{"adoption": {"forks": 79, "observed_at": "2026-08-28T04:03:31.026000+00:00", "stars": 1082}, "canonical_url": "https://ross.abutalabs.com/products/s2orc", "card": {"archived": false, "artifact_type": "dataset", "description": "S2ORC: The Semantic Scholar Open Research Corpus:  https://www.aclweb.org/anthology/2020.acl-main.447/", "domain": ["data-science", "big-data"], "enriched": true, "function": ["nlp", "data-science", "parser"], "health_score": 20, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["allenai/s2orc"], "name": "allenai/s2orc", "platform": ["python", "cross-platform"], "pushed_at": "2024-04-26T20:45:42+00:00", "repo": "allenai/s2orc", "stars": 1082, "tags": ["scientific-papers", "research-corpus", "text-mining", "open-research-corpus", "semantic-scholar", "pdf-parsing", "latex-parsing", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["train language models on scientific full text", "mine citations and citation contexts from research papers", "build search or recommendation systems over scholarly literature", "extract structured text from PDFs and LaTeX sources", "run NLP experiments on academic corpora", "analyze trends across millions of scientific papers"], "what_it_is": "S2ORC is a large-scale open corpus of over 136 million scientific paper records with full text for roughly 12 million papers, built for NLP and text mining research. It is now distributed as a continuously updated bulk dataset via the Semantic Scholar Public API, with tooling like s2orc-doc2 for parsing PDFs and LaTeX into JSON.", "when_to_avoid": ["you need a small curated dataset rather than hundreds of gigabytes of data", "you require a permissive software license for the repo code (the corpus is ODC-By 1.0 and the repo has no license)", "you need hands-on support for the legacy 2020 release, which is no longer supported"], "when_to_choose": ["you need large-scale full-text scientific paper data for NLP or text mining", "you want citation-linked metadata and parsed paper text in a consistent schema", "you want a continuously updated corpus via the Semantic Scholar API"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/s2orc", "repo": "allenai/s2orc", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.026000+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:51:14.378589+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "885ed1b78569a6ec67963516662780a05bd52f70bbb143f602e05aea1901e1cf", "fetched_at": "2026-08-28T04:03:31.026000+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/s2orc"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.026000+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:51:14.378589+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "885ed1b78569a6ec67963516662780a05bd52f70bbb143f602e05aea1901e1cf", "fetched_at": "2026-08-28T04:03:31.026000+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/s2orc"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:51:14.378589+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "885ed1b78569a6ec67963516662780a05bd52f70bbb143f602e05aea1901e1cf", "fetched_at": "2026-08-28T04:03:31.026000+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/s2orc"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.026000+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.026000+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.026000+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:51:14.378589+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "885ed1b78569a6ec67963516662780a05bd52f70bbb143f602e05aea1901e1cf", "fetched_at": "2026-08-28T04:03:31.026000+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/s2orc"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.026000+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.026000+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:51:14.378589+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "885ed1b78569a6ec67963516662780a05bd52f70bbb143f602e05aea1901e1cf", "fetched_at": "2026-08-28T04:03:31.026000+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/s2orc"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.026000+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.026000+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.026000+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:51:14.378589+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "885ed1b78569a6ec67963516662780a05bd52f70bbb143f602e05aea1901e1cf", "fetched_at": "2026-08-28T04:03:31.026000+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/s2orc"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.026000+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:31.026000+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:51:14.378589+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "885ed1b78569a6ec67963516662780a05bd52f70bbb143f602e05aea1901e1cf", "fetched_at": "2026-08-28T04:03:31.026000+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/s2orc"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:51:14.378589+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "885ed1b78569a6ec67963516662780a05bd52f70bbb143f602e05aea1901e1cf", "fetched_at": "2026-08-28T04:03:31.026000+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/s2orc"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:51:14.378589+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "885ed1b78569a6ec67963516662780a05bd52f70bbb143f602e05aea1901e1cf", "fetched_at": "2026-08-28T04:03:31.026000+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/s2orc"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:51:14.378589+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "885ed1b78569a6ec67963516662780a05bd52f70bbb143f602e05aea1901e1cf", "fetched_at": "2026-08-28T04:03:31.026000+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/s2orc"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-03T02:20:16.233290+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": 2494, "days_push": 859, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 32, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}