{"adoption": {"forks": 36, "observed_at": "2026-08-28T04:04:00.123968+00:00", "stars": 1211}, "canonical_url": "https://ross.abutalabs.com/products/lakebench", "card": {"archived": false, "artifact_type": "dataset", "description": null, "domain": ["databases", "data-science", "big-data", "analytics"], "enriched": true, "function": ["benchmarking", "search-engine", "data-science", "machine-learning"], "health_score": 34, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["BIT-DataLab/LakeBench"], "name": "BIT-DataLab/LakeBench", "platform": ["python", "cross-platform"], "pushed_at": "2025-05-25T05:59:15+00:00", "repo": "BIT-DataLab/LakeBench", "stars": 1211, "tags": ["table-discovery", "data-lakes", "join-search", "union-search", "benchmark-dataset"], "topics": [], "urls": [], "use_cases": ["benchmark table discovery algorithms on large data lakes", "evaluate joinable table search methods", "evaluate unionable table search methods", "compare state-of-the-art table search systems like DeepJoin and Starmie", "research scalable schema matching in data lakes"], "what_it_is": "LakeBench is a large-scale benchmark for evaluating table discovery methods (joinable and unionable table search) in data lakes, containing over 16 million real tables and 10 thousand queries. It includes implementations of state-of-the-art join and union search algorithms for comparison.", "when_to_avoid": ["you need a production table discovery system rather than a benchmark", "your data lake is small and existing smaller benchmarks suffice", "you need a non-Python or non-PyTorch evaluation environment"], "when_to_choose": ["you need a realistic large-scale benchmark for table discovery research", "you want to evaluate join or union search algorithms at scale", "you need reproducible baselines for data lake table search"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/lakebench", "repo": "BIT-DataLab/LakeBench", "role": "main", "score": 37}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.123968+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:18:02.070987+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "242c9dfc15bb8f1802d1cc61e2fa1b0016e934c52640653ef07af1c366177e6d", "fetched_at": "2026-08-28T04:04:00.123968+00:00", "kind": "readme", "missing": false, "url": "https://github.com/BIT-DataLab/LakeBench"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.123968+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:18:02.070987+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "242c9dfc15bb8f1802d1cc61e2fa1b0016e934c52640653ef07af1c366177e6d", "fetched_at": "2026-08-28T04:04:00.123968+00:00", "kind": "readme", "missing": false, "url": "https://github.com/BIT-DataLab/LakeBench"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:18:02.070987+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "242c9dfc15bb8f1802d1cc61e2fa1b0016e934c52640653ef07af1c366177e6d", "fetched_at": "2026-08-28T04:04:00.123968+00:00", "kind": "readme", "missing": false, "url": "https://github.com/BIT-DataLab/LakeBench"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.123968+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.123968+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.123968+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:18:02.070987+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "242c9dfc15bb8f1802d1cc61e2fa1b0016e934c52640653ef07af1c366177e6d", "fetched_at": "2026-08-28T04:04:00.123968+00:00", "kind": "readme", "missing": false, "url": "https://github.com/BIT-DataLab/LakeBench"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.123968+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.123968+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:18:02.070987+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "242c9dfc15bb8f1802d1cc61e2fa1b0016e934c52640653ef07af1c366177e6d", "fetched_at": "2026-08-28T04:04:00.123968+00:00", "kind": "readme", "missing": false, "url": "https://github.com/BIT-DataLab/LakeBench"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.123968+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.123968+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.123968+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:18:02.070987+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "242c9dfc15bb8f1802d1cc61e2fa1b0016e934c52640653ef07af1c366177e6d", "fetched_at": "2026-08-28T04:04:00.123968+00:00", "kind": "readme", "missing": false, "url": "https://github.com/BIT-DataLab/LakeBench"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.123968+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:00.123968+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:18:02.070987+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "242c9dfc15bb8f1802d1cc61e2fa1b0016e934c52640653ef07af1c366177e6d", "fetched_at": "2026-08-28T04:04:00.123968+00:00", "kind": "readme", "missing": false, "url": "https://github.com/BIT-DataLab/LakeBench"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:18:02.070987+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "242c9dfc15bb8f1802d1cc61e2fa1b0016e934c52640653ef07af1c366177e6d", "fetched_at": "2026-08-28T04:04:00.123968+00:00", "kind": "readme", "missing": false, "url": "https://github.com/BIT-DataLab/LakeBench"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:18:02.070987+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "242c9dfc15bb8f1802d1cc61e2fa1b0016e934c52640653ef07af1c366177e6d", "fetched_at": "2026-08-28T04:04:00.123968+00:00", "kind": "readme", "missing": false, "url": "https://github.com/BIT-DataLab/LakeBench"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:18:02.070987+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "242c9dfc15bb8f1802d1cc61e2fa1b0016e934c52640653ef07af1c366177e6d", "fetched_at": "2026-08-28T04:04:00.123968+00:00", "kind": "readme", "missing": false, "url": "https://github.com/BIT-DataLab/LakeBench"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 23, "longevity": 74, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1036, "days_push": 465, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 37, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}