q1457

R-SET NOT_EQUAL

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

The question

Give the full name and contact number of members who had to spend more than average on each expense.

the hint the set supplies: full name refers to first_name, last_name; contact number refers to phone; had spent more than average on each expense refers to cost > AVG(cost)

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 3 members; the prediction returns 11, one per expense

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.

The statements

gold

SELECT DISTINCT T3.first_name, T3.last_name, T3.phone FROM expense AS T1 INNER JOIN budget AS T2 ON T1.link_to_budget = T2.budget_id INNER JOIN member AS T3 ON T3.member_id = T1.link_to_member WHERE T1.cost > (SELECT AVG(T1.cost) FROM expense AS T1 INNER JOIN budget AS T2 ON T1.link_to_budget = T2.budget_id INNER JOIN member AS T3 ON T3.member_id = T1.link_to_member)

this statement states no ordering of its own

sha256:8b26bbf5c0485fd3d9b6439e58ec3549d6a1885f79aa5e9aca030207fe5ba5ca

second

SELECT m.first_name, m.last_name, m.phone
FROM member m
JOIN expense e ON m.member_id = e.link_to_member
WHERE e.cost > (SELECT AVG(cost) FROM expense);

this statement states no ordering of its own

sha256:a9afa38c74cefb93b25a34cb9590c6d259cd7cc2d05bd52912d9407edcfd4890

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.

The rows they differ in

in gold, not in the prediction, 0 rows

from counterexample.json, 0 rows, up to 25 shown per side

side first_nametext last_nametext phonetext
no rows

in the prediction, not in gold, 8 rows

from counterexample.json, 8 rows, up to 25 shown per side, 3 on this page

sidetimes first_nametext last_nametext phonetext
second5 Sacha Harrison 840-555-4781
second2 Elijah Allen 724-555-5721
second1 Phillip Cullen 905-555-5035

What the benchmark would have said

BIRD's own check: 1

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

gold_rows
3
second_rows
11
gold_distinct_rows
3
second_distinct_rows
3

the test-suite check: 0

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

order_matters
false
gold_rows
3
second_rows
11
gold_columns
3
second_columns
3

the class: multiplicity

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.

how many rows each result holds, and how many rows both hold, from evidence-gold.json and evidence-second.json3 gold11 prediction3 rows both results hold
The gold returned 3 rows and the prediction 11. 3 rows occur in both results at least once.
gold_types
["text", "text", "text"]
second_types
["text", "text", "text"]
multiset_equal
false
set_equal
true
order_equal
false
shorter_result_is_a_prefix
false

The results

gold, 3 rows

from counterexample.json, 3 rows

first_nametext last_nametext phonetext
Phillip Cullen 905-555-5035
Elijah Allen 724-555-5721
Sacha Harrison 840-555-4781
second, 11 rows

from counterexample.json, 11 rows

first_nametext last_nametext phonetext
Sacha Harrison 840-555-4781
Sacha Harrison 840-555-4781
Sacha Harrison 840-555-4781
Sacha Harrison 840-555-4781
Sacha Harrison 840-555-4781
Sacha Harrison 840-555-4781
Phillip Cullen 905-555-5035
Phillip Cullen 905-555-5035
Elijah Allen 724-555-5721
Elijah Allen 724-555-5721
Elijah Allen 724-555-5721

The probes

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.

ordering-over-numeric-text not applicable

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

what it measured 
{
  "heuristic": true,
  "reason": "the statement states no top level ORDER BY"
}

arbitrary-cut not applicable

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

what it measured 
{
  "heuristic": true,
  "reason": "the statement states no LIMIT"
}

