R-SET GOLD-ONLY float-aggregate-order
debit_card_specializing · 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
What is the amount spent by customer "38508" at the gas stations? How much had the customer spent in January 2012?
the hint the set supplies: January 2012 refers to the Date value = '201201'
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 SUM(T1.Price ), SUM(CASE WHEN T3.Date = '201201' THEN T1.Price ELSE 0 END) FROM transactions_1k AS T1 INNER JOIN gasstations AS T2 ON T1.GasStationID = T2.GasStationID INNER JOIN yearmonth AS T3 ON T1.CustomerID = T3.CustomerID WHERE T1.CustomerID = '38508'this statement states no ordering of its own
sha256:abac40bcf8bcd1919ece362aaa46a30b6a2f8d5731b5198ed89de90803225106
from evidence-gold.json, 1 row
| sumfloat4 | sumfloat4 |
|---|---|
| 68740.22 | 3437.01 |
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
| 68740.23 | 3437.0103 |
{
"heuristic": true,
"rule": "R-SET",
"baseline_result_hash": "sha256:abac40bcf8bcd1919ece362aaa46a30b6a2f8d5731b5198ed89de90803225106",
"baseline_result": {
"columns": [
{
"name": "sum",
"declared_type": "float4"
},
{
"name": "sum",
"declared_type": "float4"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "dec",
"value": "68740.22"
},
{
"type": "dec",
"value": "3437.01"
}
]
],
"result_hash": "sha256:abac40bcf8bcd1919ece362aaa46a30b6a2f8d5731b5198ed89de90803225106"
},
"planner_statistics": {
"yearmonth": {
"last_analyze": null,
"last_autoanalyze": null,
"n_mod_since_analyze": 383282
},
"transactions_1k": {
"last_analyze": null,
"last_autoanalyze": null,
"n_mod_since_analyze": 1000
},
"gasstations": {
"last_analyze": null,
"last_autoanalyze": null,
"n_mod_since_analyze": 5716
}
},
"shuffle": {
"seed": "1",
"row_limit": 300000,
"tables": [
"yearmonth",
"transactions_1k",
"gasstations"
],
"tables_not_shuffled": [
"yearmonth"
],
"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": "sha256:2542c0243d0729b5724e56716e4d917e69d897aa5fddca8003b4a6e6291092b7",
"result": {
"columns": [
{
"name": "sum",
"declared_type": "float4"
},
{
"name": "sum",
"declared_type": "float4"
}
],
"row_count": 1,
"truncated": false,
"rows_shown": 1,
"rows": [
[
{
"type": "dec",
"value": "68740.23"
},
{
"type": "dec",
"value": "3437.0103"
}
]
],
"result_hash": "sha256:2542c0243d0729b5724e56716e4d917e69d897aa5fddca8003b4a6e6291092b7"
}
},
"plan_variant": {
"run": false,
"reason": "the plan variant was not asked for"
},
"float_cells": [
{
"row": 0,
"column": "sum",
"declared_type": "float4",
"baseline": "68740.22",
"rerun": "68740.23"
},
{
"row": 0,
"column": "sum",
"declared_type": "float4",
"baseline": "3437.01",
"rerun": "3437.0103"
}
],
"significant_digits": 6
}SELECT SUM(T1.Price ), SUM(CASE WHEN T3.Date = '201201' THEN T1.Price ELSE 0 END) FROM transactions_1k AS T1 INNER JOIN gasstations AS T2 ON T1.GasStationID = T2.GasStationID INNER JOIN yearmonth AS T3 ON T1.CustomerID = T3.CustomerID WHERE T1.CustomerID = '38508'result_hash sha256:abac40bcf8bcd1919ece362aaa46a30b6a2f8d5731b5198ed89de90803225106 recomputed from this JSON: match
record_hash sha256:8dfa4e723ccf5d5a3a5e25269565ee11f84c118882e7b73081fcc15fd45fbb0a recomputed from this JSON: match
from evidence-gold.json, 1 row
| sumfloat4 | sumfloat4 |
|---|---|
| 68740.22 | 3437.01 |
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