{"adoption": {"forks": 38, "observed_at": "2026-08-28T04:04:08.924685+00:00", "stars": 1255}, "canonical_url": "https://ross.abutalabs.com/products/coyo-dataset", "card": {"archived": true, "artifact_type": "dataset", "description": "COYO-700M: Large-scale Image-Text Pair Dataset", "domain": ["machine-learning", "computer-vision", "artificial-intelligence"], "enriched": true, "function": ["machine-learning", "data-science", "etl"], "health_score": 10, "homepage": "https://kakaobrain.com/contents?contentId=7eca73e3-3089-43cb-b701-332e8a1743fd", "language": "Python", "license": null, "license_family": "other", "maturity": "maintenance", "member_repos": ["kakaobrain/coyo-dataset"], "name": "kakaobrain/coyo-dataset", "platform": ["python", "cross-platform"], "pushed_at": "2022-11-30T06:54:50+00:00", "repo": "kakaobrain/coyo-dataset", "stars": 1255, "tags": ["image-text-pairs", "multimodal", "vision-language", "common-crawl", "foundation-models", "text-to-image", "alt-text", "natural-language-processing"], "topics": [], "urls": [], "use_cases": ["train text-to-image diffusion models", "pretrain CLIP-style contrastive vision-language models", "get large-scale image caption pairs for multimodal research", "download a web-crawled image-text dataset as an alternative to LAION", "filter and prepare web-scraped training data", "train large-scale vision-language foundation models"], "what_it_is": "COYO-700M is a large-scale dataset of 747M image-text pairs scraped from CommonCrawl HTML documents, with extensive image- and text-level filtering and meta-attributes. The repository provides documentation, download tooling, and subset releases like COYO-Labeled-300M for training vision-language foundation models.", "when_to_avoid": ["you need curated, human-annotated image captions", "you only need a small clean dataset for fine-tuning", "you require a permissive license - the repo has no license file"], "when_to_choose": []}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/coyo-dataset", "repo": "kakaobrain/coyo-dataset", "role": "main", "score": 10}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.924685+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T05:07:20.249384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d204e3a4c8a7cb5bea04f46060d2a58531611eaf6625cfc7469f419dd2620bc8", "fetched_at": "2026-08-28T04:04:08.924685+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kakaobrain/coyo-dataset"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.924685+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T05:07:20.249384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d204e3a4c8a7cb5bea04f46060d2a58531611eaf6625cfc7469f419dd2620bc8", "fetched_at": "2026-08-28T04:04:08.924685+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kakaobrain/coyo-dataset"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T05:07:20.249384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d204e3a4c8a7cb5bea04f46060d2a58531611eaf6625cfc7469f419dd2620bc8", "fetched_at": "2026-08-28T04:04:08.924685+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kakaobrain/coyo-dataset"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.924685+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.924685+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.924685+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T05:07:20.249384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d204e3a4c8a7cb5bea04f46060d2a58531611eaf6625cfc7469f419dd2620bc8", "fetched_at": "2026-08-28T04:04:08.924685+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kakaobrain/coyo-dataset"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.924685+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.924685+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T05:07:20.249384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d204e3a4c8a7cb5bea04f46060d2a58531611eaf6625cfc7469f419dd2620bc8", "fetched_at": "2026-08-28T04:04:08.924685+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kakaobrain/coyo-dataset"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.924685+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.924685+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.924685+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T05:07:20.249384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d204e3a4c8a7cb5bea04f46060d2a58531611eaf6625cfc7469f419dd2620bc8", "fetched_at": "2026-08-28T04:04:08.924685+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kakaobrain/coyo-dataset"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.924685+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:08.924685+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T05:07:20.249384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d204e3a4c8a7cb5bea04f46060d2a58531611eaf6625cfc7469f419dd2620bc8", "fetched_at": "2026-08-28T04:04:08.924685+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kakaobrain/coyo-dataset"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T05:07:20.249384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d204e3a4c8a7cb5bea04f46060d2a58531611eaf6625cfc7469f419dd2620bc8", "fetched_at": "2026-08-28T04:04:08.924685+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kakaobrain/coyo-dataset"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T05:07:20.249384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d204e3a4c8a7cb5bea04f46060d2a58531611eaf6625cfc7469f419dd2620bc8", "fetched_at": "2026-08-28T04:04:08.924685+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kakaobrain/coyo-dataset"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T05:07:20.249384+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d204e3a4c8a7cb5bea04f46060d2a58531611eaf6625cfc7469f419dd2620bc8", "fetched_at": "2026-08-28T04:04:08.924685+00:00", "kind": "readme", "missing": false, "url": "https://github.com/kakaobrain/coyo-dataset"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 0, "longevity": 100, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+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": 1464, "days_push": 1372, "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}}