The whole of this run is a release asset
This site holds 1 of the 10 question directories this run wrote; the archive holds every one:
- archive
- minidev-sqlite-mistralai-mixtral-8x7b-instru-4.tar.gz
- size
- 1,075,349 bytes
- sha256
- 7f34c38f4a2fbc7c9cfd7720ee1dcc8af8c27748e47e2bdd6ebe556f7e3703ea
What it counted
| what | how many |
|---|---|
| questions audited | 40 |
| NOT_EQUAL | 10 |
| ERROR | 21 |
| EQUAL | 9 |
| probes fired | 0 |
the probes
| probe | fired on |
|---|---|
| ordering-over-numeric-text | 0 |
| arbitrary-cut | 0 |
| not-a-function-of-the-data | 0 |
| float-aggregate-order | 0 |
| direction-against-question | 0 |
credited by BIRD's own check and NOT_EQUAL here
| what | how many |
|---|---|
| credited by BIRD and NOT_EQUAL here | 2 |
| multiplicity | 2 |
| type | 0 |
| order | 0 |
| truncation | 0 |
| other | 0 |
| the test-suite check answered 1 | 0 |
| the test-suite check answered 0 | 2 |
What the run was made of
- run
- audit-2d4ec9d4-28e3-4b98-9d28-d020a587bb34
- summary format
- attestql/audit/summary/2
- question file
- data/questions/mini_dev_sqlite.json sha256:4ba5fa8de55856222f484d380d2ba872b380bf79d825de70478e2120cb0fc43b | https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_sqlite.json, 2024-06-19
- questions in the file
- 500
- prediction file
- data/preds-sqlite/predict_mini_dev_mistralai-mixtral-8x7b-instru-4_sqlite.json sha256:53cdf9142e3f2e49941eb7b50ebbea90361b2c5b46de37d5ba1c244187d643a2 | https://raw.githubusercontent.com/bird-bench/mini_dev/b3d4bcbbae9a96934ad812551eb400c7a3b23c12/llm/exp_result/sql_output_kg/predict_mini_dev_mistralai-mixtral-8x7b-instru-4_sqlite.json, 2024-06-19
- statements read
- 500
- keyed by
- position
- data file
- data/minidev/dev_databases/toxicology/toxicology.sqlite sha256:35ef27ae6bdfda530e125ed369666ac0abb8bc8c0bcc0ad09407f547ecb61a93 | minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f), member minidev/MINIDEV/dev_databases, toxicology/toxicology.sqlite, 2024-06-13
- server
- SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/minidev/dev_databases/toxicology/toxicology.sqlite | size=2678784
- database role
- file
- engine
- sqlite
- parser
- validator audit:sqlglot-sqlite-parse, sqlglot 30.18.0, dialect sqlite
- serialization
- attestql/audit/2
- statement timeout
- 30 s
- fixture digest depth
- counts
- schema digest
- sha256:e31e13a0dd8834a30b867b1b7f46a0da62573bc5318da4230b24d801f34a519a
- data as of
- 2026-09-08T05:05:01.622412+00:00 the instant the run started
- shuffled copies
- prepared
- shuffle seed
- 1
- experimental probe
- off
The session the run was made in
what the engine reported, 9 settings
- sqlite_version
- 3.53.4
- encoding
- UTF-8
- reverse_unordered_selects
- 0
- query_only
- 1
- journal_mode
- delete
- data_version
- 1
- compile_options
- ATOMIC_INTRINSICS=1,COMPILER=clang-21.0.0,DEFAULT_AUTOVACUUM,DEFAULT_CACHE_SIZE=-2000,DEFAULT_FILE_FORMAT=4,DEFAULT_JOURNAL_SIZE_LIMIT=-1,DEFAULT_MMAP_SIZE=0,DEFAULT_PAGE_SIZE=4096,DEFAULT_PCACHE_INITSZ=20,DEFAULT_RECURSIVE_TRIGGERS,DEFAULT_SECTOR_SIZE=4096,DEFAULT_SYNCHRONOUS=2,DEFAULT_WAL_AUTOCHECKPOINT=1000,DEFAULT_WAL_SYNCHRONOUS=2,DEFAULT_WORKER_THREADS=0,DIRECT_OVERFLOW_READ,ENABLE_API_ARMOR,ENABLE_COLUMN_METADATA,ENABLE_DBSTAT_VTAB,ENABLE_FTS3,ENABLE_FTS3_PARENTHESIS,ENABLE_FTS5,ENABLE_GEOPOLY,ENABLE_MATH_FUNCTIONS,ENABLE_MEMORY_MANAGEMENT,ENABLE_PERCENTILE,ENABLE_PREUPDATE_HOOK,ENABLE_RTREE,ENABLE_SESSION,ENABLE_STAT4,ENABLE_UNLOCK_NOTIFY,MALLOC_SOFT_LIMIT=1024,MAX_ATTACHED=10,MAX_COLUMN=2000,MAX_COMPOUND_SELECT=500,MAX_DEFAULT_PAGE_SIZE=8192,MAX_EXPR_DEPTH=1000,MAX_FUNCTION_ARG=1000,MAX_LENGTH=1000000000,MAX_LIKE_PATTERN_LENGTH=50000,MAX_MMAP_SIZE=0x7fff0000,MAX_PAGE_COUNT=0xfffffffe,MAX_PAGE_SIZE=65536,MAX_SQL_LENGTH=1000000000,MAX_TRIGGER_DEPTH=1000,MAX_VARIABLE_NUMBER=250000,MAX_VDBE_OP=250000000,MAX_WORKER_THREADS=8,MUTEX_PTHREADS,SYSTEM_MALLOC,TEMP_STORE=1,THREADSAFE=1,USE_URI
- collation_list
- RTRIM,NOCASE,BINARY
- case_sensitive_like
- 0
What the run states about itself
- ids the question file states twice
- 137, 138
- prediction positions not compared
- 487, 488
