{
  "format": "attestql/audit/summary/2",
  "run_id": "audit-49215ef1-ae35-4207-99a0-4538f9872bc4",
  "backend_identity": "SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/minidev/dev_databases/codebase_community/codebase_community.sqlite | size=481419264",
  "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": 49,
    "duplicate_ids": [
      137,
      138
    ],
    "ids": [
      531,
      532,
      533,
      539,
      537,
      544,
      547,
      549,
      555,
      557,
      563,
      565,
      567,
      568,
      571,
      572,
      573,
      576,
      578,
      581,
      584,
      586,
      587,
      592,
      595,
      598,
      604,
      629,
      633,
      634,
      637,
      639,
      640,
      665,
      669,
      671,
      672,
      678,
      682,
      683,
      685,
      687,
      694,
      701,
      704,
      705,
      707,
      710,
      716
    ]
  },
  "predictions": {
    "path": "data/preds-sqlite/predict_mini_dev_gpt-35-turbo-instruct_sqlite.json",
    "digest": "sha256:a4a5f5e12d19d3fa742d0f3111723bd1dca50b29887eb705438580efe6dcc04b",
    "origin": "https://raw.githubusercontent.com/bird-bench/mini_dev/b3d4bcbbae9a96934ad812551eb400c7a3b23c12/llm/exp_result/sql_output_kg/predict_mini_dev_gpt-35-turbo-instruct_sqlite.json",
    "date": "2024-06-19",
    "keyed_by": "position",
    "statements": 500,
    "positions_unused": [
      487,
      488
    ]
  },
  "verdicts": {
    "NOT_EQUAL": 19,
    "EQUAL": 17,
    "ERROR": 13
  },
  "smells": {
    "ordering-over-numeric-text": 0,
    "arbitrary-cut": 1,
    "not-a-function-of-the-data": 2,
    "float-aggregate-order": 0,
    "direction-against-question": 0
  },
  "smells_fired": 3,
  "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/gpt-35-turbo-instruct/codebase_community/fixture.json",
    "source": {
      "path": "data/minidev/dev_databases/codebase_community/codebase_community.sqlite",
      "digest": "sha256:92101be6d2a9f6adceea59d38f6d1c556087f9eea1432432a21268cb1348036d",
      "origin": "minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f), member minidev/MINIDEV/dev_databases, codebase_community/codebase_community.sqlite",
      "date": "2024-06-13"
    },
    "schema_digest": "sha256:486946f86da61f185ded65fa40ebd1c1d34f6761a295222563857ffb491c6d5d",
    "row_counts": {
      "main.badges": 79851,
      "main.comments": 174285,
      "main.postHistory": 303155,
      "main.postLinks": 11102,
      "main.posts": 91966,
      "main.tags": 1032,
      "main.users": 40325,
      "main.votes": 38930
    },
    "content_digests": {},
    "measured_tables": [
      "users",
      "posts",
      "tags",
      "comments",
      "votes",
      "postHistory",
      "badges",
      "postLinks"
    ],
    "missing_tables": [],
    "unreadable_tables": [],
    "refused": ""
  },
  "planner_statistics": {},
  "shuffle": {
    "seed": 1,
    "row_limit": 300000,
    "scratch_schema": "temp",
    "prepared": true,
    "reason": "",
    "copied": [
      "badges",
      "comments",
      "postLinks",
      "posts",
      "tags",
      "users",
      "votes"
    ],
    "skipped": {
      "postHistory": 303155
    },
    "not_reached_by_a_copy": {}
  },
  "settings": {
    "statement_timeout_seconds": 30,
    "fail_on_smell": false,
    "experimental_s2": false,
    "plan_variant": false,
    "out": "runs/minidev-sqlite/gpt-35-turbo-instruct/codebase_community",
    "serialization": "attestql/audit/2",
    "work_mem": null,
    "hash_mem_multiplier": null
  },
  "data_as_of": "2026-09-08T05:00:01.024913+00:00",
  "data_as_of_source": "the instant the run started",
  "elapsed_seconds": {
    "fixture": 0.021,
    "questions": 14.561,
    "shuffle": 1.92
  },
  "errors": [
    {
      "question_id": 587,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: Text"
    },
    {
      "question_id": 592,
      "side": "prediction",
      "step": "execute",
      "message": "execute: misuse of aggregate: Count()"
    },
    {
      "question_id": 598,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such function: Year"
    },
    {
      "question_id": 604,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: UserId"
    },
    {
      "question_id": 634,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: DisplayName"
    },
    {
      "question_id": 639,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: PostId"
    },
    {
      "question_id": 640,
      "side": "prediction",
      "step": "statement",
      "message": "the text does not parse: Invalid expression / Unexpected token. Line 1, Col: 93. SELECT SUM(ViewCount) FROM posts WHERE OwnerDisplayName = 'Mornington' - SUM(ViewCount) \u001b[4mFROM\u001b[0m posts WHERE OwnerDisplayName = 'Amos'"
    },
    {
      "question_id": 665,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such function: YEAR"
    },
    {
      "question_id": 682,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: CreationDate"
    },
    {
      "question_id": 685,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: Text"
    },
    {
      "question_id": 701,
      "side": "prediction",
      "step": "statement",
      "message": "the text does not parse: Expecting ). Line 1, Col: 39. SELECT 100 * COUNT(stats_posts.Id \u001b[4mwhere\u001b[0m Score > 50 and MAX(Reputation)) / COUNT(stats_posts.Id where MAX(Reputation)) FROM posts INNER JOIN"
    },
    {
      "question_id": 707,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: Text"
    },
    {
      "question_id": 716,
      "side": "prediction",
      "step": "execute",
      "message": "execute: no such column: UpVotes"
    }
  ],
  "timed_out": {
    "gold": [],
    "prediction": []
  },
  "exit_status": 1
}
