{"dataset":{"slug":"penumbraai-sec-edgar-filing-risks","id":"PenumbraAI/sec-edgar-filing-risks","org":"PenumbraAI","name":"sec-edgar-filing-risks","description":"Penumbra AI SEC 10-K Risk Factor Disclosures (S&P 500, FY2025-2026) Dataset Summary This dataset contains a sample of 2,683 individual risk factor disclosures from the most recent Form 10-K filing of 50 S&P 500 companies (fiscal year ends ranging from May 2025 to February 2026). Each record is a single risk driver — one discrete point a company disclosed under \"Risk Factors\" — together with the ve","category":"public-records","category_title":"Public Records & Filings","source":"huggingface","sources":["huggingface"],"url":"https://huggingface.co/datasets/PenumbraAI/sec-edgar-filing-risks","listings":[{"org":"PenumbraAI","provider_slug":null,"source":"huggingface","url":"https://huggingface.co/datasets/PenumbraAI/sec-edgar-filing-risks","pricing":null,"license":"cc-by-4.0","has_source_logo":true}],"providers":[{"name":"PenumbraAI","slug":null,"url":"https://huggingface.co/datasets/PenumbraAI/sec-edgar-filing-risks"}],"license":"cc-by-4.0","size":"1K<n<10K","tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2026-09-03","tags":["finance","sec-edgar","10-k","risk-factors","financial-nlp","task_categories:text-classification","language:en","license:cc-by-4.0","size_categories:1K<n<10K","format:json"],"preview_supported":true,"seo_indexable":true,"seo_canonical_slug":"penumbraai-sec-edgar-filing-risks","category_inferred":false,"provider_slug":null,"org_url":"https://huggingface.co/PenumbraAI","has_source_logo":true,"hay":"penumbraai sec-edgar-filing-risks penumbra ai sec 10-k risk factor disclosures (s&p 500, fy2025-2026) dataset summary this dataset contains a sample of 2,683 individual risk factor disclosures from the most recent form 10-k filing of 50 s&p 500 companies (fiscal year ends ranging from may 2025 to february 2026). each record is a single risk driver — one discrete point a company disclosed under \"risk factors\" — together with the ve finance sec-edgar 10-k risk-factors financial-nlp task_categories:text-classification language:en license:cc-by-4.0 size_categories:1k<n<10k format:json public records & filings cc-by-4.0 download huggingface  "},"related":[{"slug":"2001jdev-clinical-trials-eligibility-graphs-rerank","id":"2001jdev/clinical-trials-eligibility-graphs-rerank","org":"2001jdev","name":"clinical-trials-eligibility-graphs-rerank","description":"Parsed eligibility criteria from 13,229 ClinicalTrials.gov studies representing the candidate pool gathered by two first-stage retrievers during TREC Clinical Trials 2021–2023, formatted as typed entity-relation graphs for reranking models.","category":"public-records","category_title":"Public Records & Filings","source":"huggingface","sources":["huggingface"],"url":"https://huggingface.co/datasets/2001jdev/clinical-trials-eligibility-graphs-rerank","listings":[{"org":"2001jdev","provider_slug":null,"source":"huggingface","url":"https://huggingface.co/datasets/2001jdev/clinical-trials-eligibility-graphs-rerank","pricing":null,"license":"cc-by-nc-4.0","has_source_logo":true}],"providers":[{"name":"2001jdev","slug":null,"url":"https://huggingface.co/datasets/2001jdev/clinical-trials-eligibility-graphs-rerank"}],"license":"cc-by-nc-4.0","size":"10K<n<100K","tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2026-08-27","tags":["clinical-trials","information-extraction","knowledge-graph","biomedical","language:en","license:cc-by-nc-4.0","size_categories:10K<n<100K","format:parquet","modality:tabular","modality:text"],"preview_supported":true,"seo_indexable":true,"seo_canonical_slug":"2001jdev-clinical-trials-eligibility-graphs-rerank","category_inferred":false,"provider_slug":null,"org_url":"https://huggingface.co/2001jdev","has_source_logo":true,"hay":"2001jdev clinical-trials-eligibility-graphs-rerank parsed eligibility criteria from 13,229 clinicaltrials.gov studies representing the candidate pool gathered by two first-stage retrievers during trec clinical trials 2021–2023, formatted as typed entity-relation graphs for reranking models. clinical-trials information-extraction knowledge-graph biomedical language:en license:cc-by-nc-4.0 size_categories:10k<n<100k format:parquet modality:tabular modality:text public records & filings cc-by-nc-4.0 download huggingface  "},{"slug":"2001jdev-clinical-trials-eligibility-graphs-subset-gpt4-5mini","id":"2001jdev/clinical-trials-eligibility-graphs_subset_gpt4.5mini","org":"2001jdev","name":"clinical-trials-eligibility-graphs_subset_gpt4.5mini","description":"This dataset is a small parquet-format subset of clinical-trial eligibility criteria represented as entity and relation graphs. It is published on a community