{"adoption": {"forks": 58, "observed_at": "2026-08-28T04:03:39.069712+00:00", "stars": 1117}, "canonical_url": "https://ross.abutalabs.com/products/datadreamer", "card": {"archived": false, "artifact_type": "library", "description": "DataDreamer: Prompt. Generate Synthetic Data. Train & Align Models.    🤖💤", "domain": ["machine-learning", "large-language-models", "data-science", "artificial-intelligence"], "enriched": true, "function": ["machine-learning", "llm-training", "prompt-engineering", "rag", "data-generation", "etl"], "health_score": 34, "homepage": "https://datadreamer.dev", "language": "Python", "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["datadreamer-dev/DataDreamer"], "name": "datadreamer-dev/DataDreamer", "platform": ["python", "cross-platform"], "pushed_at": "2025-02-02T21:23:50+00:00", "repo": "datadreamer-dev/DataDreamer", "stars": 1117, "tags": ["synthetic-data", "llm-workflows", "instruction-tuning", "alignment", "distillation", "pytorch", "transformers", "openai", "research-tools", "llmops", "natural-language-processing", "gpu"], "topics": ["deep-learning", "machine-learning", "natural-language-processing", "nlp", "nlp-library", "python", "pytorch", "transformers", "alignment", "fine-tuning", "gpt", "instruction-tuning", "llm", "llmops", "llms", "openai", "synthetic-data", "synthetic-dataset-generation"], "urls": [], "use_cases": ["generate synthetic training data with an llm", "distill gpt-4 capabilities into a smaller cheaper model", "instruction-tune a large language model", "align a model with human preferences", "augment an existing dataset using llms", "clean or filter a dataset with llm prompts", "bootstrap few-shot examples for prompting", "train a self-improving llm with self-rewarding"], "what_it_is": "DataDreamer is an open-source Python library for prompting LLMs, generating synthetic datasets, and training or aligning models in reproducible workflows. It provides research-grade building blocks for data generation, distillation, instruction-tuning, and preference alignment.", "when_to_avoid": ["you only need a simple OpenAI API wrapper without training features", "you need a production serving/inference platform rather than data and training workflows", "you work outside Python or the PyTorch/Transformers ecosystem"], "when_to_choose": ["you need reproducible, research-grade synthetic data generation pipelines", "you want to distill a large LLM into a smaller model", "you are doing NLP/ML research involving instruction-tuning or alignment", "you want caching and saved outputs for LLM workflows out of the box"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/datadreamer", "repo": "datadreamer-dev/DataDreamer", "role": "main", "score": 33}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:03:39.069712+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T06:41:53.201547+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "248c7326918f65141b95ce05755a079aa6a3b945041b04fc5eec00e8f3461511", "fetched_at": "2026-08-28T04:03:39.069712+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datadreamer-dev/DataDreamer"}, {"content_hash": "f9eb22f1969b033aff20e7f1a86586221a9a8879f50cf80a9739b7b6efc1a102", "fetched_at": "2026-08-29T12:45:59.739980+00:00", "kind": "homepage", "missing": false, "url": "https://datadreamer.dev"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:45:59.749071+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/installation.html"}, {"content_hash": "a5da9539f76f4ad8ef5d11b71bb6a0fea2b4706ccb6302c0904b08394bfa8584", "fetched_at": "2026-08-29T12:45:59.750801+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/index.html"}, {"content_hash": "35a2f166823aa7f5e40c3851f8ed37952c16b0f88a11aaa11d6e639505273297", "fetched_at": "2026-08-29T12:45:59.752934+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/motivation_and_design.html"}, {"content_hash": "aa515dd9acfdb29fd32a28143808b01c8b8f02ef3b38d0837983ff76c5148836", "fetched_at": "2026-08-29T12:45:59.755490+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/abstract_to_tweet.html"}, {"content_hash": "528c62dec0b1eefe24e2208cb60706ba1b32b7b4e984b8fbecf8b9a1a0013a9e