q1168

R-ORD GOLD-ONLY arbitrary-cut not-a-function-of-the-data

thrombosis_prediction · mini_dev_pg-00000-of-00001 from https://huggingface.co/datasets/birdsql/bird_mini_dev/resolve/f65faf4ae3b638c1fa6df1d3370c8d92c8366301/data/mini_dev_pg-00000-of-00001.json (commit f65faf4a, downloaded 2026-09-08)

The question

The oldest SJS patient's medical laboratory work was completed on what date, and what age was the patient when they initially arrived at the hospital?

the hint the set supplies: The larger the birthday value, the younger the person is, and vice versa; 'SJS' refers to diagnosis; (SUBTRACT(year(`First Date`)), year(Birthday)); age of the patients when they initially arrived at the hospital refers to year(Birthday)

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.

The statements

gold

SELECT T1.Date, EXTRACT(YEAR FROM T2."First Date") - EXTRACT(YEAR FROM T2.Birthday) AS Age, T2.Birthday FROM Laboratory AS T1 INNER JOIN Patient AS T2 ON T1.ID = T2.ID WHERE T2.Diagnosis = 'SJS' AND T2.Birthday IS NOT NULL ORDER BY T2.Birthday ASC LIMIT 1
t2.birthday
ascending

sha256:6b55468927f94152e74429191a5e2d1782a5d8ec759b3952b9b50e54b9f08264

The results

gold, 1 row

from evidence-gold.json, 1 row

datedate agenumeric birthdaydate
1981-07-31 69 1917-04-18

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

no ORDER BY key resolves to a text column

what it measured 
{
  "heuristic": true,
  "reason": "no ORDER BY key resolves to a text column",
  "keys": [
    {
      "key": "t2.birthday",
      "column": "patient.birthday",
      "declared_type": "date",
      "not_applicable": "the column is not declared as text"
    }
  ]
}

arbitrary-cut fired

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

from smells.json, 10 rows

1986-01-07 69 1917-04-18 1917-04-18
1981-07-31 69 1917-04-18 1917-04-18
1981-12-11 69 1917-04-18 1917-04-18
1982-05-01 69 1917-04-18 1917-04-18
1982-12-02 69 1917-04-18 1917-04-18
1984-01-28 69 1917-04-18 1917-04-18
1984-02-02 69 1917-04-18 1917-04-18
1984-04-26 69 1917-04-18 1917-04-18
1985-04-20 69 1917-04-18 1917-04-18
1985-11-26 69 1917-04-18 1917-04-18
what it measured 
{
  "heuristic": true,
  "cut": 1,
  "offset": 0,
  "distinct_kept": false,
  "unbounded_sql": "SELECT t1.date, extract ('year' FROM t2.\"First Date\") - extract ('year' FROM t2.birthday) AS age, t2.birthday, t2.birthday AS attestql_ordering_key_0 FROM laboratory t1 JOIN patient t2 ON t1.id = t2.id WHERE t2.diagnosis = 'SJS' AND t2.birthday IS NOT NULL ORDER BY t2.birthday ASC",
  "unbounded_rows": 1086,
  "projected_columns": [
    "date",
    "age",
    "birthday"
  ],
  "ordering_key_columns": [
    "attestql_ordering_key_0"
  ],
  "ordering_keys": [
    {
      "key": "t2.birthday",
      "direction": "asc",
      "nulls": "default",
      "nulls_first_in_effect": false,
      "returned_rows_null_in_this_key": 0,
      "fires": false
    }
  ],
  "tied_at_the_cut": {
    "positions": [
      0,
      1,
      2,
      3,
      4,
      5,
      6,
      7,
      8,
      9
    ],
    "tied_rows": 10,
    "distinct_projected_answers": 10,
    "rows": [
      [
        {
          "type": "date",
          "value": "1986-01-07"
        },
        {
          "type": "dec",
          "value": "69"
        },
        {
          "type": "date",
          "value": "1917-04-18"
        }
      ],
      [
        {
          "type": "date",
          "value": "1981-07-31"
        },
        {
          "type": "dec",
          "value": "69"
        },
        {
          "type": "date",
          "value": "1917-04-18"
        }
      ],
      [
        {
          "type": "date",
          "value": "1981-12-11"
        },
        {
          "type": "dec",
          "value": "69"
        },
        {
          "type": "date",
          "value": "1917-04-18"
        }
      ],
      [
        {
          "type": "date",
          "value": "1982-05-01"
        },
        {
          "type": "dec",
          "value": "69"
        },
        {
          "type": "date",
          "value": "1917-04-18"
        }
      ],
      [
        {
          "type": "date",
          "value": "1982-12-02"
        },
        {
          "type": "dec",
          "value": "69"
        },
        {
          "type": "date",
          "value": "1917-04-18"
        }
      ],
      [
        {
          "type": "date",
          "value": "1984-01-28"
        },
        {
          "type": "dec",
          "value": "69"
        },
        {
          "type": "date",
          "value": "1917-04-18"
        }
      ],
      [
        {
          "type": "date",
          "value": "1984-02-02"
        },
        {
          "type": "dec",
          "value": "69"
        },
        {
          "type": "date",
          "value": "1917-04-18"
        }
      ],
      [
        {
          "type": "date",
          "value": "1984-04-26"
        },
        {
          "type": "dec",
          "value": "69"
        },
        {
          "type": "date",
          "value": "1917-04-18"
        }
      ],
      [
        {
          "type": "date",
          "value": "1985-04-20"
        },
        {
          "type": "dec",
          "value": "69"
        },
        {
          "type": "date",
          "value": "1917-04-18"
        }
      ],
      [
        {
          "type": "date",
          "value": "1985-11-26"
        },
        {
          "type": "dec",
          "value": "69"
        },
        {
          "type": "date",
          "value": "1917-04-18"
        }
      ]
    ]
  },
  "case": "tie-at-the-cut"
}

