{
  "format": "attestql/audit/summary/2",
  "run_id": "audit-e68aafff-7739-4280-b3dc-d30f0144b6d4",
  "backend_identity": "SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/minidev/dev_databases/financial/financial.sqlite | size=71294976",
  "effective_database_role": "file",
  "session_settings": {
    "engine": "sqlite",
    "recorded": {
      "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"
    }
  },
  "parser": {
    "validator": "audit:sqlglot-sqlite-parse",
    "sqlglot": "30.18.0",
    "dialect": "sqlite"
  },
  "question_set": {
    "path": "data/questions/mini_dev_sqlite.json",
    "digest": "sha256:4ba5fa8de55856222f484d380d2ba872b380bf79d825de70478e2120cb0fc43b",
    "origin": "https://bird-bench.oss-cn-beijing.aliyuncs.com/minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f, downloaded 2026-09-07), member minidev/MINIDEV/mini_dev_sqlite.json",
    "date": "2024-06-19",
    "entries": 500,
    "audited": 30,
    "duplicate_ids": [
      137,
      138
    ],
    "ids": [
      89,
      92,
      93,
      94,
      95,
      98,
      99,
      100,
      112,
      115,
      116,
      117,
      118,
      125,
      128,
      136,
      137,
      138,
      129,
      145,
      149,
      152,
      159,
      168,
      169,
      173,
      186,
      189,
      192,
      194
    ]
  },
  "predictions": {
    "path": "data/preds-sqlite/predict_mini_dev_phi-3-medium-128k-instruct-1_sqlite.json",
    "digest": "sha256:5e1a3a37cb174cbe62ff3bd269b293b6473c99da34f3fe3ac6f186dd5a1a7ff5",
    "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_sqlite.json",
    "date": "2024-06-19",
    "keyed_by": "position",
    "statements": 500,
    "positions_unused": [
      487,
      488
    ]
  },
  "verdicts": {
    "NOT_EQUAL": 13,
    "ERROR": 13,
    "EQUAL": 4
  },
  "smells": {
    "ordering-over-numeric-text": 1,
    "arbitrary-cut": 0,
    "not-a-function-of-the-data": 0,
    "float-aggregate-order": 0,
    "direction-against-question": 0
  },
  "smells_fired": 1,
  "credited_but_not_equal": {
    "total": 0,
    "by_mechanism": {
      "multiplicity": 0,
      "type": 0,
      "order": 0,
      "truncation": 0,
      "other": 0
    },
    "by_test_suite_ex": {
      "1": 0,
      "0": 0
    }
  },
  "fixture": {
    "depth": "counts",
    "cache": "runs/minidev-sqlite/phi-3-medium-128k-instruct-1/financial/fixture.json",
    "source": {
      "path": "data/minidev/dev_databases/financial/financial.sqlite",
      "digest": "sha256:d15d89cdb068a202b6f2b99342af44dffc1d52545b39ceaf62efdc0ba570101e",
      "origin": "minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f), member minidev/MINIDEV/dev_databases, financial/financial.sqlite",
      "date": "2024-06-13"
    },
    "schema_digest": "sha256:dec3b7590cdaf8df74c4ddbef766cac24a33554a327998fe33ef165b15bdf90a",
    "row_counts": {
      "main.account": 4500,
      "main.card": 892,
      "main.client": 5369,
      "main.disp": 5369,
      "main.district": 77,
      "main.loan": 682,
      "main.order": 6471,
      "main.trans": 1056320
    },
    "content_digests": {},
    "measured_tables": [
      "district",
      "account",
      "client",
      "disp",
      "loan",
      "trans",
      "order",
      "card"
    ],
    "missing_tables": [],
    "unreadable_tables": [],
    "refused": ""
  },
  "planner_statistics": {},
  "shuffle": {
    "seed": 1,
    "row_limit": 300000,
    "scratch_schema": "temp",
    "prepared": true,
    "reason": "",
    "copied": [
      "account",
      "card",
      "client",
      "disp",
      "district",
      "loan",
      "order"
    ],
    "skipped": {
      "trans": 1056320
    },
    "not_reached_by_a_copy": {}
  },
  "settings": {
    "statement_timeout_seconds": 30,
    "fail_on_smell": false,
    "experimental_s2": false,
    "plan_variant": false,
    "out": "runs/minidev-sqlite/phi-3-medium-128k-instruct-1/financial",
    "serialization": "attestql/audit/2",
    "work_mem": null,
    "hash_mem_multiplier": null
  },
  "data_as_of": "2026-09-08T05:30:12.599549+00:00",
  "data_as_of_source": "the instant the run started",
  "elapsed_seconds": {
    "fixture": 0.01,
    "questions": 31.889,
    "shuffle": 0.028
  },
  "errors": [
    {
      "question_id": 92,
      "side": "prediction",
      "step": "execute",
      "message": "execute: ambiguous column name: district_id"
    },
    {
      "question_id": 94,
      "side": "prediction",
      "step": "statement",
      "message": "the text does not parse: Invalid expression / Unexpected token. Line 38, Col: 30. t_id = a.client_id JOIN female_clients fc ON c.client_id = fc.client_id JOIN average_salaries as ON \u001b[4mfc\u001b[0m.district_id = as.district_id JOIN lowest_avg_salary las ON as.avg_salary = las.min_avg_salary JOIN"
    },
    {
      "question_id": 95,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: account_id"
    },
    {
      "question_id": 98,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: frequency"
    },
    {
      "question_id": 116,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: balance"
    },
    {
      "question_id": 137,
      "side": "prediction",
      "step": "execute",
      "message": "execute: ambiguous column name: account_id"
    },
    {
      "question_id": 138,
      "side": "prediction",
      "step": "execute",
      "message": "execute: the statement ran past its 30s timeout"
    },
    {
      "question_id": 149,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: account.type"
    },
    {
      "question_id": 159,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: account.client_id"
    },
    {
      "question_id": 169,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such function: YEAR"
    },
    {
      "question_id": 186,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: frequency"
    },
    {
      "question_id": 192,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: account.status"
    },
    {
      "question_id": 194,
      "side": "prediction",
      "step": "execute",
      "message": "execute: ambiguous column name: client_id"
    }
  ],
  "timed_out": {
    "gold": [],
    "prediction": [
      138
    ]
  },
  "exit_status": 1
}