", "fetched_at": "2026-08-29T12:45:59.757556+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/attributed_prompts.html"}, {"content_hash": "f455d2b07ca03e1cada466569f5bc29d9d10a298c84c7c983ccd87573b9138bb", "fetched_at": "2026-08-29T12:45:59.759216+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/openai_distillation.html"}, {"content_hash": "f95b33c9b937097598fb9c4619e4081453a17778bb8a42ed7849f5b2fd90fcff", "fetched_at": "2026-08-29T12:45:59.760744+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_augmentation.html"}, {"content_hash": "fc5a838745a8070e611c25300c2253f031dfe3189cd5f6f5e89657b9fbc2d797", "fetched_at": "2026-08-29T12:45:59.762278+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_cleaning.html"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:03:39.069712+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T06:41:53.201547+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "248c7326918f65141b95ce05755a079aa6a3b945041b04fc5eec00e8f3461511", "fetched_at": "2026-08-28T04:03:39.069712+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datadreamer-dev/DataDreamer"}, {"content_hash": "f9eb22f1969b033aff20e7f1a86586221a9a8879f50cf80a9739b7b6efc1a102", "fetched_at": "2026-08-29T12:45:59.739980+00:00", "kind": "homepage", "missing": false, "url": "https://datadreamer.dev"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:45:59.749071+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/installation.html"}, {"content_hash": "a5da9539f76f4ad8ef5d11b71bb6a0fea2b4706ccb6302c0904b08394bfa8584", "fetched_at": "2026-08-29T12:45:59.750801+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/index.html"}, {"content_hash": "35a2f166823aa7f5e40c3851f8ed37952c16b0f88a11aaa11d6e639505273297", "fetched_at": "2026-08-29T12:45:59.752934+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/motivation_and_design.html"}, {"content_hash": "aa515dd9acfdb29fd32a28143808b01c8b8f02ef3b38d0837983ff76c5148836", "fetched_at": "2026-08-29T12:45:59.755490+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/abstract_to_tweet.html"}, {"content_hash": "528c62dec0b1eefe24e2208cb60706ba1b32b7b4e984b8fbecf8b9a1a0013a9e", "fetched_at": "2026-08-29T12:45:59.757556+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/attributed_prompts.html"}, {"content_hash": "f455d2b07ca03e1cada466569f5bc29d9d10a298c84c7c983ccd87573b9138bb", "fetched_at": "2026-08-29T12:45:59.759216+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/openai_distillation.html"}, {"content_hash": "f95b33c9b937097598fb9c4619e4081453a17778bb8a42ed7849f5b2fd90fcff", "fetched_at": "2026-08-29T12:45:59.760744+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_augmentation.html"}, {"content_hash": "fc5a838745a8070e611c25300c2253f031dfe3189cd5f6f5e89657b9fbc2d797", "fetched_at": "2026-08-29T12:45:59.762278+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_cleaning.html"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T06:41:53.201547+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "248c7326918f65141b95ce05755a079aa6a3b945041b04fc5eec00e8f3461511", "fetched_at": "2026-08-28T04:03:39.069712+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datadreamer-dev/DataDreamer"}, {"content_hash": "f9eb22f1969b033aff20e7f1a86586221a9a8879f50cf80a9739b7b6efc1a102", "fetched_at": "2026-08-29T12:45:59.739980+00:00", "kind": "homepage", "missing": false, "url": "https://datadreamer.dev"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:45:59.749071+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/installation.html"}, {"content_hash": "a5da9539f76f4ad8ef5d11b71bb6a0fea2b4706ccb6302c0904b08394bfa8584", "fetched_at": "2026-08-29T12:45:59.750801+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/index.html"}, {"content_hash": "35a2f166823aa7f5e40c3851f8ed37952c16b0f88a11aaa11d6e639505273297", "fetched_at": "2026-08-29T12:45:59.752934+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/motivation_and_design.html"}, {"content_hash": "aa515dd9acfdb29fd32a28143808b01c8b8f02ef3b38d0837983ff76c5148836", "fetched_at": "2026-08-29T12:45:59.755490+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/abstract_to_tweet.