The questions
| question | rule | verdict | class | probes | what was asked |
|---|---|---|---|---|---|
| q206 | R-SET | NOT_EQUAL | multiplicity | What elements are in the TR004_8_9 bond atoms? | |
| q197 | ERROR | prediction: execute: execute: misuse of aggregate function COUNT() | |||
| q198 | ERROR | prediction: execute: execute: no such column: bond_type | |||
| q200 | ERROR | prediction: statement: the text does not parse: Invalid expression / Unexpected token. Line 1, Col: 27. SELECT DISTINCT m.molecule[4m\[0m_id FROM molecule m JOIN atom a ON m.molecule\_id = a.molecule\_id JOIN connected c ON a.atom\_id = | |||
| q201 | ERROR | prediction: statement: the text does not parse: Expecting ). Line 1, Col: 83. SELECT DIVIDE(SUM(CASE WHEN atom.element = 'c' THEN 1 ELSE 0 END), COUNT(atom.atom[4m\[0m_id)) AS percentage FROM atom JOIN connected ON atom.atom\_id = connected.atom\_id OR atom.atom\_id | |||
| q207 | ERROR | prediction: execute: execute: ambiguous column name: element | |||
| q208 | ERROR | prediction: execute: execute: no such column: a2.atom_id2 | |||
| q218 | ERROR | prediction: statement: the text does not parse: Error tokenizing ' JOIN connected c ON m.molecule_id = c.atom_id; ``' | |||
| q219 | ERROR | prediction: execute: execute: no such function: DIVIDE | |||
| q228 | ERROR | prediction: statement: the text does not parse: Expecting ). Line 1, Col: 79. SELECT ROUND(DIVIDE(SUM(CASE WHEN element = 'h' THEN 1 ELSE 0 END), COUNT(atom[4m\[0m_id)) \* 100, 4) AS percent_hydrogen FROM atom JOIN molecule ON atom.molecule\_id = molecule.molecul | |||
| q231 | ERROR | prediction: statement: the text does not parse: Expecting ). Line 9, Col: 16. .bond_id WHERE molecule_id = 'TR010' GROUP BY bond_type ORDER BY COUNT(*) DESC LIMIT 1; (The above [4mquery[0m will give you the majority bond type in molecule TR010. However, I cannot determine if this molecul | |||
| q234 | ERROR | prediction: execute: execute: no such column: molecule_id | |||
| q242 | ERROR | prediction: statement: the text does not parse: Invalid expression / Unexpected token. Line 1, Col: 27. SELECT DISTINCT m.molecule[4m\[0m_id FROM atom a JOIN molecule m ON a.molecule\_id = m.molecule\_id JOIN connected c1 ON a.atom\_id = | |||
| q248 | ERROR | prediction: execute: execute: ambiguous column name: molecule_id | |||
| q253 | ERROR | prediction: execute: execute: no such column: c1.atom_id1 | |||
| q255 | ERROR | prediction: execute: execute: incomplete input | |||
| q260 | ERROR | prediction: statement: the text does not parse: Expecting ). Line 1, Col: 29. SELECT COUNT(DISTINCT a.atom[4m\[0m_id) FROM atom a JOIN connected c ON a.atom\_id = c.atom\_id OR a.atom\_id = c.atom\_id2 JOIN bond b | |||
| q263 | ERROR | prediction: statement: the text does not parse: Expecting ). Line 1, Col: 74. SELECT DIVIDE(SUM(CASE WHEN element = 'cl' THEN 1 ELSE 0 END), COUNT(atom[4m\[0m_id)) AS percent FROM atom a JOIN connected c ON a.atom\_id = c.atom\_id JOIN bond b ON c.bond\_id = | |||
| q273 | ERROR | prediction: execute: execute: no such function: DIVIDE | |||
| q281 | ERROR | prediction: statement: the text does not parse: Invalid expression / Unexpected token. Line 1, Col: 18. SELECT m.molecule[4m\[0m_id, a.element FROM molecule m JOIN atom a ON m.molecule\_id = a.molecule\_id JOIN connected c ON a. | |||
| q282 | ERROR | prediction: execute: execute: no such function: DIVIDE | |||
| q327 | ERROR | prediction: statement: the text does not parse: Invalid expression / Unexpected token. Line 1, Col: 18. SELECT m.molecule[4m\[0m_id, m.label FROM molecule m JOIN atom a ON m.molecule\_id = a.molecule\_id JOIN connected c ON a.at |
A question whose statement could not be run wrote no directory, so it is a row here and has no page: the summary holds the side that stopped, the step it stopped at and the engine's own message.
The same index, restricted
Each of these is a page of its own, so a filtered view has an address a reader can send. Nothing here is done by a script or by a query string.
The JSON this page was rendered from
- summary.json attestql/audit/summary/2