not-a-function-of-the-data quiet

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

what it measured 
{
  "heuristic": true,
  "rule": "R-SET",
  "baseline_result_hash": "sha256:8b26bbf5c0485fd3d9b6439e58ec3549d6a1885f79aa5e9aca030207fe5ba5ca",
  "baseline_result": {
    "columns": [
      {
        "name": "first_name",
        "declared_type": "text"
      },
      {
        "name": "last_name",
        "declared_type": "text"
      },
      {
        "name": "phone",
        "declared_type": "text"
      }
    ],
    "row_count": 3,
    "truncated": false,
    "rows_shown": 3,
    "rows": [
      [
        {
          "type": "str",
          "value": "Phillip"
        },
        {
          "type": "str",
          "value": "Cullen"
        },
        {
          "type": "str",
          "value": "905-555-5035"
        }
      ],
      [
        {
          "type": "str",
          "value": "Elijah"
        },
        {
          "type": "str",
          "value": "Allen"
        },
        {
          "type": "str",
          "value": "724-555-5721"
        }
      ],
      [
        {
          "type": "str",
          "value": "Sacha"
        },
        {
          "type": "str",
          "value": "Harrison"
        },
        {
          "type": "str",
          "value": "840-555-4781"
        }
      ]
    ],
    "result_hash": "sha256:8b26bbf5c0485fd3d9b6439e58ec3549d6a1885f79aa5e9aca030207fe5ba5ca"
  },
  "planner_statistics": {
    "member": {
      "last_analyze": null,
      "last_autoanalyze": null,
      "n_mod_since_analyze": 33
    },
    "expense": {
      "last_analyze": null,
      "last_autoanalyze": null,
      "n_mod_since_analyze": 32
    },
    "budget": {
      "last_analyze": null,
      "last_autoanalyze": null,
      "n_mod_since_analyze": 52
    }
  },
  "shuffle": {
    "seed": "1",
    "row_limit": 300000,
    "tables": [
      "member",
      "expense",
      "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": "equal",
    "differs": false,
    "result_hash": "sha256:8b26bbf5c0485fd3d9b6439e58ec3549d6a1885f79aa5e9aca030207fe5ba5ca",
    "result": {
      "columns": [
        {
          "name": "first_name",
          "declared_type": "text"
        },
        {
          "name": "last_name",
          "declared_type": "text"
        },
        {
          "name": "phone",
          "declared_type": "text"
        }
      ],
      "row_count": 3,
      "truncated": false,
      "rows_shown": 3,
      "rows": [
        [
          {
            "type": "str",
            "value": "Phillip"
          },
          {
            "type": "str",
            "value": "Cullen"
          },
          {
            "type": "str",
            "value": "905-555-5035"
          }
        ],
        [
          {
            "type": "str",
            "value": "Elijah"
          },
          {
            "type": "str",
            "value": "Allen"
          },
          {
            "type": "str",
            "value": "724-555-5721"
          }
        ],
        [
          {
            "type": "str",
            "value": "Sacha"
          },
          {
            "type": "str",
            "value": "Harrison"
          },
          {
            "type": "str",
            "value": "840-555-4781"
          }
        ]
      ],
      "result_hash": "sha256:8b26bbf5c0485fd3d9b6439e58ec3549d6a1885f79aa5e9aca030207fe5ba5ca"
    }
  },
  "plan_variant": {
    "run": false,
    "reason": "the plan variant was not asked for"
  }
}

The evidence records

gold: evidence-gold.json

SELECT DISTINCT T3.first_name, T3.last_name, T3.phone FROM expense AS T1 INNER JOIN budget AS T2 ON T1.link_to_budget = T2.budget_id INNER JOIN member AS T3 ON T3.member_id = T1.link_to_member WHERE T1.cost > (SELECT AVG(T1.cost) FROM expense AS T1 INNER JOIN budget AS T2 ON T1.link_to_budget = T2.budget_id INNER JOIN member AS T3 ON T3.member_id = T1.link_to_member)
statement read from
data/questions/mini_dev_postgresql.json
digest
sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
origin
https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_postgresql.json, 2024-06-19

result_hash sha256:8b26bbf5c0485fd3d9b6439e58ec3549d6a1885f79aa5e9aca030207fe5ba5ca recomputed from this JSON: match

record_hash sha256:9a4b46590ed2fcd604a420b1b74ff51bf409241a860e98006e53aaa00ff6254b recomputed from this JSON: match

the result this record holds, 3 rows

from evidence-gold.json, 3 rows

first_nametext last_nametext phonetext
Phillip Cullen 905-555-5035
Elijah Allen 724-555-5721
Sacha Harrison 840-555-4781
what ran, and where
run
audit-715e02b9-6229-4aab-aa2e-7df62f68e7a4
executed at
2026-09-08T05:25:47.857570+00:00
data as of
2026-09-08T05:25:39.400422+00:00
backend at checkout
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
backend that answered
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
database role
auditor
replay rule
R-SET
question set version
sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
validator
audit:libpg_query-parse
checks run
parses_as_exactly_one_statement, the_one_statement_is_a_select, no_placeholder_without_a_bound_parameter
statement timeout
120000 ms
rows
3 rows
the session it ran under
engine
postgresql
time_zone
Etc/UTC
date_style
ISO, MDY
interval_style
postgres
extra_float_digits
1
database_collation
en_US.utf8
work_mem
4096
hash_mem_multiplier
2

