{"adoption": {"forks": 95, "observed_at": "2026-08-28T04:05:02.281414+00:00", "stars": 1551}, "canonical_url": "https://ross.abutalabs.com/products/awesome-llm-synthetic-data", "card": {"archived": false, "artifact_type": "learning-resource", "description": "A reading list on LLM based Synthetic Data Generation 🔥", "domain": ["large-language-models", "machine-learning", "artificial-intelligence", "data-science", "awesome-lists"], "enriched": true, "function": ["data-generation", "llm-training", "rag", "prompt-engineering"], "health_score": 35, "homepage": null, "language": null, "license": "MIT", "license_family": "permissive", "maturity": "active", "member_repos": ["wasiahmad/Awesome-LLM-Synthetic-Data"], "name": "wasiahmad/Awesome-LLM-Synthetic-Data", "platform": [], "pushed_at": "2025-06-05T19:16:26+00:00", "repo": "wasiahmad/Awesome-LLM-Synthetic-Data", "stars": 1551, "tags": ["awesome-list", "synthetic-data", "reading-list", "papers", "curated-resources", "web-server"], "topics": [], "urls": [], "use_cases": ["find papers on LLM synthetic data generation", "learn how to generate training data with LLMs", "research instruction tuning data generation methods", "find tools for generating synthetic datasets", "survey synthetic data for code generation or math reasoning", "find datasets generated by LLMs for model training"], "what_it_is": "A curated awesome-list of papers, tools, and blogs about synthetic data generation with large language models. It organizes resources by surveys, techniques, application areas (math reasoning, code generation, alignment, etc.), datasets, and tools.", "when_to_avoid": ["you need runnable software rather than a reading list", "you want non-LLM synthetic data methods (GANs, simulation)", "you need a maintained library with APIs"], "when_to_choose": ["you need a curated starting point for LLM synthetic data research", "you want recent papers and tools on data generation with LLMs", "you are surveying application areas like text-to-SQL or alignment data synthesis"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/awesome-llm-synthetic-data", "repo": "wasiahmad/Awesome-LLM-Synthetic-Data", "role": "main", "score": 34}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.281414+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:30:17.953503+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b782173bf128f851b2f6d206dbce7e6314f47dac25f964bba81551104d8dd6ea", "fetched_at": "2026-08-28T04:05:02.281414+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wasiahmad/Awesome-LLM-Synthetic-Data"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.281414+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:30:17.953503+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b782173bf128f851b2f6d206dbce7e6314f47dac25f964bba81551104d8dd6ea", "fetched_at": "2026-08-28T04:05:02.281414+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wasiahmad/Awesome-LLM-Synthetic-Data"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:30:17.953503+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b782173bf128f851b2f6d206dbce7e6314f47dac25f964bba81551104d8dd6ea", "fetched_at": "2026-08-28T04:05:02.281414+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wasiahmad/Awesome-LLM-Synthetic-Data"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.281414+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.281414+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.281414+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:30:17.953503+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b782173bf128f851b2f6d206dbce7e6314f47dac25f964bba81551104d8dd6ea", "fetched_at": "2026-08-28T04:05:02.281414+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wasiahmad/Awesome-LLM-Synthetic-Data"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.281414+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.281414+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:30:17.953503+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b782173bf128f851b2f6d206dbce7e6314f47dac25f964bba81551104d8dd6ea", "fetched_at": "2026-08-28T04:05:02.281414+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wasiahmad/Awesome-LLM-Synthetic-Data"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.281414+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.281414+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.281414+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:30:17.953503+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b782173bf128f851b2f6d206dbce7e6314f47dac25f964bba81551104d8dd6ea", "fetched_at": "2026-08-28T04:05:02.281414+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wasiahmad/Awesome-LLM-Synthetic-Data"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.281414+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:05:02.281414+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:30:17.953503+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b782173bf128f851b2f6d206dbce7e6314f47dac25f964bba81551104d8dd6ea", "fetched_at": "2026-08-28T04:05:02.281414+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wasiahmad/Awesome-LLM-Synthetic-Data"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:30:17.953503+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b782173bf128f851b2f6d206dbce7e6314f47dac25f964bba81551104d8dd6ea", "fetched_at": "2026-08-28T04:05:02.281414+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wasiahmad/Awesome-LLM-Synthetic-Data"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:30:17.953503+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b782173bf128f851b2f6d206dbce7e6314f47dac25f964bba81551104d8dd6ea", "fetched_at": "2026-08-28T04:05:02.281414+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wasiahmad/Awesome-LLM-Synthetic-Data"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:30:17.953503+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "b782173bf128f851b2f6d206dbce7e6314f47dac25f964bba81551104d8dd6ea", "fetched_at": "2026-08-28T04:05:02.281414+00:00", "kind": "readme", "missing": false, "url": "https://github.com/wasiahmad/Awesome-LLM-Synthetic-Data"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 25, "longevity": 53, "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": 755, "days_push": 454, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 34, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}