R-SET NOT_EQUAL float-aggregate-order
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
Calculate the difference of the total amount spent in all events by the Student_Club in year 2019 and 2020.
the hint the set supplies: The first 4 strings of the event_date values in the event table can represent year; The difference of the total amount spent = SUBTRACT(spent where YEAR(event_date) = 2019, spent where YEAR(event_date) = 2020)
NOT_EQUAL states that these two statements disagree on this data under this rule. It does not state which of them is wrong.
The two statements name their result columns differently. A projection is compared by position and declared type, so these names did not decide the verdict. They are part of the canonical rendering each result is hashed under, so the two result hashes differ with them.
SELECT SUM(CASE WHEN SUBSTR(T1.event_date, 1, 4) = '2019' THEN T2.spent ELSE 0 END) - SUM(CASE WHEN SUBSTR(T1.event_date, 1, 4) = '2020' THEN T2.spent ELSE 0 END) AS num FROM event AS T1 INNER JOIN budget AS T2 ON T1.event_id = T2.link_to_eventthis statement states no ordering of its own
sha256:8ec9642f1f2d773f23ac5c701909c24d0e993619408c86f4e3ea41ebf18e2bca
SELECT (SUM(b1.spent) - SUM(b2.spent)) AS difference
FROM budget b1
JOIN event e1 ON b1.link_to_event = e1.event_id
JOIN budget b2 ON b1.budget_id = b2.budget_id
JOIN event e2 ON b2.link_to_event = e2.event_id
WHERE EXTRACT(YEAR FROM e1.event_date::date) = 2019
AND EXTRACT(YEAR FROM e2.event_date::date) = 2020this statement states no ordering of its own
sha256:e265b8c707962b87d85406cb879f0a07dc4c8771f0685357b1515b918382707f
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, 1 row, up to 25 shown per side
| side | numfloat4 |
|---|---|
| gold | 2086.05 |
from counterexample.json, 1 row, up to 25 shown per side
| side | differencefloat4 |
|---|---|
| second | NULL |
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, 1 row
| numfloat4 |
|---|
| 2086.05 |
from counterexample.json, 1 row
| differencefloat4 |
|---|
| NULL |
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"
}this statement aggregates floating point numbers, so its last digits depend on the order the rows were summed in; the values agree to six significant digits
from smells.json, 1 row
| 2086.0498 |
{
"heuristic": true,
"rule": "R-SET",
"baseline_result_hash": "sha256:8ec9642f1f2d773f23ac5c701909c24d0e993619408c86f4e3ea41ebf18e2bca",
"baseline_result": {
"columns": [
{
"name": "num",
"declared_type": "float4"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "dec",
"value": "2086.05"
}
]
],
"result_hash": "sha256:8ec9642f1f2d773f23ac5c701909c24d0e993619408c86f4e3ea41ebf18e2bca"
},
"planner_statistics": {
"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": [
"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": "not_equal",
"differs": true,
"result_hash": "sha256:9ad97a5c0926efb47b6342d9c84bb54b4da61167b93ffc31827473296a8cc4fc",
"result": {
"columns": [
{
"name": "num",
"declared_type": "float4"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "dec",
"value": "2086.0498"
}
]
],
"result_hash": "sha256:9ad97a5c0926efb47b6342d9c84bb54b4da61167b93ffc31827473296a8cc4fc"
}
},
"plan_variant": {
"run": false,
"reason": "the plan variant was not asked for"
},
"float_cells": [
{
"row": 0,
"column": "num",
"declared_type": "float4",
"baseline": "2086.05",
"rerun": "2086.0498"
}
],
"significant_digits": 6
}SELECT SUM(CASE WHEN SUBSTR(T1.event_date, 1, 4) = '2019' THEN T2.spent ELSE 0 END) - SUM(CASE WHEN SUBSTR(T1.event_date, 1, 4) = '2020' THEN T2.spent ELSE 0 END) AS num FROM event AS T1 INNER JOIN budget AS T2 ON T1.event_id = T2.link_to_eventresult_hash sha256:8ec9642f1f2d773f23ac5c701909c24d0e993619408c86f4e3ea41ebf18e2bca recomputed from this JSON: match
record_hash sha256:e5b59f9a1280bd451096f84bd4015d77a928a2c12b937aec54a49f19608471e3 recomputed from this JSON: match
from evidence-gold.json, 1 row
| numfloat4 |
|---|
| 2086.05 |
SELECT (SUM(b1.spent) - SUM(b2.spent)) AS difference
FROM budget b1
JOIN event e1 ON b1.link_to_event = e1.event_id
JOIN budget b2 ON b1.budget_id = b2.budget_id
JOIN event e2 ON b2.link_to_event = e2.event_id
WHERE EXTRACT(YEAR FROM e1.event_date::date) = 2019
AND EXTRACT(YEAR FROM e2.event_date::date) = 2020result_hash sha256:e265b8c707962b87d85406cb879f0a07dc4c8771f0685357b1515b918382707f recomputed from this JSON: match
record_hash sha256:9de82e3818d85b035044e3af77147186a565b1987daa18a4db4334ebe6e62b9e recomputed from this JSON: match
from evidence-second.json, 1 row
| differencefloat4 |
|---|
| NULL |
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