{"adoption": {"forks": 232, "observed_at": "2026-08-28T04:05:25.816808+00:00", "stars": 1712}, "canonical_url": "https://ross.abutalabs.com/products/scibert", "card": {"archived": false, "artifact_type": "library", "description": "A BERT model for scientific text.", "domain": ["machine-learning", "artificial-intelligence"], "enriched": true, "function": ["nlp", "machine-learning", "parser"], "health_score": 20, "homepage": "https://arxiv.org/abs/1903.10676", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "maintenance", "member_repos": ["allenai/scibert"], "name": "allenai/scibert", "platform": ["python"], "pushed_at": "2022-02-22T19:57:07+00:00", "repo": "allenai/scibert", "stars": 1712, "tags": ["bert", "scientific-text", "pretrained-model", "transformers", "named-entity-recognition", "sentence-classification", "natural-language-processing"], "topics": ["bert", "nlp", "scientific-papers"], "urls": [], "use_cases": ["extract named entities like chemicals and diseases from biomedical papers", "classify citation intent in scientific literature", "classify sentences in scientific abstracts by their role", "extract relations between scientific entities", "fine-tune a language model on scientific text with limited labeled data", "parse dependencies in scientific sentences"], "what_it_is": "SciBERT is a BERT-based pretrained language model trained on a large multi-domain corpus of scientific publications, released by the Allen Institute for AI. It provides pretrained weights and code that improve performance on downstream scientific NLP tasks such as sequence tagging, sentence classification, and dependency parsing.", "when_to_avoid": ["you need a general-purpose language model for non-scientific text", "you need the latest large language models rather than BERT-era encoders", "you require actively maintained tooling, as the repo has seen few recent updates"], "when_to_choose": ["you need strong baselines or embeddings for scientific or biomedical NLP tasks", "you have limited labeled scientific data and want transfer learning from a domain-specific pretrained model", "you want a well-cited, Apache-2.0 licensed BERT variant for academic text"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/scibert", "repo": "allenai/scibert", "role": "main", "score": 32}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.816808+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T03:34:51.832396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "af33585bef6b4720264545eb0827bc63ded2f4d5db10f6ba3c357cafa0c08688", "fetched_at": "2026-08-28T04:05:25.816808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/scibert"}, {"content_hash": "c1cce416fb17694e7e6007a209a48856b3ad6aa95e1b7f8d0b67f6bad3a8f697", "fetched_at": "2026-08-29T11:10:53.595738+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1903.10676"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:10:53.605244+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:10:53.608963+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:10:53.610900+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:10:53.607157+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.816808+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T03:34:51.832396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "af33585bef6b4720264545eb0827bc63ded2f4d5db10f6ba3c357cafa0c08688", "fetched_at": "2026-08-28T04:05:25.816808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/scibert"}, {"content_hash": "c1cce416fb17694e7e6007a209a48856b3ad6aa95e1b7f8d0b67f6bad3a8f697", "fetched_at": "2026-08-29T11:10:53.595738+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1903.10676"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:10:53.605244+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:10:53.608963+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:10:53.610900+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:10:53.607157+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T03:34:51.832396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "af33585bef6b4720264545eb0827bc63ded2f4d5db10f6ba3c357cafa0c08688", "fetched_at": "2026-08-28T04:05:25.816808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/scibert"}, {"content_hash": "c1cce416fb17694e7e6007a209a48856b3ad6aa95e1b7f8d0b67f6bad3a8f697", "fetched_at": "2026-08-29T11:10:53.595738+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1903.10676"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:10:53.605244+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:10:53.608963+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:10:53.610900+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:10:53.607157+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.816808+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.816808+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.816808+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T03:34:51.832396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "af33585bef6b4720264545eb0827bc63ded2f4d5db10f6ba3c357cafa0c08688", "fetched_at": "2026-08-28T04:05:25.816808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/scibert"}, {"content_hash": "c1cce416fb17694e7e6007a209a48856b3ad6aa95e1b7f8d0b67f6bad3a8f697", "fetched_at": "2026-08-29T11:10:53.595738+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1903.10676"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:10:53.605244+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:10:53.608963+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:10:53.610900+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:10:53.607157+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.816808