c66035e59a7892f44746ee924406034f953c7da179a36ee96072a5eebe3b0e recomputed from this JSON: match
record_hash sha256:085fa78ef1434a14c5edb96c1f4bd2b5249b7401dcbb2285fc377760472cbf05 recomputed from this JSON: match
from evidence-gold.json, 8 rows
| CommentTEXT |
|---|
| edited title |
| TeXified the formulas. |
| deleted 5 characters in body; edited title |
| deleted 5 characters in body; edited title |
| edited title |
re-run this statement read-only against SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/dev/dev_databases/codebase_community/codebase_community.sqlite | size=481419264 under the session settings and over the data this record's fixture digest names, and compare the two results under R-SET