{"adoption": {"forks": 194, "observed_at": "2026-08-28T04:06:37.283020+00:00", "stars": 2323}, "canonical_url": "https://ross.abutalabs.com/products/open-thoughts", "card": {"archived": false, "artifact_type": "dataset", "description": "Fully open data curation for reasoning models", "domain": ["large-language-models", "machine-learning", "artificial-intelligence", "data-science"], "enriched": true, "function": ["data-generation", "machine-learning", "llm-training", "rag"], "health_score": 53, "homepage": "https://open-thoughts.ai", "language": "Python", "license": "Apache-2.0", "license_family": "permissive", "maturity": "active", "member_repos": ["open-thoughts/open-thoughts"], "name": "open-thoughts/open-thoughts", "platform": ["python"], "pushed_at": "2025-12-02T21:57:07+00:00", "repo": "open-thoughts/open-thoughts", "stars": 2323, "tags": ["reasoning-datasets", "post-training", "sft", "distillation", "open-data", "huggingface"], "topics": ["open-data", "reasoning"], "urls": [], "use_cases": ["train a small reasoning model that beats DeepSeek-R1-Distill-Qwen-7B", "download open SFT reasoning traces for math and code", "fine-tune an LLM on curated chain-of-thought data", "reproduce a state-of-the-art reasoning dataset recipe", "evaluate reasoning models on open benchmarks", "build post-training data for agent models"], "what_it_is": "OpenThoughts is a community project curating fully open datasets for training reasoning models, including OpenThoughts3-1.2M and OpenThinker models that rival DeepSeek-R1 distills. It provides data curation recipes, training traces, and evaluation benchmarks for math and code reasoning.", "when_to_avoid": ["you need a ready-to-use inference server or chatbot product", "you want general-purpose pretraining corpora rather than reasoning SFT data", "you lack GPU resources for fine-tuning large models"], "when_to_choose": ["you need open, permissively licensed reasoning training data", "you want to distill reasoning capability into smaller models", "you are researching post-training data curation for LLMs"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/open-thoughts", "repo": "open-thoughts/open-thoughts", "role": "main", "score": 45}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.283020+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T02:38:36.239407+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d3dc2d558b93237a8a76a601aa53dca8c9d10abb0b7fd36fc39c6e378ba5a588", "fetched_at": "2026-08-28T04:06:37.283020+00:00", "kind": "readme", "missing": false, "url": "https://github.com/open-thoughts/open-thoughts"}, {"content_hash": "dbc73bf0ac187bf6c51cd4062a01a883a53a1b62d8e9985f95c7294e2f11c622", "fetched_at": "2026-08-29T10:18:50.546412+00:00", "kind": "homepage", "missing": false, "url": "https://open-thoughts.ai"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.283020+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T02:38:36.239407+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d3dc2d558b93237a8a76a601aa53dca8c9d10abb0b7fd36fc39c6e378ba5a588", "fetched_at": "2026-08-28T04:06:37.283020+00:00", "kind": "readme", "missing": false, "url": "https://github.com/open-thoughts/open-thoughts"}, {"content_hash": "dbc73bf0ac187bf6c51cd4062a01a883a53a1b62d8e9985f95c7294e2f11c622", "fetched_at": "2026-08-29T10:18:50.546412+00:00", "kind": "homepage", "missing": false, "url": "https://open-thoughts.ai"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T02:38:36.239407+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d3dc2d558b93237a8a76a601aa53dca8c9d10abb0b7fd36fc39c6e378ba5a588", "fetched_at": "2026-08-28T04:06:37.283020+00:00", "kind": "readme", "missing": false, "url": "https://github.com/open-thoughts/open-thoughts"}, {"content_hash": "dbc73bf0ac187bf6c51cd4062a01a883a53a1b62d8e9985f95c7294e2f11c622", "fetched_at": "2026-08-29T10:18:50.546412+00:00", "kind": "homepage", "missing": false, "url": "https://open-thoughts.ai"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.283020+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.283020+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.283020+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T02:38:36.239407+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d3dc2d558b93237a8a76a601aa53dca8c9d10abb0b7fd36fc39