data hub under an unspecified license.","category":"public-records","category_title":"Public Records & Filings","source":"huggingface","sources":["huggingface"],"url":"https://huggingface.co/datasets/2001jdev/clinical-trials-eligibility-graphs_subset_gpt4.5mini","listings":[{"org":"2001jdev","provider_slug":null,"source":"huggingface","url":"https://huggingface.co/datasets/2001jdev/clinical-trials-eligibility-graphs_subset_gpt4.5mini","pricing":null,"license":"unknown","has_source_logo":true}],"providers":[{"name":"2001jdev","slug":null,"url":"https://huggingface.co/datasets/2001jdev/clinical-trials-eligibility-graphs_subset_gpt4.5mini"}],"license":"unknown","size":null,"tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2026-05-08","tags":["size_categories:n<1K","format:parquet","format:optimized-parquet","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant"],"preview_supported":true,"seo_indexable":true,"seo_canonical_slug":"2001jdev-clinical-trials-eligibility-graphs-subset-gpt4-5mini","category_inferred":false,"provider_slug":null,"org_url":"https://huggingface.co/2001jdev","has_source_logo":true,"hay":"2001jdev clinical-trials-eligibility-graphs_subset_gpt4.5mini this dataset is a small parquet-format subset of clinical-trial eligibility criteria represented as entity and relation graphs. it is published on a community data hub under an unspecified license. size_categories:n<1k format:parquet format:optimized-parquet modality:text library:datasets library:pandas library:polars library:mlcroissant public records & filings unknown download huggingface  "},{"slug":"2001jdev-clinical-trials-eligibility-graphs-v2","id":"2001jdev/clinical-trials-eligibility-graphs_v2","org":"2001jdev","name":"clinical-trials-eligibility-graphs_v2","description":"This dataset, published by 2001jdev on Hugging Face, packages eligibility-criteria information from clinical trials into structured entity and relation records. It is distributed in Parquet format and contains a single split of roughly 104,000 rows.","category":"public-records","category_title":"Public Records & Filings","source":"huggingface","sources":["huggingface"],"url":"https://huggingface.co/datasets/2001jdev/clinical-trials-eligibility-graphs_v2","listings":[{"org":"2001jdev","provider_slug":null,"source":"huggingface","url":"https://huggingface.co/datasets/2001jdev/clinical-trials-eligibility-graphs_v2","pricing":null,"license":"unknown","has_source_logo":true}],"providers":[{"name":"2001jdev","slug":null,"url":"https://huggingface.co/datasets/2001jdev/clinical-trials-eligibility-graphs_v2"}],"license":"unknown","size":null,"tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2026-04-23","tags":["size_categories:100K<n<1M","format:parquet","format:optimized-parquet","modality:text","library:datasets","library:dask","library:polars","library:mlcroissant"],"preview_supported":true,"seo_indexable":true,"seo_canonical_slug":"2001jdev-clinical-trials-eligibility-graphs-v2","category_inferred":false,"provider_slug":null,"org_url":"https://huggingface.co/2001jdev","has_source_logo":true,"hay":"2001jdev clinical-trials-eligibility-graphs_v2 this dataset, published by 2001jdev on hugging face, packages eligibility-criteria information from clinical trials into structured entity and relation records. it is distributed in parquet format and contains a single split of roughly 104,000 rows. size_categories:100k<n<1m format:parquet format:optimized-parquet modality:text library:datasets library:dask library:polars library:mlcroissant public records & filings unknown download huggingface  "},{"slug":"2001jdev-clinical-trials-synth-patient-profiles2","id":"2001jdev/clinical-trials-synth-patient-profiles2","org":"2001jdev","name":"clinical-trials-synth-patient-profiles2","description":"clinical-trials-synth-patient-profiles2 is a synthetic patient-profile dataset distributed by publisher 2001jdev on a public dataset registry. It pairs clinical trial identifiers with short free-text profile descriptions and a coded entity taxonomy, designed for text and entity-recognition work rather than production research.","category":"public-records","category_title":"Public Records & Filings","source":"huggingface","sources":["huggingface"],"url":"https://huggingface.co/datasets/2001jdev/clinical-trials-synth-patient-profiles2","listings":[{"org":"2001jdev","provider_slug":null,"source":"huggingface","url":"https://huggingface.co/datasets/2001jdev/clinical-trials-synth-patient-profiles2","pricing":null,"license":"unknown","has_source_logo":true}],"providers":[{"name":"2001jdev","slug":null,"url":"https://huggingface.co/datasets/2001jdev/clinical-trials-synth-patient-profiles2"}],"license":"unknown","size":null,"tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2026-04-28","tags":["size_categories:1K<n<10K","format:parquet","format:optimized-parquet","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant"],"preview_supported":true,"seo_indexable":true,"seo_canonical_slug":"2001jdev-clinical-trials-synth-patient-profiles2","category_inferred":false,"provider_slug":null,"org_url":"https://huggingface.co/2001jdev","has_source_logo":true,"hay":"2001jdev