{"adoption": {"forks": 164, "observed_at": "2026-08-28T04:03:44.083816+00:00", "stars": 1138}, "canonical_url": "https://ross.abutalabs.com/products/natural-questions", "card": {"archived": true, "artifact_type": "dataset", "description": "Natural Questions (NQ) contains real user questions issued to Google search, and answers found from Wikipedia by annotators. NQ is designed for the training and evaluation of automatic question answering systems.", "domain": ["machine-learning"], "enriched": true, "function": ["machine-learning", "nlp", "data-science"], "health_score": 10, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["google-research-datasets/natural-questions"], "name": "google-research-datasets/natural-questions", "platform": ["python"], "pushed_at": "2021-07-30T00:22:08+00:00", "repo": "google-research-datasets/natural-questions", "stars": 1138, "tags": ["question-answering", "benchmark", "wikipedia", "google-search-queries", "dataset", "natural-language-processing", "search"], "topics": [], "urls": [], "use_cases": ["train a question answering model on real search queries", "evaluate extractive QA systems against a benchmark", "get question-answer pairs from Wikipedia pages", "benchmark long answer and short answer selection models", "compare my QA system on the Natural Questions leaderboard"], "what_it_is": "Natural Questions is a large-scale question answering dataset from Google containing 307k real user search questions paired with Wikipedia pages annotated with long and short answers. The repository provides data utilities, a data browser, and evaluation tooling for training and benchmarking QA systems.", "when_to_avoid": ["you need conversational or multi-turn QA data", "you need small lightweight datasets for quick prototyping", "you need non-English question answering data"], "when_to_choose": ["you need a large, realistic QA benchmark based on real user queries", "you want to compare against published QA baselines and leaderboard results", "you need Wikipedia-sourced training data with human-annotated answers"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/natural-questions", "repo": "google-research-datasets/natural-questions", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:44.083816+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:36:09.031073+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9ca80dc605ab686f997f8cf2338518f2202b102b066cdd1640883cd6b93eb24b", "fetched_at": "2026-08-28T04:03:44.083816+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/natural-questions"}, {"content_hash": "26b41aa48518cc63a23647b8ea6e5e971edcc67410e3e7b34e63329df36d6487", "fetched_at": "2026-08-29T12:41:16.727988+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/natural-questions/json"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:44.083816+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:36:09.031073+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9ca80dc605ab686f997f8cf2338518f2202b102b066cdd1640883cd6b93eb24b", "fetched_at": "2026-08-28T04:03:44.083816+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/natural-questions"}, {"content_hash": "26b41aa48518cc63a23647b8ea6e5e971edcc67410e3e7b34e63329df36d6487", "fetched_at": "2026-08-29T12:41:16.727988+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/natural-questions/json"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:36:09.031073+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9ca80dc605ab686f997f8cf2338518f2202b102b066cdd1640883cd6b93eb24b", "fetched_at": "2026-08-28T04:03:44.083816+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/natural-questions"}, {"content_hash": "26b41aa48518cc63a23647b8ea6e5e971edcc67410e3e7b34e63329df36d6487", "fetched_at": "2026-08-29T12:41:16.727988+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/natural-questions/json"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:44.083816+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:44.083816+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:44.083816+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:36:09.031073+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9ca80dc605ab686f997f8cf2338518f2202b102b066cdd1640883cd6b93eb24b", "fetched_at": "2026-08-28T04:03:44.083816+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/natural-questions"}, {"content_hash": "26b41aa48518cc63a23647b8ea6e5e971edcc67410e3e7b34e63329df36d6487", "fetched_at": "2026-08-29T12:41:16.727988+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/natural-questions/json"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:44.083816+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:44.083816+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:36:09.031073+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9ca80dc605ab686f997f8cf2338518f2202b102b066cdd1640883cd6b93eb24b", "fetched_at": "2026-08-28T04:03:44.083816+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/natural-questions"}, {"content_hash": "26b41aa48518cc63a23647b8ea6e5e971edcc67410e3e7b34e63329df36d6487", "fetched_at": "2026-08-29T12:41:16.727988+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/natural-questions/json"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:44.083816+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:44.083816+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:44.083816+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:36:09.031073+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9ca80dc605ab686f997f8cf2338518f2202b102b066cdd1640883cd6b93eb24b", "fetched_at": "2026-08-28T04:03:44.083816+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/natural-questions"}, {"content_hash": "26b41aa48518cc63a23647b8ea6e5e971edcc67410e3e7b34e63329df36d6487", "fetched_at": "2026-08-29T12:41:16.727988+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/natural-questions/json"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:44.083816+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:44.083816+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:36:09.031073+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9ca80dc605ab686f997f8cf2338518f2202b102b066cdd1640883cd6b93eb24b", "fetched_at": "2026-08-28T04:03:44.083816+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/natural-questions"}, {"content_hash": "26b41aa48518cc63a23647b8ea6e5e971edcc67410e3e7b34e63329df36d6487", "fetched_at": "2026-08-29T12:41:16.727988+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/natural-questions/json"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:36:09.031073+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9ca80dc605ab686f997f8cf2338518f2202b102b066cdd1640883cd6b93eb24b", "fetched_at": "2026-08-28T04:03:44.083816+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/natural-questions"}, {"content_hash": "26b41aa48518cc63a23647b8ea6e5e971edcc67410e3e7b34e63329df36d6487", "fetched_at": "2026-08-29T12:41:16.727988+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/natural-questions/json"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:36:09.031073+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9ca80dc605ab686f997f8cf2338518f2202b102b066cdd1640883cd6b93eb24b", "fetched_at": "2026-08-28T04:03:44.083816+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/natural-questions"}, {"content_hash": "26b41aa48518cc63a23647b8ea6e5e971edcc67410e3e7b34e63329df36d6487", "fetched_at": "2026-08-29T12:41:16.727988+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/natural-questions/json"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:36:09.031073+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "9ca80dc605ab686f997f8cf2338518f2202b102b066cdd1640883cd6b93eb24b", "fetched_at": "2026-08-28T04:03:44.083816+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/natural-questions"}, {"content_hash": "26b41aa48518cc63a23647b8ea6e5e971edcc67410e3e7b34e63329df36d6487", "fetched_at": "2026-08-29T12:41:16.727988+00:00", "kind": "registry_pypi", "missing": false, "url": "https://pypi.org/pypi/natural-questions/json"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": ["no_releases", "archived"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2780, "days_push": 1861, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 10, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}