c6e378ba5a588", "fetched_at": "2026-08-28T04:06:37.283020+00:00", "kind": "readme", "missing": false, "url": "https://github.com/open-thoughts/open-thoughts"}, {"content_hash": "dbc73bf0ac187bf6c51cd4062a01a883a53a1b62d8e9985f95c7294e2f11c622", "fetched_at": "2026-08-29T10:18:50.546412+00:00", "kind": "homepage", "missing": false, "url": "https://open-thoughts.ai"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.283020+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.283020+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T02:38:36.239407+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d3dc2d558b93237a8a76a601aa53dca8c9d10abb0b7fd36fc39c6e378ba5a588", "fetched_at": "2026-08-28T04:06:37.283020+00:00", "kind": "readme", "missing": false, "url": "https://github.com/open-thoughts/open-thoughts"}, {"content_hash": "dbc73bf0ac187bf6c51cd4062a01a883a53a1b62d8e9985f95c7294e2f11c622", "fetched_at": "2026-08-29T10:18:50.546412+00:00", "kind": "homepage", "missing": false, "url": "https://open-thoughts.ai"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.283020+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.283020+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.283020+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T02:38:36.239407+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d3dc2d558b93237a8a76a601aa53dca8c9d10abb0b7fd36fc39c6e378ba5a588", "fetched_at": "2026-08-28T04:06:37.283020+00:00", "kind": "readme", "missing": false, "url": "https://github.com/open-thoughts/open-thoughts"}, {"content_hash": "dbc73bf0ac187bf6c51cd4062a01a883a53a1b62d8e9985f95c7294e2f11c622", "fetched_at": "2026-08-29T10:18:50.546412+00:00", "kind": "homepage", "missing": false, "url": "https://open-thoughts.ai"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.283020+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:06:37.283020+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T02:38:36.239407+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d3dc2d558b93237a8a76a601aa53dca8c9d10abb0b7fd36fc39c6e378ba5a588", "fetched_at": "2026-08-28T04:06:37.283020+00:00", "kind": "readme", "missing": false, "url": "https://github.com/open-thoughts/open-thoughts"}, {"content_hash": "dbc73bf0ac187bf6c51cd4062a01a883a53a1b62d8e9985f95c7294e2f11c622", "fetched_at": "2026-08-29T10:18:50.546412+00:00", "kind": "homepage", "missing": false, "url": "https://open-thoughts.ai"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T02:38:36.239407+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d3dc2d558b93237a8a76a601aa53dca8c9d10abb0b7fd36fc39c6e378ba5a588", "fetched_at": "2026-08-28T04:06:37.283020+00:00", "kind": "readme", "missing": false, "url": "https://github.com/open-thoughts/open-thoughts"}, {"content_hash": "dbc73bf0ac187bf6c51cd4062a01a883a53a1b62d8e9985f95c7294e2f11c622", "fetched_at": "2026-08-29T10:18:50.546412+00:00", "kind": "homepage", "missing": false, "url": "https://open-thoughts.ai"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T02:38:36.239407+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d3dc2d558b93237a8a76a601aa53dca8c9d10abb0b7fd36fc39c6e378ba5a588", "fetched_at": "2026-08-28T04:06:37.283020+00:00", "kind": "readme", "missing": false, "url": "https://github.com/open-thoughts/open-thoughts"}, {"content_hash": "dbc73bf0ac187bf6c51cd4062a01a883a53a1b62d8e9985f95c7294e2f11c622", "fetched_at": "2026-08-29T10:18:50.546412+00:00", "kind": "homepage", "missing": false, "url": "https://open-thoughts.ai"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T02:38:36.239407+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "d3dc2d558b93237a8a76a601aa53dca8c9d10abb0b7fd36fc39c6e378ba5a588", "fetched_at": "2026-08-28T04:06:37.283020+00:00", "kind": "readme", "missing": false, "url": "https://github.com/open-thoughts/open-thoughts"}, {"content_hash": "dbc73bf0ac187bf6c51cd4062a01a883a53a1b62d8e9985f95c7294e2f11c622", "fetched_at": "2026-08-29T10:18:50.546412+00:00", "kind": "homepage", "missing": false, "url": "https://open-thoughts.ai"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 55, "longevity": 41, "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": 583, "days_push": 274, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 45, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}