html"}, {"content_hash": "528c62dec0b1eefe24e2208cb60706ba1b32b7b4e984b8fbecf8b9a1a0013a9e", "fetched_at": "2026-08-29T12:45:59.757556+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/attributed_prompts.html"}, {"content_hash": "f455d2b07ca03e1cada466569f5bc29d9d10a298c84c7c983ccd87573b9138bb", "fetched_at": "2026-08-29T12:45:59.759216+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/openai_distillation.html"}, {"content_hash": "f95b33c9b937097598fb9c4619e4081453a17778bb8a42ed7849f5b2fd90fcff", "fetched_at": "2026-08-29T12:45:59.760744+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_augmentation.html"}, {"content_hash": "fc5a838745a8070e611c25300c2253f031dfe3189cd5f6f5e89657b9fbc2d797", "fetched_at": "2026-08-29T12:45:59.762278+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_cleaning.html"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:03:39.069712+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:03:39.069712+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:03:39.069712+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T06:41:53.201547+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "248c7326918f65141b95ce05755a079aa6a3b945041b04fc5eec00e8f3461511", "fetched_at": "2026-08-28T04:03:39.069712+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datadreamer-dev/DataDreamer"}, {"content_hash": "f9eb22f1969b033aff20e7f1a86586221a9a8879f50cf80a9739b7b6efc1a102", "fetched_at": "2026-08-29T12:45:59.739980+00:00", "kind": "homepage", "missing": false, "url": "https://datadreamer.dev"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:45:59.749071+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/installation.html"}, {"content_hash": "a5da9539f76f4ad8ef5d11b71bb6a0fea2b4706ccb6302c0904b08394bfa8584", "fetched_at": "2026-08-29T12:45:59.750801+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/index.html"}, {"content_hash": "35a2f166823aa7f5e40c3851f8ed37952c16b0f88a11aaa11d6e639505273297", "fetched_at": "2026-08-29T12:45:59.752934+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/motivation_and_design.html"}, {"content_hash": "aa515dd9acfdb29fd32a28143808b01c8b8f02ef3b38d0837983ff76c5148836", "fetched_at": "2026-08-29T12:45:59.755490+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/abstract_to_tweet.html"}, {"content_hash": "528c62dec0b1eefe24e2208cb60706ba1b32b7b4e984b8fbecf8b9a1a0013a9e", "fetched_at": "2026-08-29T12:45:59.757556+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/attributed_prompts.html"}, {"content_hash": "f455d2b07ca03e1cada466569f5bc29d9d10a298c84c7c983ccd87573b9138bb", "fetched_at": "2026-08-29T12:45:59.759216+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/openai_distillation.html"}, {"content_hash": "f95b33c9b937097598fb9c4619e4081453a17778bb8a42ed7849f5b2fd90fcff", "fetched_at": "2026-08-29T12:45:59.760744+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_augmentation.html"}, {"content_hash": "fc5a838745a8070e611c25300c2253f031dfe3189cd5f6f5e89657b9fbc2d797", "fetched_at": "2026-08-29T12:45:59.762278+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_cleaning.html"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:03:39.069712+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:03:39.069712+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T06:41:53.201547+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "248c7326918f65141b95ce05755a079aa6a3b945041b04fc5eec00e8f3461511", "fetched_at": "2026-08-28T04:03:39.069712+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datadreamer-dev/DataDreamer"}, {"content_hash": "f9eb22f1969b033aff20e7f1a86586221a9a8879f50cf80a9739b7b6efc1a102", "fetched_at": "2026-08-29T12:45:59.739980+00:00", "kind": "homepage", "missing": false, "url": "https://datadreamer.dev"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:45:59.749071+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/installation.html"}, {"content_hash": "a5da9539f76f4ad8ef5d11b71bb6a0fea2b4706ccb6302c0904b08394bfa8584", "fetched_at": "2026-08-29T12:45:59.750801+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/index.html"}, {"content_hash": "35a2f166823aa7f5e40c3851f8ed37952