{"adoption": {"forks": 36, "observed_at": "2026-08-28T04:03:34.855440+00:00", "stars": 1098}, "canonical_url": "https://ross.abutalabs.com/products/bird-critic-1", "card": {"archived": false, "artifact_type": "dataset", "description": "[NeurIPS 2025 Main] SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications", "domain": ["databases", "large-language-models", "artificial-intelligence", "developer-tools"], "enriched": true, "function": ["benchmarking", "llm-inference", "database", "testing"], "health_score": 64, "homepage": "https://bird-critic.github.io/", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["bird-bench/BIRD-CRITIC-1"], "name": "bird-bench/BIRD-CRITIC-1", "platform": ["python", "cross-platform"], "pushed_at": "2026-03-23T23:05:33+00:00", "repo": "bird-bench/BIRD-CRITIC-1", "stars": 1098, "tags": ["sql-benchmark", "text-to-sql", "llm-evaluation", "sql-debugging", "swe-benchmark", "leaderboard"], "topics": [], "urls": [], "use_cases": ["evaluate llms on fixing real-world sql issues", "benchmark llm sql debugging across dialects", "test llm agents on postgresql sql problems", "compare models on a sql issue leaderboard", "research agentic sql issue resolution", "measure human-ai collaboration on sql troubleshooting"], "what_it_is": "BIRD-CRITIC 1.0 (a.k.a. SWE-SQL) is a benchmark dataset of real-world SQL user issues for evaluating whether LLMs can diagnose and fix database problems across MySQL, PostgreSQL, SQL Server, Oracle, and BigQuery. It includes 600 development tasks, 200 held-out OOD tests, and an execution-based evaluation environment with a public leaderboard.", "when_to_avoid": ["you need a simple text-to-SQL natural-language-to-query dataset rather than issue fixing", "you want a lightweight general coding benchmark not focused on SQL", "you cannot access gated ground-truth data requiring email request"], "when_to_choose": ["you need a rigorous, execution-based benchmark for LLM SQL debugging", "you want cross-dialect coverage including PostgreSQL, MySQL, SQL Server, and Oracle", "you are benchmarking agentic or multi-turn SQL issue-solving pipelines"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/bird-critic-1", "repo": "bird-bench/BIRD-CRITIC-1", "role": "main", "score": 53}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.855440+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:46:18.060376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0eaa02e508745cd39f844cc21cfee5a17e88e39a93553517c32371907487ecb", "fetched_at": "2026-08-28T04:03:34.855440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-CRITIC-1"}, {"content_hash": "1546f928a5650f758b3b3f68c9a51a9869f546420ee4caececf272bf14fdebff", "fetched_at": "2026-08-29T12:49:44.804589+00:00", "kind": "homepage", "missing": false, "url": "https://bird-critic.github.io/"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.855440+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:46:18.060376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0eaa02e508745cd39f844cc21cfee5a17e88e39a93553517c32371907487ecb", "fetched_at": "2026-08-28T04:03:34.855440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-CRITIC-1"}, {"content_hash": "1546f928a5650f758b3b3f68c9a51a9869f546420ee4caececf272bf14fdebff", "fetched_at": "2026-08-29T12:49:44.804589+00:00", "kind": "homepage", "missing": false, "url": "https://bird-critic.github.io/"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:46:18.060376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0eaa02e508745cd39f844cc21cfee5a17e88e39a93553517c32371907487ecb", "fetched_at": "2026-08-28T04:03:34.855440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-CRITIC-1"}, {"content_hash": "1546f928a5650f758b3b3f68c9a51a9869f546420ee4caececf272bf14fdebff", "fetched_at": "2026-08-29T12:49:44.804589+00:00", "kind": "homepage", "missing": false, "url": "https://bird-critic.github.io/"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.855440+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.855440+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.855440+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:46:18.060376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0eaa02e508745cd39f844cc21cfee5a17e88e39a93553517c32371907487ecb", "fetched_at": "2026-08-28T04:03:34.855440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-CRITIC-1"}, {"content_hash": "1546f928a5650f758b3b3f68c9a51a9869f546420ee4caececf272bf14fdebff", "fetched_at": "2026-08-29T12:49:44.804589+00:00", "kind": "homepage", "missing": false, "url": "https://bird-critic.github.io/"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.855440+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.855440+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:46:18.060376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0eaa02e508745cd39f844cc21cfee5a17e88e39a93553517c32371907487ecb", "fetched_at": "2026-08-28T04:03:34.855440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-CRITIC-1"}, {"content_hash": "1546f928a5650f758b3b3f68c9a51a9869f546420ee4caececf272bf14fdebff", "fetched_at": "2026-08-29T12:49:44.804589+00:00", "kind": "homepage", "missing": false, "url": "https://bird-critic.github.io/"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.855440+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.855440+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.855440+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:46:18.060376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0eaa02e508745cd39f844cc21cfee5a17e88e39a93553517c32371907487ecb", "fetched_at": "2026-08-28T04:03:34.855440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-CRITIC-1"}, {"content_hash": "1546f928a5650f758b3b3f68c9a51a9869f546420ee4caececf272bf14fdebff", "fetched_at": "2026-08-29T12:49:44.804589+00:00", "kind": "homepage", "missing": false, "url": "https://bird-critic.github.io/"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.855440+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:34.855440+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:46:18.060376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0eaa02e508745cd39f844cc21cfee5a17e88e39a93553517c32371907487ecb", "fetched_at": "2026-08-28T04:03:34.855440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-CRITIC-1"}, {"content_hash": "1546f928a5650f758b3b3f68c9a51a9869f546420ee4caececf272bf14fdebff", "fetched_at": "2026-08-29T12:49:44.804589+00:00", "kind": "homepage", "missing": false, "url": "https://bird-critic.github.io/"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:46:18.060376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0eaa02e508745cd39f844cc21cfee5a17e88e39a93553517c32371907487ecb", "fetched_at": "2026-08-28T04:03:34.855440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-CRITIC-1"}, {"content_hash": "1546f928a5650f758b3b3f68c9a51a9869f546420ee4caececf272bf14fdebff", "fetched_at": "2026-08-29T12:49:44.804589+00:00", "kind": "homepage", "missing": false, "url": "https://bird-critic.github.io/"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:46:18.060376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0eaa02e508745cd39f844cc21cfee5a17e88e39a93553517c32371907487ecb", "fetched_at": "2026-08-28T04:03:34.855440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-CRITIC-1"}, {"content_hash": "1546f928a5650f758b3b3f68c9a51a9869f546420ee4caececf272bf14fdebff", "fetched_at": "2026-08-29T12:49:44.804589+00:00", "kind": "homepage", "missing": false, "url": "https://bird-critic.github.io/"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:46:18.060376+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d0eaa02e508745cd39f844cc21cfee5a17e88e39a93553517c32371907487ecb", "fetched_at": "2026-08-28T04:03:34.855440+00:00", "kind": "readme", "missing": false, "url": "https://github.com/bird-bench/BIRD-CRITIC-1"}, {"content_hash": "1546f928a5650f758b3b3f68c9a51a9869f546420ee4caececf272bf14fdebff", "fetched_at": "2026-08-29T12:49:44.804589+00:00", "kind": "homepage", "missing": false, "url": "https://bird-critic.github.io/"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 73, "longevity": 41, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 582, "days_push": 163, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 53, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}