{ "format": "attestql/audit/summary/2", "run_id": "audit-6e8823c0-2c9a-4f1f-a1da-943e1f5ea07b", "backend_identity": "SQLite 3.53.4 | file=/private/tmp/attestql-runs/data/minidev/dev_databases/superhero/superhero.sqlite | size=237568", "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": 52, "duplicate_ids": [ 137, 138 ], "ids": [ 717, 719, 723, 724, 726, 728, 730, 732, 733, 736, 737, 738, 739, 740, 743, 744, 745, 747, 750, 751, 753, 758, 760, 761, 764, 765, 766, 769, 772, 773, 775, 779, 781, 782, 785, 786, 788, 790, 791, 792, 794, 796, 797, 798, 800, 801, 806, 819, 822, 824, 825, 829 ] }, "predictions": { "path": "data/preds-sqlite/predict_mini_dev_gpt-4-32k_sqlite.json", "digest": "sha256:7ee53fcc67b9eaca363efb53ddb94dabd61526dafc09d835d832989e4911a1ca", "origin": "https://raw.githubusercontent.com/bird-bench/mini_dev/b3d4bcbbae9a96934ad812551eb400c7a3b23c12/llm/exp_result/sql_output_kg/predict_mini_dev_gpt-4-32k_sqlite.json", "date": "2024-06-19", "keyed_by": "position", "statements": 500, "positions_unused": [ 487, 488 ] }, "verdicts": { "EQUAL": 37, "NOT_EQUAL": 14, "ERROR": 1 }, "smells": { "ordering-over-numeric-text": 0, "arbitrary-cut": 3, "not-a-function-of-the-data": 0, "float-aggregate-order": 0, "direction-against-question": 0 }, "smells_fired": 3, "credited_but_not_equal": { "total": 1, "by_mechanism": { "multiplicity": 0, "type": 1, "order": 0, "truncation": 0, "other": 0 }, "by_test_suite_ex": { "1": 1, "0": 0 } }, "fixture": { "depth": "counts", "cache": "runs/minidev-sqlite/gpt-4-32k/superhero/fixture.json", "source": { "path": "data/minidev/dev_databases/superhero/superhero.sqlite", "digest": "sha256:75e94a2c3236ee3bb2c01fb97a1c4b4c1c269bcefd4eab1d04be323d2d0825b1", "origin": "minidev.zip (sha256 cc48ba16838204e4e214512030cb572eeb5f7bcdd999bae4b9b6ff12ec13b92f), member minidev/MINIDEV/dev_databases, superhero/superhero.sqlite", "date": "2024-06-13" }, "schema_digest": "sha256:921b79dd088877e3b6090a31ab919676ab6b45adf398a468edc025b74a77f750", "row_counts": { "main.alignment": 4, "main.attribute": 6, "main.colour": 35, "main.gender": 3, "main.hero_attribute": 3738, "main.hero_power": 5825, "main.publisher": 25, "main.race": 61, "main.superhero": 750, "main.superpower": 167 }, "content_digests": {}, "measured_tables": [ "superhero", "hero_power", "superpower", "colour", "publisher", "hero_attribute", "attribute", "race", "gender", "alignment" ], "missing_tables": [], "unreadable_tables": [], "refused": "" }, "planner_statistics": {}, "shuffle": { "seed": 1, "row_limit": 300000, "scratch_schema": "temp", "prepared": true, "reason": "", "copied": [ "alignment", "attribute", "colour", "gender", "hero_attribute", "hero_power", "publisher", "race", "superhero", "superpower" ], "skipped": {}, "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-4-32k/superhero", "serialization": "attestql/audit/2", "work_mem": null, "hash_mem_multiplier": null }, "data_as_of": "2026-09-08T05:01:56.358817+00:00", "data_as_of_source": "the instant the run started", "elapsed_seconds": { "fixture": 0.002, "questions": 0.648, "shuffle": 0.011 }, "errors": [ { "question_id": 790, "side": "prediction", "step": "statement", "message": "the text does not parse: Expecting ). Line 1, Col: 28. SELECT (SUM(weight_kg) \u001b[4mWHERE\u001b[0m full_name = 'Emil Blonsky') - (SUM(weight_kg) WHERE full_name = 'Charles Chandler') AS weight_diffe" } ], "timed_out": { "gold": [], "prediction": [] }, "exit_status": 1 }