{"adoption": {"forks": 47, "observed_at": "2026-08-28T04:03:38.116061+00:00", "stars": 1113}, "canonical_url": "https://ross.abutalabs.com/products/wit", "card": {"archived": true, "artifact_type": "dataset", "description": "WIT (Wikipedia-based Image Text) Dataset is a large multimodal multilingual dataset comprising 37M+ image-text sets with 11M+ unique images across 100+ languages.", "domain": ["machine-learning", "computer-vision", "large-language-models"], "enriched": true, "function": ["machine-learning", "nlp", "image-processing"], "health_score": 10, "homepage": "https://github.com/google-research-datasets/wit", "language": null, "license": "NOASSERTION", "license_family": "other", "maturity": "maintenance", "member_repos": ["google-research-datasets/wit"], "name": "google-research-datasets/wit", "platform": ["python", "cross-platform"], "pushed_at": "2024-09-27T20:55:42+00:00", "repo": "google-research-datasets/wit", "stars": 1113, "tags": ["multimodal", "multilingual", "image-text", "wikipedia", "pretraining", "vision-language", "dataset", "natural-language-processing"], "topics": ["nlp", "machine-learning", "wikipedia", "multimodal", "multilingual", "cc-by-sa-3"], "urls": [], "use_cases": ["pretrain a vision-language model on image-text pairs", "find a large multilingual image captioning dataset", "train a CLIP-style multimodal model", "evaluate cross-lingual image-text retrieval", "get image-text training data covering 100+ languages", "benchmark multimodal models on real-world entities"], "what_it_is": "WIT (Wikipedia-based Image Text) is a large multimodal multilingual dataset of 37.6 million image-text pairs with 11.5 million unique images across 108 Wikipedia languages. It is intended for pretraining and evaluating multimodal machine learning models such as vision-language models.", "when_to_avoid": ["you need a small, curated dataset for quick experiments", "you require commercial licensing beyond CC BY-SA 3.0 terms", "you need actively maintained tooling rather than a static dataset release"], "when_to_choose": ["you need a massive, publicly available image-text corpus for multimodal pretraining", "you need multilingual coverage across 108 languages", "you want page-level metadata and contextual information alongside image-text pairs"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/wit", "repo": "google-research-datasets/wit", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.116061+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:42:36.698234+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "17f39a59724d48f3b4ef7b70c128ab6a408655767b0622ef404951161a854626", "fetched_at": "2026-08-28T04:03:38.116061+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/wit"}, {"content_hash": "ce69c99827e604573434dd6ab448f6167b1de535811d8cb2ccd8bf59a37e2c1f", "fetched_at": "2026-08-29T12:46:37.289644+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/google-research-datasets/wit"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.116061+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:42:36.698234+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "17f39a59724d48f3b4ef7b70c128ab6a408655767b0622ef404951161a854626", "fetched_at": "2026-08-28T04:03:38.116061+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/wit"}, {"content_hash": "ce69c99827e604573434dd6ab448f6167b1de535811d8cb2ccd8bf59a37e2c1f", "fetched_at": "2026-08-29T12:46:37.289644+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/google-research-datasets/wit"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:42:36.698234+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "17f39a59724d48f3b4ef7b70c128ab6a408655767b0622ef404951161a854626", "fetched_at": "2026-08-28T04:03:38.116061+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/wit"}, {"content_hash": "ce69c99827e604573434dd6ab448f6167b1de535811d8cb2ccd8bf59a37e2c1f", "fetched_at": "2026-08-29T12:46:37.289644+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/google-research-datasets/wit"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.116061+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.116061+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.116061+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:42:36.698234+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "17f39a59724d48f3b4ef7b70c128ab6a408655767b0622ef404951161a854626", "fetched_at": "2026-08-28T04:03:38.116061+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/wit"}, {"content_hash": "ce69c99827e604573434dd6ab448f6167b1de535811d8cb2ccd8bf59a37e2c1f", "fetched_at": "2026-08-29T12:46:37.289644+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/google-research-datasets/wit"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.116061+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.116061+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:42:36.698234+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "17f39a59724d48f3b4ef7b70c128ab6a408655767b0622ef404951161a854626", "fetched_at": "2026-08-28T04:03:38.116061+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/wit"}, {"content_hash": "ce69c99827e604573434dd6ab448f6167b1de535811d8cb2ccd8bf59a37e2c1f", "fetched_at": "2026-08-29T12:46:37.289644+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/google-research-datasets/wit"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.116061+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.116061+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.116061+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:42:36.698234+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "17f39a59724d48f3b4ef7b70c128ab6a408655767b0622ef404951161a854626", "fetched_at": "2026-08-28T04:03:38.116061+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/wit"}, {"content_hash": "ce69c99827e604573434dd6ab448f6167b1de535811d8cb2ccd8bf59a37e2c1f", "fetched_at": "2026-08-29T12:46:37.289644+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/google-research-datasets/wit"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.116061+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:38.116061+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:42:36.698234+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "17f39a59724d48f3b4ef7b70c128ab6a408655767b0622ef404951161a854626", "fetched_at": "2026-08-28T04:03:38.116061+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/wit"}, {"content_hash": "ce69c99827e604573434dd6ab448f6167b1de535811d8cb2ccd8bf59a37e2c1f", "fetched_at": "2026-08-29T12:46:37.289644+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/google-research-datasets/wit"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:42:36.698234+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "17f39a59724d48f3b4ef7b70c128ab6a408655767b0622ef404951161a854626", "fetched_at": "2026-08-28T04:03:38.116061+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/wit"}, {"content_hash": "ce69c99827e604573434dd6ab448f6167b1de535811d8cb2ccd8bf59a37e2c1f", "fetched_at": "2026-08-29T12:46:37.289644+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/google-research-datasets/wit"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:42:36.698234+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "17f39a59724d48f3b4ef7b70c128ab6a408655767b0622ef404951161a854626", "fetched_at": "2026-08-28T04:03:38.116061+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/wit"}, {"content_hash": "ce69c99827e604573434dd6ab448f6167b1de535811d8cb2ccd8bf59a37e2c1f", "fetched_at": "2026-08-29T12:46:37.289644+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/google-research-datasets/wit"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:42:36.698234+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "17f39a59724d48f3b4ef7b70c128ab6a408655767b0622ef404951161a854626", "fetched_at": "2026-08-28T04:03:38.116061+00:00", "kind": "readme", "missing": false, "url": "https://github.com/google-research-datasets/wit"}, {"content_hash": "ce69c99827e604573434dd6ab448f6167b1de535811d8cb2ccd8bf59a37e2c1f", "fetched_at": "2026-08-29T12:46:37.289644+00:00", "kind": "homepage", "missing": false, "url": "https://github.com/google-research-datasets/wit"}], "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", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 2016, "days_push": 705, "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}}