{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/cocohd-congress-committee-hearing-dataset","title":"CoCoHD: Congress Committee Hearing Dataset","arxiv_id":"2410.03099","date":"2024-10-04","proceeding":null,"authors":["Arnav Hiray","Yunsong Liu","Mingxiao Song","Agam Shah","Sudheer Chava"],"abstract":"U.S. congressional hearings significantly influence the national economy and social fabric, impacting individual lives. Despite their importance, there is a lack of comprehensive datasets for analyzing these discourses. To address this, we propose the Congress Committee Hearing Dataset (CoCoHD), covering hearings from 1997 to 2024 across 86 committees, with 32,697 records. This dataset enables researchers to study policy language on critical issues like healthcare, LGBTQ+ rights, and climate justice. We demonstrate its potential with a case study on 1,000 energy-related sentences, analyzing the Energy and Commerce Committee's stance on fossil fuel consumption. By fine-tuning pre-trained language models, we create energy-relevant measures for each hearing. Our market analysis shows that natural language analysis using CoCoHD can predict and highlight trends in the energy sector.","url_abs":"https://arxiv.org/abs/2410.03099v1","url_pdf":"https://arxiv.org/pdf/2410.03099v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"cocohd-congress-committee-hearing-dataset","repo_url":"https://github.com/gtfintechlab/CoCoHD","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":0,"framework":"none","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.03099","atlas_url":"https://app.syntology.ai/?focus=2410.03099","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03099"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/gtfintechlab/CoCoHD","reach":{"status":"ok"}}],"summary":{"ran":2,"unverified":2},"by_repo_kind":{"official":{"samples":4,"ran":2,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":4,"samples":[{"code_sha256_prefix":"5a6f0c3636ebbb8d","entry":"count_files_in_folder","repo":"gtfintechlab/CoCoHD","repo_kind":"official","path":"data_collection/scrape_transcripts.py","file_url":"https://github.com/gtfintechlab/CoCoHD/blob/HEAD/data_collection/scrape_transcripts.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"5a6f0c3636ebbb8d"}},{"code_sha256_prefix":"2de461a7d36dd30c","entry":"generate_mapping","repo":"gtfintechlab/CoCoHD","repo_kind":"official","path":"data_cleaning/generate_mapping.py","file_url":"https://github.com/gtfintechlab/CoCoHD/blob/HEAD/data_cleaning/generate_mapping.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"2de461a7d36dd30c"}},{"code_sha256_prefix":"27982069dec9f283","entry":"fine_tune_plm","repo":"gtfintechlab/CoCoHD","repo_kind":"official","path":"finetuning/fine_tune_plm_grid_search.py","file_url":"https://github.com/gtfintechlab/CoCoHD/blob/HEAD/finetuning/fine_tune_plm_grid_search.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"27982069dec9f283"}},{"code_sha256_prefix":"65135a2920b02256","entry":"retrieve","repo":"gtfintechlab/CoCoHD","repo_kind":"official","path":"data_collection/scrape_transcripts.py","file_url":"https://github.com/gtfintechlab/CoCoHD/blob/HEAD/data_collection/scrape_transcripts.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"65135a2920b02256"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}