{"adoption": {"forks": 239, "observed_at": "2026-08-28T04:04:16.921438+00:00", "stars": 1296}, "canonical_url": "https://ross.abutalabs.com/products/rc-data", "card": {"archived": true, "artifact_type": "dataset", "description": "Question answering dataset featured in \"Teaching Machines to Read and Comprehend", "domain": ["machine-learning", "deep-learning"], "enriched": true, "function": ["nlp", "machine-learning", "data-generation"], "health_score": 10, "homepage": null, "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["google-deepmind/rc-data"], "name": "google-deepmind/rc-data", "platform": ["python", "cli"], "pushed_at": "2017-04-26T15:05:19+00:00", "repo": "google-deepmind/rc-data", "stars": 1296, "tags": ["question-answering", "reading-comprehension", "cnn-dailymail", "benchmark-dataset", "nips-2015", "natural-language-processing", "linux"], "topics": [], "urls": [], "use_cases": ["train reading comprehension models on CNN/Daily Mail QA pairs", "benchmark machine reading comprehension algorithms", "generate question answering datasets from news articles", "evaluate abstractive and extractive summarization baselines", "download processed CNN/Daily Mail QA data for NLP research"], "what_it_is": "A question answering corpus from DeepMind accompanying the paper 'Teaching Machines to Read and Comprehend' (Hermann et al., NIPS 2015). It includes a Python script to generate question/answer pairs from CNN and Daily Mail news articles downloaded via the Wayback Machine.", "when_to_avoid": ["you need a modern, actively maintained QA dataset", "you cannot work with Python 2.7-era scripts and Wayback Machine downloads", "you want conversational or multi-hop QA rather than cloze-style entity questions"], "when_to_choose": ["you need the original CNN/Daily Mail reading comprehension dataset from the NIPS 2015 paper", "you want to reproduce or cite Hermann et al.'s QA corpus in research", "you need a large-scale cloze-style question answering benchmark"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/rc-data", "repo": "google-deepmind/rc-data", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.921438+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:53:57.480683+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6ebf26d9ffd7460c7137382028f535e1621f467c5db15de24dbaee9f6c82c8f5", "fetched_at": "2026-08-28T04:04:16.921438+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-deepmind/rc-data"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.921438+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:53:57.480683+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6ebf26d9ffd7460c7137382028f535e1621f467c5db15de24dbaee9f6c82c8f5", "fetched_at": "2026-08-28T04:04:16.921438+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-deepmind/rc-data"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:53:57.480683+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6ebf26d9ffd7460c7137382028f535e1621f467c5db15de24dbaee9f6c82c8f5", "fetched_at": "2026-08-28T04:04:16.921438+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-deepmind/rc-data"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.921438+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.921438+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.921438+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:53:57.480683+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6ebf26d9ffd7460c7137382028f535e1621f467c5db15de24dbaee9f6c82c8f5", "fetched_at": "2026-08-28T04:04:16.921438+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-deepmind/rc-data"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.921438+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.921438+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:53:57.480683+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6ebf26d9ffd7460c7137382028f535e1621f467c5db15de24dbaee9f6c82c8f5", "fetched_at": "2026-08-28T04:04:16.921438+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-deepmind/rc-data"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.921438+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.921438+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.921438+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:53:57.480683+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6ebf26d9ffd7460c7137382028f535e1621f467c5db15de24dbaee9f6c82c8f5", "fetched_at": "2026-08-28T04:04:16.921438+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-deepmind/rc-data"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.921438+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:16.921438+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:53:57.480683+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6ebf26d9ffd7460c7137382028f535e1621f467c5db15de24dbaee9f6c82c8f5", "fetched_at": "2026-08-28T04:04:16.921438+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-deepmind/rc-data"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:53:57.480683+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6ebf26d9ffd7460c7137382028f535e1621f467c5db15de24dbaee9f6c82c8f5", "fetched_at": "2026-08-28T04:04:16.921438+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-deepmind/rc-data"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:53:57.480683+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6ebf26d9ffd7460c7137382028f535e1621f467c5db15de24dbaee9f6c82c8f5", "fetched_at": "2026-08-28T04:04:16.921438+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-deepmind/rc-data"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:53:57.480683+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "6ebf26d9ffd7460c7137382028f535e1621f467c5db15de24dbaee9f6c82c8f5", "fetched_at": "2026-08-28T04:04:16.921438+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-deepmind/rc-data"}], "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": 3992, "days_push": 3416, "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}}