+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.816808+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T03:34:51.832396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "af33585bef6b4720264545eb0827bc63ded2f4d5db10f6ba3c357cafa0c08688", "fetched_at": "2026-08-28T04:05:25.816808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/scibert"}, {"content_hash": "c1cce416fb17694e7e6007a209a48856b3ad6aa95e1b7f8d0b67f6bad3a8f697", "fetched_at": "2026-08-29T11:10:53.595738+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1903.10676"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:10:53.605244+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:10:53.608963+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:10:53.610900+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:10:53.607157+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.816808+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.816808+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.816808+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T03:34:51.832396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "af33585bef6b4720264545eb0827bc63ded2f4d5db10f6ba3c357cafa0c08688", "fetched_at": "2026-08-28T04:05:25.816808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/scibert"}, {"content_hash": "c1cce416fb17694e7e6007a209a48856b3ad6aa95e1b7f8d0b67f6bad3a8f697", "fetched_at": "2026-08-29T11:10:53.595738+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1903.10676"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:10:53.605244+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:10:53.608963+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:10:53.610900+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:10:53.607157+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.816808+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:25.816808+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T03:34:51.832396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "af33585bef6b4720264545eb0827bc63ded2f4d5db10f6ba3c357cafa0c08688", "fetched_at": "2026-08-28T04:05:25.816808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/scibert"}, {"content_hash": "c1cce416fb17694e7e6007a209a48856b3ad6aa95e1b7f8d0b67f6bad3a8f697", "fetched_at": "2026-08-29T11:10:53.595738+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1903.10676"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:10:53.605244+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:10:53.608963+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:10:53.610900+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:10:53.607157+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T03:34:51.832396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "af33585bef6b4720264545eb0827bc63ded2f4d5db10f6ba3c357cafa0c08688", "fetched_at": "2026-08-28T04:05:25.816808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/scibert"}, {"content_hash": "c1cce416fb17694e7e6007a209a48856b3ad6aa95e1b7f8d0b67f6bad3a8f697", "fetched_at": "2026-08-29T11:10:53.595738+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1903.10676"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:10:53.605244+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:10:53.608963+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:10:53.610900+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:10:53.607157+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T03:34:51.832396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "af33585bef6b4720264545eb0827bc63ded2f4d5db10f6ba3c357cafa0c08688", "fetched_at": "2026-08-28T04:05:25.816808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/scibert"}, {"content_hash": "c1cce416fb17694e7e6007a209a48856b3ad6aa95e1b7f8d0b67f6bad3a8f697", "fetched_at": "2026-08-29T11:10:53.595738+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1903.10676"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:10:53.605244+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:10:53.608963+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:10:53.610900+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:10:53.607157+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T03:34:51.832396+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "af33585bef6b4720264545eb0827bc63ded2f4d5db10f6ba3c357cafa0c08688", "fetched_at": "2026-08-28T04:05:25.816808+00:00", "kind": "readme", "missing": false, "url": "https://github.com/allenai/scibert"}, {"content_hash": "c1cce416fb17694e7e6007a209a48856b3ad6aa95e1b7f8d0b67f6bad3a8f697", "fetched_at": "2026-08-29T11:10:53.595738+00:00", "kind": "homepage", "missing": false, "url": "https://arxiv.org/abs/1903.10676"}, {"content_hash": "cca9c3a11c56b1212864e03fb8a5511a3bdb6df53398ba4dd2ed778f931607dd", "fetched_at": "2026-08-29T11:10:53.605244+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/donate.html"}, {"content_hash": "47cbc55ff1deaca3f36b463373de863a7053d91cacf9f95725618e11610209ae", "fetched_at": "2026-08-29T11:10:53.608963+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about/ourmembers.html"}, {"content_hash": "a1f16f915a9ad89ee57c3e929a1b6577d481f52c05f8015fc720b16ee8014f19", "fetched_at": "2026-08-29T11:10:53.610900+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/about"}, {"content_hash": "b14a8d05a0ec337409ab63bffd91306b5317b16fac358aa6d1fe6afbaf3c8628", "fetched_at": "2026-08-29T11:10:53.607157+00:00", "kind": "site_page", "missing": false, "url": "https://info.arxiv.org/labs/index.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "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": 2772, "days_push": 1653, "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}}