{"dataset":{"slug":"alea-institute-kl3m-data-edgar","id":"alea-institute/kl3m-data-edgar","org":"alea-institute","name":"kl3m-data-edgar","description":"A copyright-clean text collection released by the ALEA Institute as part of the KL3M Data Project, intended for training language models; full documentation is available via the linked paper and GitHub repository.","category":"public-records","category_title":"Public Records & Filings","source":"huggingface","sources":["huggingface"],"url":"https://huggingface.co/datasets/alea-institute/kl3m-data-edgar","dataset_url":"https://huggingface.co/datasets/alea-institute/kl3m-data-edgar","catalogue_url":"https://altdata.wiki/wiki/datasets/alea-institute-kl3m-data-edgar","listings":[{"org":"alea-institute","provider_slug":null,"source":"huggingface","url":"https://huggingface.co/datasets/alea-institute/kl3m-data-edgar","pricing":null,"license":"cc-by-4.0","has_source_logo":true}],"providers":[{"name":"alea-institute","slug":null,"url":"https://huggingface.co/datasets/alea-institute/kl3m-data-edgar"}],"license":"cc-by-4.0","size":null,"tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2026-10-17","tags":["license:cc-by-4.0","size_categories:1K<n<10K","format:parquet","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant","arxiv:2504.07854","arxiv:2503.17247"],"preview_supported":true,"seo_indexable":true,"seo_quality_ok":true,"seo_canonical_slug":"alea-institute-kl3m-data-edgar","category_inferred":false,"provider_slug":null,"org_url":"https://huggingface.co/alea-institute","has_source_logo":true,"hay":"alea-institute kl3m-data-edgar a copyright-clean text collection released by the alea institute as part of the kl3m data project, intended for training language models; full documentation is available via the linked paper and github repository. license:cc-by-4.0 size_categories:1k<n<10k format:parquet modality:text library:datasets library:pandas library:polars library:mlcroissant arxiv:2504.07854 arxiv:2503.17247 public records & filings cc-by-4.0 download huggingface  "},"related":[{"slug":"abdurrahmanhakanacar-nasdaq-financials-and-fundamentals-2024-2026","id":"abdurrahmanhakanacar/nasdaq-financials-and-fundamentals-2024-2026","org":"abdurrahmanhakanacar","name":"nasdaq-financials-and-fundamentals-2024-2026","description":"SEC EDGAR 10-K & 10-Q financial statements for 2,600+ NASDAQ companies.","category":"public-records","category_title":"Public Records & Filings","source":"kaggle","sources":["kaggle"],"url":"https://www.kaggle.com/datasets/abdurrahmanhakanacar/nasdaq-financials-and-fundamentals-2024-2026","dataset_url":"https://www.kaggle.com/datasets/abdurrahmanhakanacar/nasdaq-financials-and-fundamentals-2024-2026","catalogue_url":"https://altdata.wiki/wiki/datasets/abdurrahmanhakanacar-nasdaq-financials-and-fundamentals-2024-2026","listings":[{"org":"abdurrahmanhakanacar","provider_slug":null,"source":"kaggle","url":"https://www.kaggle.com/datasets/abdurrahmanhakanacar/nasdaq-financials-and-fundamentals-2024-2026","pricing":null,"license":"Attribution 4.0 International (CC BY 4.0)","has_source_logo":true}],"providers":[{"name":"abdurrahmanhakanacar","slug":null,"url":"https://www.kaggle.com/datasets/abdurrahmanhakanacar/nasdaq-financials-and-fundamentals-2024-2026"}],"license":"Attribution 4.0 International (CC BY 4.0)","size":"1649941","tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2026-09-13","tags":["business","finance","economics","tabular","investing"],"preview_supported":true,"seo_indexable":true,"seo_quality_ok":false,"seo_canonical_slug":"abdurrahmanhakanacar-nasdaq-financials-and-fundamentals-2024-2026","category_inferred":false,"provider_slug":null,"org_url":"https://www.kaggle.com/abdurrahmanhakanacar","has_source_logo":true,"hay":"abdurrahmanhakanacar nasdaq-financials-and-fundamentals-2024-2026 sec edgar 10-k & 10-q financial statements for 2,600+ nasdaq companies. business finance economics tabular investing public records & filings attribution 4.0 international (cc by 4.0) download kaggle  "},{"slug":"ahmedshahriarsakib-usa-real-estate-dataset","id":"ahmedshahriarsakib/usa-real-estate-dataset","org":"ahmedshahriarsakib","name":"usa-real-estate-dataset","description":"Real Estate listings (2.2M+) in the US broken by State and zip code","category":"public-records","category_title":"Public Records & Filings","source":"kaggle","sources":["kaggle"],"url":"https://www.kaggle.com/datasets/ahmedshahriarsakib/usa-real-estate-dataset","dataset_url":"https://www.kaggle.com/datasets/ahmedshahriarsakib/usa-real-estate-dataset","catalogue_url":"https://altdata.wiki/wiki/datasets/ahmedshahriarsakib-usa-real-estate-dataset","listings":[{"org":"ahmedshahriarsakib","provider_slug":null,"source":"kaggle","url":"https://www.kaggle.com/datasets/ahmedshahriarsakib/usa-real-estate-dataset","pricing":null,"license":"Other (specified in