recorded beside them

statement_timeout
0
search_path
"$user", public
server_version
16.15 (Debian 16.15-1.pgdg13+2)
server_version_num
160015
transaction_read_only
on
max_parallel_workers_per_gather
2
server_encoding
UTF8
datlocprovider
c
daticulocale
datcollversion
2.41
the rendering and the data
version
attestql/audit/2
numeric_scale
6
timestamp_format
%Y-%m-%dT%H:%M:%S.%fZ
timezone
UTC
null_rendering
NULL
encoding
utf-8
schema digest
sha256:506753b73f2c658b0c540e99204705002216f0bd04ef2d9d2b06d63b796b1a73
source file sha256
sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.budget
52
rows in public.expense
32
rows in public.member
33

second: evidence-second.json

SELECT m.first_name, m.last_name, m.phone
FROM member m
JOIN expense e ON m.member_id = e.link_to_member
WHERE e.cost > (SELECT AVG(cost) FROM expense);
statement read from
data/preds-pg/predict_mini_dev_phi-3-medium-128k-instruct-1_postgresql.json
digest
sha256:8defb4399ab3393200cfba510024df7d9cf2cff8c9c7df647e3309cf751ac82d
origin
https://raw.githubusercontent.com/bird-bench/mini_dev/b3d4bcbbae9a96934ad812551eb400c7a3b23c12/llm/exp_result/sql_output_kg/predict_mini_dev_phi-3-medium-128k-instruct-1_postgresql.json, 2024-06-19

result_hash sha256:a9afa38c74cefb93b25a34cb9590c6d259cd7cc2d05bd52912d9407edcfd4890 recomputed from this JSON: match

record_hash sha256:57efcf8506c833dcfebd5b1ca846d721031a3913e9b4fea0e3cca308d7ed2514 recomputed from this JSON: match

the result this record holds, 11 rows

from evidence-second.json, 11 rows

first_nametext last_nametext phonetext
Sacha Harrison 840-555-4781
Sacha Harrison 840-555-4781
Sacha Harrison 840-555-4781
Sacha Harrison 840-555-4781
Sacha Harrison 840-555-4781
Sacha Harrison 840-555-4781
Phillip Cullen 905-555-5035
Phillip Cullen 905-555-5035
Elijah Allen 724-555-5721
Elijah Allen 724-555-5721
Elijah Allen 724-555-5721
what ran, and where
run
audit-715e02b9-6229-4aab-aa2e-7df62f68e7a4
executed at
2026-09-08T05:25:47.860003+00:00
data as of
2026-09-08T05:25:39.400422+00:00
backend at checkout
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
backend that answered
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
database role
auditor
replay rule
R-SET
question set version
sha256:d2731292f20b8d8569cd956dd747ffe1df13cd625076263e38ae9ebcef50b1ab
validator
audit:libpg_query-parse
checks run
parses_as_exactly_one_statement, the_one_statement_is_a_select, no_placeholder_without_a_bound_parameter
statement timeout
120000 ms
rows
11 rows
the session it ran under
engine
postgresql
time_zone
Etc/UTC
date_style
ISO, MDY
interval_style
postgres
extra_float_digits
1
database_collation
en_US.utf8
work_mem
4096
hash_mem_multiplier
2

recorded beside them

statement_timeout
0
search_path
"$user", public
server_version
16.15 (Debian 16.15-1.pgdg13+2)
server_version_num
160015
transaction_read_only
on
max_parallel_workers_per_gather
2
server_encoding
UTF8
datlocprovider
c
daticulocale
datcollversion
2.41
the rendering and the data
version
attestql/audit/2
numeric_scale
6
timestamp_format
%Y-%m-%dT%H:%M:%S.%fZ
timezone
UTC
null_rendering
NULL
encoding
utf-8
schema digest
sha256:506753b73f2c658b0c540e99204705002216f0bd04ef2d9d2b06d63b796b1a73
source file sha256
sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.budget
52
rows in public.expense
32
rows in public.member
33

Running these again

gold

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

second

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

This question's run

run
audit-715e02b9-6229-4aab-aa2e-7df62f68e7a4
server
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
question set
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
replay rule
R-SET

the run this question belongs to

The JSON this page was rendered from