c16b0f88a11aaa11d6e639505273297", "fetched_at": "2026-08-29T12:45:59.752934+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/motivation_and_design.html"}, {"content_hash": "aa515dd9acfdb29fd32a28143808b01c8b8f02ef3b38d0837983ff76c5148836", "fetched_at": "2026-08-29T12:45:59.755490+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/abstract_to_tweet.html"}, {"content_hash": "528c62dec0b1eefe24e2208cb60706ba1b32b7b4e984b8fbecf8b9a1a0013a9e", "fetched_at": "2026-08-29T12:45:59.757556+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/attributed_prompts.html"}, {"content_hash": "f455d2b07ca03e1cada466569f5bc29d9d10a298c84c7c983ccd87573b9138bb", "fetched_at": "2026-08-29T12:45:59.759216+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/openai_distillation.html"}, {"content_hash": "f95b33c9b937097598fb9c4619e4081453a17778bb8a42ed7849f5b2fd90fcff", "fetched_at": "2026-08-29T12:45:59.760744+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_augmentation.html"}, {"content_hash": "fc5a838745a8070e611c25300c2253f031dfe3189cd5f6f5e89657b9fbc2d797", "fetched_at": "2026-08-29T12:45:59.762278+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_cleaning.html"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:03:39.069712+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:03:39.069712+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:03:39.069712+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T06:41:53.201547+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "248c7326918f65141b95ce05755a079aa6a3b945041b04fc5eec00e8f3461511", "fetched_at": "2026-08-28T04:03:39.069712+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datadreamer-dev/DataDreamer"}, {"content_hash": "f9eb22f1969b033aff20e7f1a86586221a9a8879f50cf80a9739b7b6efc1a102", "fetched_at": "2026-08-29T12:45:59.739980+00:00", "kind": "homepage", "missing": false, "url": "https://datadreamer.dev"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:45:59.749071+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/installation.html"}, {"content_hash": "a5da9539f76f4ad8ef5d11b71bb6a0fea2b4706ccb6302c0904b08394bfa8584", "fetched_at": "2026-08-29T12:45:59.750801+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/index.html"}, {"content_hash": "35a2f166823aa7f5e40c3851f8ed37952c16b0f88a11aaa11d6e639505273297", "fetched_at": "2026-08-29T12:45:59.752934+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/motivation_and_design.html"}, {"content_hash": "aa515dd9acfdb29fd32a28143808b01c8b8f02ef3b38d0837983ff76c5148836", "fetched_at": "2026-08-29T12:45:59.755490+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/abstract_to_tweet.html"}, {"content_hash": "528c62dec0b1eefe24e2208cb60706ba1b32b7b4e984b8fbecf8b9a1a0013a9e", "fetched_at": "2026-08-29T12:45:59.757556+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/attributed_prompts.html"}, {"content_hash": "f455d2b07ca03e1cada466569f5bc29d9d10a298c84c7c983ccd87573b9138bb", "fetched_at": "2026-08-29T12:45:59.759216+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/openai_distillation.html"}, {"content_hash": "f95b33c9b937097598fb9c4619e4081453a17778bb8a42ed7849f5b2fd90fcff", "fetched_at": "2026-08-29T12:45:59.760744+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_augmentation.html"}, {"content_hash": "fc5a838745a8070e611c25300c2253f031dfe3189cd5f6f5e89657b9fbc2d797", "fetched_at": "2026-08-29T12:45:59.762278+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_cleaning.html"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:03:39.069712+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:03:39.069712+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T06:41:53.201547+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "248c7326918f65141b95ce05755a079aa6a3b945041b04fc5eec00e8f3461511", "fetched_at": "2026-08-28T04:03:39.069712+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datadreamer-dev/DataDreamer"}, {"content_hash": "f9eb22f1969b033aff20e7f1a86586221a9a8879f50cf80a9739b7b6efc1a102", "fetched_at": "2026-08-29T12:45:59.739980+00:00", "kind": "homepage", "missing": false, "url": "https://datadreamer.dev"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