description)","has_source_logo":true}],"providers":[{"name":"ahmedshahriarsakib","slug":null,"url":"https://www.kaggle.com/datasets/ahmedshahriarsakib/usa-real-estate-dataset"}],"license":"Other (specified in description)","size":"40085115","tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2024-03-30","tags":["united states","housing","real estate","computer science","tabular","regression"],"preview_supported":true,"seo_indexable":true,"seo_quality_ok":false,"seo_canonical_slug":"ahmedshahriarsakib-usa-real-estate-dataset","category_inferred":false,"provider_slug":null,"org_url":"https://www.kaggle.com/ahmedshahriarsakib","has_source_logo":true,"hay":"ahmedshahriarsakib usa-real-estate-dataset real estate listings (2.2m+) in the us broken by state and zip code united states housing real estate computer science tabular regression public records & filings other (specified in description) download kaggle  "},{"slug":"ai-growth-lab-patents-claims-1-5m-traim-test","id":"AI-Growth-Lab/patents_claims_1.5m_traim_test","org":"AI-Growth-Lab","name":"patents_claims_1.5m_traim_test","description":"About 1.5 million US patent claims split into training and test partitions in CSV, organized for claim-level classification and summarization work (Apache 2.0). A large, ready-split corpus for IP-claims modeling.","category":"public-records","category_title":"Public Records & Filings","source":"huggingface","sources":["huggingface"],"url":"https://huggingface.co/datasets/AI-Growth-Lab/patents_claims_1.5m_traim_test","dataset_url":"https://huggingface.co/datasets/AI-Growth-Lab/patents_claims_1.5m_traim_test","catalogue_url":"https://altdata.wiki/wiki/datasets/ai-growth-lab-patents-claims-1-5m-traim-test","listings":[{"org":"AI-Growth-Lab","provider_slug":null,"source":"huggingface","url":"https://huggingface.co/datasets/AI-Growth-Lab/patents_claims_1.5m_traim_test","pricing":null,"license":"unknown","has_source_logo":true}],"providers":[{"name":"AI-Growth-Lab","slug":null,"url":"https://huggingface.co/datasets/AI-Growth-Lab/patents_claims_1.5m_traim_test"}],"license":"unknown","size":null,"tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2022-07-31","tags":["size_categories:1M<n<10M","format:csv","modality:tabular","modality:text","library:datasets","library:pandas","library:mlcroissant","library:polars"],"preview_supported":true,"seo_indexable":true,"seo_quality_ok":true,"seo_canonical_slug":"ai-growth-lab-patents-claims-1-5m-traim-test","category_inferred":false,"provider_slug":null,"org_url":"https://huggingface.co/AI-Growth-Lab","has_source_logo":true,"hay":"ai-growth-lab patents_claims_1.5m_traim_test about 1.5 million us patent claims split into training and test partitions in csv, organized for claim-level classification and summarization work (apache 2.0). a large, ready-split corpus for ip-claims modeling. size_categories:1m<n<10m format:csv modality:tabular modality:text library:datasets library:pandas library:mlcroissant library:polars public records & filings unknown download huggingface  "},{"slug":"alea-institute-alea-patent-claim-graph","id":"alea-institute/alea-patent-claim-graph","org":"alea-institute","name":"alea-patent-claim-graph","description":"ALEA Patent Claim Graph Reading questions about the dependency structure of real U.S. patent claim sets: which claim a dependent claim refers back to, the chain of claims it rests on, its independent claim, which and how many claims depend on a given claim, and yes / no questions about dependency. Every answer is computed deterministically from the claim text shown in the row. This dataset is part","category":"public-records","category_title":"Public Records & Filings","source":"huggingface","sources":["huggingface"],"url":"https://huggingface.co/datasets/alea-institute/alea-patent-claim-graph","dataset_url":"https://huggingface.co/datasets/alea-institute/alea-patent-claim-graph","catalogue_url":"https://altdata.wiki/wiki/datasets/alea-institute-alea-patent-claim-graph","listings":[{"org":"alea-institute","provider_slug":null,"source":"huggingface","url":"https://huggingface.co/datasets/alea-institute/alea-patent-claim-graph","pricing":null,"license":"cc-by-4.0","has_source_logo":true}],"providers":[{"name":"alea-institute","slug":null,"url":"https://huggingface.co/datasets/alea-institute/alea-patent-claim-graph"}],"license":"cc-by-4.0","size":"10K<n<100K","tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2026-10-28","tags":["patents","legal","claims","reasoning","multi-hop","task_categories:question-answering","task_categories:text-generation","language:en","license:cc-by-4.0","size_categories:10K<n<100K"],"preview_supported":true,"seo_indexable":true,"seo_quality_ok":true,"seo_canonical_slug":"alea-institute-alea-patent-claim-graph","category_inferred":false,"provider_slug":null,"org_url":"https://huggingface.co/alea-institute","has_source_logo":true,"hay":"alea-institute