not-a-function-of-the-data fired

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

from smells.json, 1 row

1982-12-02 69 1917-04-18
what it measured 
{
  "heuristic": true,
  "rule": "R-ORD",
  "baseline_result_hash": "sha256:6b55468927f94152e74429191a5e2d1782a5d8ec759b3952b9b50e54b9f08264",
  "baseline_result": {
    "columns": [
      {
        "name": "date",
        "declared_type": "date"
      },
      {
        "name": "age",
        "declared_type": "numeric"
      },
      {
        "name": "birthday",
        "declared_type": "date"
      }
    ],
    "row_count": 1,
    "truncated": false,
    "rows_shown": 1,
    "rows": [
      [
        {
          "type": "date",
          "value": "1981-07-31"
        },
        {
          "type": "dec",
          "value": "69"
        },
        {
          "type": "date",
          "value": "1917-04-18"
        }
      ]
    ],
    "result_hash": "sha256:6b55468927f94152e74429191a5e2d1782a5d8ec759b3952b9b50e54b9f08264"
  },
  "planner_statistics": {
    "laboratory": {
      "last_analyze": null,
      "last_autoanalyze": null,
      "n_mod_since_analyze": 13908
    },
    "patient": {
      "last_analyze": null,
      "last_autoanalyze": null,
      "n_mod_since_analyze": 1238
    }
  },
  "shuffle": {
    "seed": "1",
    "row_limit": 300000,
    "tables": [
      "laboratory",
      "patient"
    ],
    "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": "sha256:6be76dc0a41148c0f19499c6c1e337f281fb5b8d81d7e9a9a5b5ad0d19b83a40",
    "result": {
      "columns": [
        {
          "name": "date",
          "declared_type": "date"
        },
        {
          "name": "age",
          "declared_type": "numeric"
        },
        {
          "name": "birthday",
          "declared_type": "date"
        }
      ],
      "row_count": 1,
      "truncated": false,
      "rows_shown": 1,
      "rows": [
        [
          {
            "type": "date",
            "value": "1982-12-02"
          },
          {
            "type": "dec",
            "value": "69"
          },
          {
            "type": "date",
            "value": "1917-04-18"
          }
        ]
      ],
      "result_hash": "sha256:6be76dc0a41148c0f19499c6c1e337f281fb5b8d81d7e9a9a5b5ad0d19b83a40"
    }
  },
  "plan_variant": {
    "run": false,
    "reason": "the plan variant was not asked for"
  }
}

The evidence records

gold: evidence-gold.json

SELECT T1.Date, EXTRACT(YEAR FROM T2."First Date") - EXTRACT(YEAR FROM T2.Birthday) AS Age, T2.Birthday FROM Laboratory AS T1 INNER JOIN Patient AS T2 ON T1.ID = T2.ID WHERE T2.Diagnosis = 'SJS' AND T2.Birthday IS NOT NULL ORDER BY T2.Birthday ASC LIMIT 1
statement read from
data/questions/mini_dev_pg-00000-of-00001.json
digest
sha256:7fa740ef9225389cff6c34432120e8325d0ca3008d73db1ae38731234bc10da7
origin
https://huggingface.co/datasets/birdsql/bird_mini_dev/resolve/f65faf4ae3b638c1fa6df1d3370c8d92c8366301/data/mini_dev_pg-00000-of-00001.json (commit f65faf4a, downloaded 2026-09-08), 2026-01-18T08:44:25Z

result_hash sha256:6b55468927f94152e74429191a5e2d1782a5d8ec759b3952b9b50e54b9f08264 recomputed from this JSON: match

record_hash sha256:2ca649db5c7206481cf21de74641ad0d0a34a29690bb247c01ca31fd628d93ff recomputed from this JSON: match

the result this record holds, 1 row

from evidence-gold.json, 1 row

datedate agenumeric birthdaydate
1981-07-31 69 1917-04-18
what ran, and where
run
audit-ed50a84a-c286-4cbb-ac89-ab3111058ad5
executed at
2026-09-08T05:19:05.826404+00:00
data as of
2026-09-08T05:18:53.188748+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-ORD
question set version
sha256:7fa740ef9225389cff6c34432120e8325d0ca3008d73db1ae38731234bc10da7
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
30000 ms
rows
1 row
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:c3f16bb2decabe492af6bb2e9dafdb557727431b0995cf3e7c730560f07f2d4c
source file sha256
sha256:31b1da211849d24a57c9af7636da46a5b82fc8a3ca1542bb3ebd8775e9a31cec
rows in public.laboratory
13908
rows in public.patient
1238

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-ORD

This question's run

run
audit-ed50a84a-c286-4cbb-ac89-ab3111058ad5
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_pg-00000-of-00001 from https://huggingface.co/datasets/birdsql/bird_mini_dev/resolve/f65faf4ae3b638c1fa6df1d3370c8d92c8366301/data/mini_dev_pg-00000-of-00001.json (commit f65faf4a, downloaded 2026-09-08)
replay rule
R-ORD

the run this question belongs to

The JSON this page was rendered from