:45:59.749071+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/installation.html"}, {"content_hash": "a5da9539f76f4ad8ef5d11b71bb6a0fea2b4706ccb6302c0904b08394bfa8584", "fetched_at": "2026-08-29T12:45:59.750801+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/index.html"}, {"content_hash": "35a2f166823aa7f5e40c3851f8ed37952c16b0f88a11aaa11d6e639505273297", "fetched_at": "2026-08-29T12:45:59.752934+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/motivation_and_design.html"}, {"content_hash": "aa515dd9acfdb29fd32a28143808b01c8b8f02ef3b38d0837983ff76c5148836", "fetched_at": "2026-08-29T12:45:59.755490+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/abstract_to_tweet.html"}, {"content_hash": "528c62dec0b1eefe24e2208cb60706ba1b32b7b4e984b8fbecf8b9a1a0013a9e", "fetched_at": "2026-08-29T12:45:59.757556+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/attributed_prompts.html"}, {"content_hash": "f455d2b07ca03e1cada466569f5bc29d9d10a298c84c7c983ccd87573b9138bb", "fetched_at": "2026-08-29T12:45:59.759216+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/openai_distillation.html"}, {"content_hash": "f95b33c9b937097598fb9c4619e4081453a17778bb8a42ed7849f5b2fd90fcff", "fetched_at": "2026-08-29T12:45:59.760744+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_augmentation.html"}, {"content_hash": "fc5a838745a8070e611c25300c2253f031dfe3189cd5f6f5e89657b9fbc2d797", "fetched_at": "2026-08-29T12:45:59.762278+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_cleaning.html"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T06:41:53.201547+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "248c7326918f65141b95ce05755a079aa6a3b945041b04fc5eec00e8f3461511", "fetched_at": "2026-08-28T04:03:39.069712+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datadreamer-dev/DataDreamer"}, {"content_hash": "f9eb22f1969b033aff20e7f1a86586221a9a8879f50cf80a9739b7b6efc1a102", "fetched_at": "2026-08-29T12:45:59.739980+00:00", "kind": "homepage", "missing": false, "url": "https://datadreamer.dev"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:45:59.749071+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/installation.html"}, {"content_hash": "a5da9539f76f4ad8ef5d11b71bb6a0fea2b4706ccb6302c0904b08394bfa8584", "fetched_at": "2026-08-29T12:45:59.750801+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/index.html"}, {"content_hash": "35a2f166823aa7f5e40c3851f8ed37952c16b0f88a11aaa11d6e639505273297", "fetched_at": "2026-08-29T12:45:59.752934+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/motivation_and_design.html"}, {"content_hash": "aa515dd9acfdb29fd32a28143808b01c8b8f02ef3b38d0837983ff76c5148836", "fetched_at": "2026-08-29T12:45:59.755490+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/abstract_to_tweet.html"}, {"content_hash": "528c62dec0b1eefe24e2208cb60706ba1b32b7b4e984b8fbecf8b9a1a0013a9e", "fetched_at": "2026-08-29T12:45:59.757556+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/attributed_prompts.html"}, {"content_hash": "f455d2b07ca03e1cada466569f5bc29d9d10a298c84c7c983ccd87573b9138bb", "fetched_at": "2026-08-29T12:45:59.759216+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/openai_distillation.html"}, {"content_hash": "f95b33c9b937097598fb9c4619e4081453a17778bb8a42ed7849f5b2fd90fcff", "fetched_at": "2026-08-29T12:45:59.760744+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_augmentation.html"}, {"content_hash": "fc5a838745a8070e611c25300c2253f031dfe3189cd5f6f5e89657b9fbc2d797", "fetched_at": "2026-08-29T12:45:59.762278+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_cleaning.html"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T06:41:53.201547+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "248c7326918f65141b95ce05755a079aa6a3b945041b04fc5eec00e8f3461511", "fetched_at": "2026-08-28T04:03:39.069712+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datadreamer-dev/DataDreamer"}, {"content_hash": "f9eb22f1969b033aff20e7f1a86586221a9a8879f50cf80a9739b7b6efc1a102", "fetched_at": "2026-08-29T12:45:59.739980+00:00", "kind": "homepage", "missing": false, "url": "https://datadreamer.dev"