alea-patent-claim-graph alea patent claim graph reading questions about the dependency structure of real u.s. patent claim sets: which claim a dependent claim refers back to, the chain of claims it rests on, its independent claim, which and how many claims depend on a given claim, and yes / no questions about dependency. every answer is computed deterministically from the claim text shown in the row. this dataset is part patents legal claims reasoning multi-hop task_categories:question-answering task_categories:text-generation language:en license:cc-by-4.0 size_categories:10k<n<100k public records & filings cc-by-4.0 download huggingface  "},{"slug":"alea-institute-kl3m-data-edgar-10-k","id":"alea-institute/kl3m-data-edgar-10-k","org":"alea-institute","name":"kl3m-data-edgar-10-k","description":"A component of the ALEA Institute's KL3M Data Project supplying training material cleared of copyright concerns. The dataset card is currently a placeholder, directing readers to the GitHub repo and project paper for full documentation.","category":"public-records","category_title":"Public Records & Filings","source":"huggingface","sources":["huggingface"],"url":"https://huggingface.co/datasets/alea-institute/kl3m-data-edgar-10-k","dataset_url":"https://huggingface.co/datasets/alea-institute/kl3m-data-edgar-10-k","catalogue_url":"https://altdata.wiki/wiki/datasets/alea-institute-kl3m-data-edgar-10-k","listings":[{"org":"alea-institute","provider_slug":null,"source":"huggingface","url":"https://huggingface.co/datasets/alea-institute/kl3m-data-edgar-10-k","pricing":null,"license":"cc-by-4.0","has_source_logo":true}],"providers":[{"name":"alea-institute","slug":null,"url":"https://huggingface.co/datasets/alea-institute/kl3m-data-edgar-10-k"}],"license":"cc-by-4.0","size":null,"tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2026-10-19","tags":["license:cc-by-4.0","size_categories:1M<n<10M","format:parquet","modality:tabular","modality:text","library:datasets","library:dask","library:polars","library:mlcroissant","arxiv:2504.07854"],"preview_supported":true,"seo_indexable":true,"seo_quality_ok":true,"seo_canonical_slug":"alea-institute-kl3m-data-edgar-10-k","category_inferred":false,"provider_slug":null,"org_url":"https://huggingface.co/alea-institute","has_source_logo":true,"hay":"alea-institute kl3m-data-edgar-10-k a component of the alea institute's kl3m data project supplying training material cleared of copyright concerns. the dataset card is currently a placeholder, directing readers to the github repo and project paper for full documentation. license:cc-by-4.0 size_categories:1m<n<10m format:parquet modality:tabular modality:text library:datasets library:dask library:polars library:mlcroissant arxiv:2504.07854 public records & filings cc-by-4.0 download huggingface  "},{"slug":"alea-institute-kl3m-data-edgar-10-q","id":"alea-institute/kl3m-data-edgar-10-q","org":"alea-institute","name":"kl3m-data-edgar-10-q","description":"The KL3M Data Project from the ALEA Institute supplies copyright-clean training material, and the dataset listed here is one component pending further documentation on its dedicated page.","category":"public-records","category_title":"Public Records & Filings","source":"huggingface","sources":["huggingface"],"url":"https://huggingface.co/datasets/alea-institute/kl3m-data-edgar-10-q","dataset_url":"https://huggingface.co/datasets/alea-institute/kl3m-data-edgar-10-q","catalogue_url":"https://altdata.wiki/wiki/datasets/alea-institute-kl3m-data-edgar-10-q","listings":[{"org":"alea-institute","provider_slug":null,"source":"huggingface","url":"https://huggingface.co/datasets/alea-institute/kl3m-data-edgar-10-q","pricing":null,"license":"cc-by-4.0","has_source_logo":true}],"providers":[{"name":"alea-institute","slug":null,"url":"https://huggingface.co/datasets/alea-institute/kl3m-data-edgar-10-q"}],"license":"cc-by-4.0","size":null,"tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2026-10-19","tags":["license:cc-by-4.0","size_categories:1M<n<10M","format:parquet","modality:tabular","modality:text","library:datasets","library:dask","library:polars","library:mlcroissant","arxiv:2504.07854"],"preview_supported":true,"seo_indexable":true,"seo_quality_ok":true,"seo_canonical_slug":"alea-institute-kl3m-data-edgar-10-q","category_inferred":false,"provider_slug":null,"org_url":"https://huggingface.co/alea-institute","has_source_logo":true,"hay":"alea-institute kl3m-data-edgar-10-q the kl3m data project from the alea institute supplies copyright-clean training material, and the dataset listed here is one component pending further documentation on its dedicated page. license:cc-by-4.0 size_categories:1m<n<10m format:parquet modality:tabular modality:text library:datasets library:dask library:polars library:mlcroissant arxiv:2504.07854 public records & filings cc-by-4.0 download huggingface  "}]}