gold
SELECT DISTINCT T1.name FROM cards AS T1 INNER JOIN rulings AS T2 ON T1.uuid = T2.uuid WHERE T1.rarity = 'uncommon' ORDER BY T2.date ASC LIMIT 3
- T2.date
- ascending
sha256:69a3d999c0c8f5178c7e86dcca9457b361b376961626a16b39a15dd766139bb1
R-ORD GOLD-ONLY arbitrary-cut not-a-function-of-the-data
card_games · 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)
Pick 3 cards with rarity of uncommon, list down name these cards according to ascending order of it's ruling date.
the hint the set supplies: uncommon refers to rarity = 'uncommon';
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.
read by hand, 2026-09-07: wrong the gold does not answer its question on this data
418 cards share the earliest ruling date; the gold's three are three of 418 and any other three answer the question as well
a maintainer's reading of this question, out of classification.json, copied from plans/reports/bird-dev-sqlite-260907/classification.json. It is not a verdict and nothing above it was computed from it.
SELECT DISTINCT T1.name FROM cards AS T1 INNER JOIN rulings AS T2 ON T1.uuid = T2.uuid WHERE T1.rarity = 'uncommon' ORDER BY T2.date ASC LIMIT 3
sha256:69a3d999c0c8f5178c7e86dcca9457b361b376961626a16b39a15dd766139bb1
from evidence-gold.json, 3 rows
| nameTEXT |
|---|
| Guerrilla Tactics |
| Aura of Silence |
| Orcish Artillery |
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
no ORDER BY key resolves to a text column
{
"heuristic": true,
"reason": "no ORDER BY key resolves to a text column",
"keys": [
{
"key": "T2.date",
"column": "rulings.date",
"declared_type": "DATE",
"not_applicable": "the column is not declared as text"
}
]
}
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
| Guerrilla Tactics | 2004-10-04 |
| Aura of Silence | 2004-10-04 |
| Orcish Artillery | 2004-10-04 |
| Puppeteer | 2004-10-04 |
| Soul Warden | 2004-10-04 |
| Spirit Link | 2004-10-04 |
| Spiketail Hatchling | 2004-10-04 |
| Stampeding Wildebeests | 2004-10-04 |
| Steel Golem | 2004-10-04 |
| Aura Graft | 2004-10-04 |
{
"heuristic": true,
"cut": 3,
"offset": 0,
"distinct_kept": true,
"unbounded_sql": "SELECT DISTINCT T1.name, T2.date AS attestql_ordering_key_0 FROM cards AS T1 INNER JOIN rulings AS T2 ON T1.uuid = T2.uuid WHERE T1.rarity = 'uncommon' ORDER BY T2.date ASC",
"unbounded_rows": 3792,
"projected_columns": [
"name"
],
"ordering_key_columns": [
"attestql_ordering_key_0"
],
"ordering_keys": [
{
"key": "T2.date",
"direction": "asc",
"nulls": "first",
"nulls_first_in_effect": true,
"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": 418,
"distinct_projected_answers": 418,
"rows": [
[
{
"type": "str",
"value": "Guerrilla Tactics"
}
],
[
{
"type": "str",
"value": "Aura of Silence"
}
],
[
{
"type": "str",
"value": "Orcish Artillery"
}
],
[
{
"type": "str",
"value": "Puppeteer"
}
],
[
{
"type": "str",
"value": "Soul Warden"
}
],
[
{
"type": "str",
"value": "Spirit Link"
}
],
[
{
"type": "str",
"value": "Spiketail Hatchling"
}
],
[
{
"type": "str",
"value": "Stampeding Wildebeests"
}
],
[
{
"type": "str",
"value": "Steel Golem"
}
],
[
{
"type": "str",
"value": "Aura Graft"
}
]
]
},
"case": "tie-at-the-cut"
}
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, 3 rows
| Urza's Mine |
| Meddle |
| Whirling Dervish |
{
"heuristic": true,
"rule": "R-ORD",
"baseline_result_hash": "sha256:69a3d999c0c8f5178c7e86dcca9457b361b376961626a16b39a15dd766139bb1",
"baseline_result": {
"columns": [
{
"name": "name",
"declared_type": "TEXT"
}
],
"row_count": 3,
"truncated": false,
"rows_shown": 3,
"rows": [
[
{
"type": "str",
"value": "Guerrilla Tactics"
}
],
[
{
"type": "str",
"value": "Aura of Silence"
}
],
[
{
"type": "str",
"value": "Orcish Artillery"
}
]
],
"result_hash": "sha256:69a3d999c0c8f5178c7e86dcca9457b361b376961626a16b39a15dd766139bb1"
},
"planner_statistics": {},
"shuffle": {
"seed": "1",
"row_limit": 300000,
"tables": [
"cards",
"rulings"
],
"tables_not_shuffled": [],
"tables_skipped_for_size": {
"legalities": 427907
},
"tables_not_reached_by_a_copy": {}
},
"shuffled_copies": {
"run": true,
"verdict": "not_equal",
"differs": true,
"result_hash": "sha256:3fa3938775237ed70d65a965e614c890819f4318157c2ffc1cacf8b60c31b2a4",
"result": {
"columns": [
{
"name": "name",
"declared_type": "TEXT"
}
],
"row_count": 3,
"truncated": false,
"rows_shown": 3,
"rows": [
[
{
"type": "str",
"value": "Urza's Mine"
}
],
[
{
"type": "str",
"value": "Meddle"
}
],
[
{
"type": "str",
"value": "Whirling Dervish"
}
]
],
"result_hash": "sha256:3fa3938775237ed70d65a965e614c890819f4318157c2ffc1cacf8b60c31b2a4"
}
},
"plan_variant": {
"run": false,
"reason": "the plan variant was not asked for"
}
}
SELECT DISTINCT T1.name FROM cards AS T1 INNER JOIN rulings AS T2 ON T1.uuid = T2.uuid WHERE T1.rarity = 'uncommon' ORDER BY T2.date ASC LIMIT 3
result_hash sha256:69a3d999c0c8f5178c7e86dcca9457b361b376961626a16b39a15dd766139bb1 recomputed from this JSON: match
record_hash sha256:a0b4754f2bb25dd6c7841d12740c797f4e9c8a4dfcd56eb0c4603bf642c160a1 recomputed from this JSON: match
from evidence-gold.json, 3 rows
| nameTEXT |
|---|
| Guerrilla Tactics |
| Aura of Silence |
| Orcish Artillery |
re-run this statement read-only against SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/dev/dev_databases/card_games/card_games.sqlite | size=261820416 under the session settings and over the data this record's fixture digest names, and compare the two results under R-ORD