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:45:59.749071+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/installation.html"}, {"content_hash": "a5da9539f76f4ad8ef5d11b71bb6a0fea2b4706ccb6302c0904b08394bfa8584", "fetched_at": "2026-08-29T12:45:59.750801+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/index.html"}, {"content_hash": "35a2f166823aa7f5e40c3851f8ed37952c16b0f88a11aaa11d6e639505273297", "fetched_at": "2026-08-29T12:45:59.752934+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/motivation_and_design.html"}, {"content_hash": "aa515dd9acfdb29fd32a28143808b01c8b8f02ef3b38d0837983ff76c5148836", "fetched_at": "2026-08-29T12:45:59.755490+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/abstract_to_tweet.html"}, {"content_hash": "528c62dec0b1eefe24e2208cb60706ba1b32b7b4e984b8fbecf8b9a1a0013a9e", "fetched_at": "2026-08-29T12:45:59.757556+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/attributed_prompts.html"}, {"content_hash": "f455d2b07ca03e1cada466569f5bc29d9d10a298c84c7c983ccd87573b9138bb", "fetched_at": "2026-08-29T12:45:59.759216+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/openai_distillation.html"}, {"content_hash": "f95b33c9b937097598fb9c4619e4081453a17778bb8a42ed7849f5b2fd90fcff", "fetched_at": "2026-08-29T12:45:59.760744+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_augmentation.html"}, {"content_hash": "fc5a838745a8070e611c25300c2253f031dfe3189cd5f6f5e89657b9fbc2d797", "fetched_at": "2026-08-29T12:45:59.762278+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_cleaning.html"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T06:41:53.201547+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "248c7326918f65141b95ce05755a079aa6a3b945041b04fc5eec00e8f3461511", "fetched_at": "2026-08-28T04:03:39.069712+00:00", "kind": "readme", "missing": false, "url": "https://github.com/datadreamer-dev/DataDreamer"}, {"content_hash": "f9eb22f1969b033aff20e7f1a86586221a9a8879f50cf80a9739b7b6efc1a102", "fetched_at": "2026-08-29T12:45:59.739980+00:00", "kind": "homepage", "missing": false, "url": "https://datadreamer.dev"}, {"content_hash": "44136fa355b3678a1146ad16f7e8649e94fb4fc21fe77e8310c060f61caaff8a", "fetched_at": "2026-08-29T12:45:59.749071+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/installation.html"}, {"content_hash": "a5da9539f76f4ad8ef5d11b71bb6a0fea2b4706ccb6302c0904b08394bfa8584", "fetched_at": "2026-08-29T12:45:59.750801+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/index.html"}, {"content_hash": "35a2f166823aa7f5e40c3851f8ed37952c16b0f88a11aaa11d6e639505273297", "fetched_at": "2026-08-29T12:45:59.752934+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/motivation_and_design.html"}, {"content_hash": "aa515dd9acfdb29fd32a28143808b01c8b8f02ef3b38d0837983ff76c5148836", "fetched_at": "2026-08-29T12:45:59.755490+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/abstract_to_tweet.html"}, {"content_hash": "528c62dec0b1eefe24e2208cb60706ba1b32b7b4e984b8fbecf8b9a1a0013a9e", "fetched_at": "2026-08-29T12:45:59.757556+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/attributed_prompts.html"}, {"content_hash": "f455d2b07ca03e1cada466569f5bc29d9d10a298c84c7c983ccd87573b9138bb", "fetched_at": "2026-08-29T12:45:59.759216+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/openai_distillation.html"}, {"content_hash": "f95b33c9b937097598fb9c4619e4081453a17778bb8a42ed7849f5b2fd90fcff", "fetched_at": "2026-08-29T12:45:59.760744+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_augmentation.html"}, {"content_hash": "fc5a838745a8070e611c25300c2253f031dfe3189cd5f6f5e89657b9fbc2d797", "fetched_at": "2026-08-29T12:45:59.762278+00:00", "kind": "site_page", "missing": false, "url": "https://datadreamer.dev/docs/latest/pages/get_started/quick_tour/dataset_cleaning.html"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 4, "longevity": 84, "rhythm": 40}, "computed_at": "2026-09-03T02:20:16.233290+00:00", "flags": [], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 1188, "days_push": 577, "days_rel": 577, "gap_med": 0, "n_releases_24m": 8}, "score": 33, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}