clinical-trials-synth-patient-profiles2 clinical-trials-synth-patient-profiles2 is a synthetic patient-profile dataset distributed by publisher 2001jdev on a public dataset registry. it pairs clinical trial identifiers with short free-text profile descriptions and a coded entity taxonomy, designed for text and entity-recognition work rather than production research. size_categories:1k<n<10k format:parquet format:optimized-parquet modality:text library:datasets library:pandas library:polars library:mlcroissant public records & filings unknown download huggingface  "},{"slug":"2001jdev-clinical-trials-trec-parsed","id":"2001jdev/clinical-trials-trec-parsed","org":"2001jdev","name":"clinical-trials-trec-parsed","description":"This dataset is a parsed snapshot of ClinicalTrials.gov records, distributed in Parquet format on the Hugging Face Hub under an unspecified license. It contains roughly 52,000 trial entries drawn from public registry filings.","category":"public-records","category_title":"Public Records & Filings","source":"huggingface","sources":["huggingface"],"url":"https://huggingface.co/datasets/2001jdev/clinical-trials-trec-parsed","listings":[{"org":"2001jdev","provider_slug":null,"source":"huggingface","url":"https://huggingface.co/datasets/2001jdev/clinical-trials-trec-parsed","pricing":null,"license":"unknown","has_source_logo":true}],"providers":[{"name":"2001jdev","slug":null,"url":"https://huggingface.co/datasets/2001jdev/clinical-trials-trec-parsed"}],"license":"unknown","size":null,"tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2026-04-25","tags":["size_categories:10K<n<100K","format:parquet","format:optimized-parquet","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant"],"preview_supported":true,"seo_indexable":true,"seo_canonical_slug":"2001jdev-clinical-trials-trec-parsed","category_inferred":false,"provider_slug":null,"org_url":"https://huggingface.co/2001jdev","has_source_logo":true,"hay":"2001jdev clinical-trials-trec-parsed this dataset is a parsed snapshot of clinicaltrials.gov records, distributed in parquet format on the hugging face hub under an unspecified license. it contains roughly 52,000 trial entries drawn from public registry filings. size_categories:10k<n<100k format:parquet format:optimized-parquet modality:text library:datasets library:pandas library:polars library:mlcroissant public records & filings unknown download huggingface  "},{"slug":"2001jdev-clinical-trials-trec-qrels","id":"2001jdev/clinical-trials-trec-qrels","org":"2001jdev","name":"clinical-trials-trec-qrels","description":"clinical-trials-trec-qrels is a tabular relevance-judgment file distributed by the 2001jdev user on the Hugging Face Hub. It maps clinical-trial topic identifiers to NCT registry IDs with graded relevance scores.","category":"public-records","category_title":"Public Records & Filings","source":"huggingface","sources":["huggingface"],"url":"https://huggingface.co/datasets/2001jdev/clinical-trials-trec-qrels","listings":[{"org":"2001jdev","provider_slug":null,"source":"huggingface","url":"https://huggingface.co/datasets/2001jdev/clinical-trials-trec-qrels","pricing":null,"license":"unknown","has_source_logo":true}],"providers":[{"name":"2001jdev","slug":null,"url":"https://huggingface.co/datasets/2001jdev/clinical-trials-trec-qrels"}],"license":"unknown","size":null,"tier":"open","pricing":null,"delivery":"Download","delivery_inferred":true,"history":null,"refresh":null,"coverage":null,"updated_at":"2026-04-20","tags":["size_categories:100K<n<1M","format:parquet","modality:tabular","modality:text","library:datasets","library:pandas","library:polars","library:mlcroissant"],"preview_supported":true,"seo_indexable":true,"seo_canonical_slug":"2001jdev-clinical-trials-trec-qrels","category_inferred":false,"provider_slug":null,"org_url":"https://huggingface.co/2001jdev","has_source_logo":true,"hay":"2001jdev clinical-trials-trec-qrels clinical-trials-trec-qrels is a tabular relevance-judgment file distributed by the 2001jdev user on the hugging face hub. it maps clinical-trial topic identifiers to nct registry ids with graded relevance scores. size_categories:100k<n<1m format:parquet modality:tabular modality:text library:datasets library:pandas library:polars library:mlcroissant public records & filings unknown download huggingface  "}]}