{"adoption": {"forks": 38, "observed_at": "2026-08-28T04:04:43.512568+00:00", "stars": 1435}, "canonical_url": "https://ross.abutalabs.com/products/frequencylaw", "card": {"archived": false, "artifact_type": "library", "description": "Official repository for textual frequency law", "domain": ["large-language-models", "machine-learning"], "enriched": true, "function": ["machine-learning", "llm-training", "nlp", "data-generation", "benchmarking"], "health_score": 66, "homepage": null, "language": "Python", "license": null, "license_family": "other", "maturity": "active", "member_repos": ["HongyuanLuke/frequencylaw"], "name": "HongyuanLuke/frequencylaw", "platform": ["python"], "pushed_at": "2026-04-14T12:24:58+00:00", "repo": "HongyuanLuke/frequencylaw", "stars": 1435, "tags": ["llm-research", "fine-tuning", "lora", "mathematical-reasoning", "machine-translation", "academic-paper", "dataset-construction", "gsm8k", "flores-200", "natural-language-processing", "research"], "topics": [], "urls": [], "use_cases": ["reproduce textual frequency law experiments on LLMs", "build high/low frequency paired datasets for math reasoning", "fine-tune LLMs with curriculum frequency-based training", "evaluate LLM performance on GSM8K and FLORES-200", "calculate textual frequency statistics for training data", "study how token frequency impacts LLM reasoning and translation"], "what_it_is": "Official code repository for the paper 'Textual Frequency Law on Large Language Models', implementing TFL, TFD, and CTFT methods for studying how textual frequency affects LLM performance. It provides end-to-end scripts for frequency calculation, paired dataset construction, LoRA fine-tuning, and evaluation on GSM8K math reasoning and FLORES-200 translation tasks.", "when_to_avoid": ["you need a production-ready LLM training framework", "you want a general-purpose fine-tuning tool unrelated to frequency research", "you need a maintained library with a license and long-term support"], "when_to_choose": ["you want to reproduce or extend the paper's frequency-based LLM training methods", "you need frequency-sorted or paired datasets for reasoning/translation experiments", "you're researching how textual frequency affects model optimization"]}, "data_as_of": "2026-08-30T08:39:29.467469+00:00", "members": [{"path": "/products/frequencylaw", "repo": "HongyuanLuke/frequencylaw", "role": "main", "score": 49}], "provenance": {"archived": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.512568+00:00", "source": "github"}, "artifact_type": {"confidence": null, "enriched_at": "2026-08-30T04:36:50.088410+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "630ad9afa89836eee5d50a815721207dfdd5e23daf6338dbe6bca5521a8bd2b5", "fetched_at": "2026-08-28T04:04:43.512568+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HongyuanLuke/frequencylaw"}], "taxonomy_version": 1}, "description": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.512568+00:00", "source": "github"}, "domain": {"confidence": null, "enriched_at": "2026-08-30T04:36:50.088410+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "630ad9afa89836eee5d50a815721207dfdd5e23daf6338dbe6bca5521a8bd2b5", "fetched_at": "2026-08-28T04:04:43.512568+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HongyuanLuke/frequencylaw"}], "taxonomy_version": 1}, "enriched": {"inputs": [], "kind": "computed", "method": "enrichment_status"}, "function": {"confidence": null, "enriched_at": "2026-08-30T04:36:50.088410+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "630ad9afa89836eee5d50a815721207dfdd5e23daf6338dbe6bca5521a8bd2b5", "fetched_at": "2026-08-28T04:04:43.512568+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HongyuanLuke/frequencylaw"}], "taxonomy_version": 1}, "health_score": {"inputs": ["days_since_push", "days_since_release", "archived"], "kind": "computed", "method": "health_v1"}, "homepage": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.512568+00:00", "source": "github"}, "language": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.512568+00:00", "source": "github"}, "license": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.512568+00:00", "source": "github"}, "license_family": {"inputs": ["license"], "kind": "computed", "method": "license_family"}, "maturity": {"confidence": null, "enriched_at": "2026-08-30T04:36:50.088410+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "630ad9afa89836eee5d50a815721207dfdd5e23daf6338dbe6bca5521a8bd2b5", "fetched_at": "2026-08-28T04:04:43.512568+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HongyuanLuke/frequencylaw"}], "taxonomy_version": 1}, "member_repos": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.512568+00:00", "source": "github"}, "name": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.512568+00:00", "source": "github"}, "platform": {"confidence": null, "enriched_at": "2026-08-30T04:36:50.088410+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "630ad9afa89836eee5d50a815721207dfdd5e23daf6338dbe6bca5521a8bd2b5", "fetched_at": "2026-08-28T04:04:43.512568+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HongyuanLuke/frequencylaw"}], "taxonomy_version": 1}, "pushed_at": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.512568+00:00", "source": "github"}, "repo": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.512568+00:00", "source": "github"}, "stars": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.512568+00:00", "source": "github"}, "tags": {"confidence": null, "enriched_at": "2026-08-30T04:36:50.088410+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "630ad9afa89836eee5d50a815721207dfdd5e23daf6338dbe6bca5521a8bd2b5", "fetched_at": "2026-08-28T04:04:43.512568+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HongyuanLuke/frequencylaw"}], "taxonomy_version": 1}, "topics": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.512568+00:00", "source": "github"}, "urls": {"kind": "observed", "observed_at": "2026-08-28T04:04:43.512568+00:00", "source": "github"}, "use_cases": {"confidence": null, "enriched_at": "2026-08-30T04:36:50.088410+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "630ad9afa89836eee5d50a815721207dfdd5e23daf6338dbe6bca5521a8bd2b5", "fetched_at": "2026-08-28T04:04:43.512568+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HongyuanLuke/frequencylaw"}], "taxonomy_version": 1}, "what_it_is": {"confidence": null, "enriched_at": "2026-08-30T04:36:50.088410+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "630ad9afa89836eee5d50a815721207dfdd5e23daf6338dbe6bca5521a8bd2b5", "fetched_at": "2026-08-28T04:04:43.512568+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HongyuanLuke/frequencylaw"}], "taxonomy_version": 1}, "when_to_avoid": {"confidence": null, "enriched_at": "2026-08-30T04:36:50.088410+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "630ad9afa89836eee5d50a815721207dfdd5e23daf6338dbe6bca5521a8bd2b5", "fetched_at": "2026-08-28T04:04:43.512568+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HongyuanLuke/frequencylaw"}], "taxonomy_version": 1}, "when_to_choose": {"confidence": null, "enriched_at": "2026-08-30T04:36:50.088410+00:00", "kind": "inferred", "prompt_version": 1, "sources": [{"content_hash": "630ad9afa89836eee5d50a815721207dfdd5e23daf6338dbe6bca5521a8bd2b5", "fetched_at": "2026-08-28T04:04:43.512568+00:00", "kind": "readme", "missing": false, "url": "https://github.com/HongyuanLuke/frequencylaw"}], "taxonomy_version": 1}}, "score": {"components": {"activity": 77, "longevity": 11, "rhythm": 35}, "computed_at": "2026-09-02T17:46:02.011165+00:00", "flags": ["no_releases", "young", "no_license"], "formula": "round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)", "inputs": {"age_days": 160, "days_push": 141, "days_rel": null, "gap_med": null, "n_releases_24m": 0}, "score": 49, "version": 2}, "staleness": {"enrichment_outdated": false, "low_confidence": false, "scrape_days": 9, "stale_scrape": false}}