{"url":"/task/information-threading","name":"Information Threading","slug":"information-threading","description_markdown":"Identifying chronological and coherent sequences of documents or passages from multiple documents that capture the temporal relationships between documents and describe diverse information about a particular event, activity or discussion.","categories":[{"name":"Medical","url":"/area/medical"},{"name":"Natural Language Processing","url":"/area/natural-language-processing"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":4,"papers_with_code":3,"benchmarks":2,"benchmark_tables_in_archive":2,"benchmark_tables_shown":2,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/information-threading-on-newshead","slug":"information-threading-on-newshead","dataset":"NewSHead","dataset_url":"/dataset/newshead","rows_in_archive":4,"metrics":["NMI"],"first_row_in_archive_order":{"model":"HINT","paper_title":"Effective Hierarchical Information Threading Using Network Community Detection","paper_url":"/paper/effective-hierarchical-information-threading","paper_date":"2023-03-17","arxiv_id":null,"code_links":[{"title":"hitt08/HINT","url":"https://github.com/hitt08/HINT"}],"syntology":null}},{"leaderboard":"/sota/information-threading-on-multi-news","slug":"information-threading-on-multi-news","dataset":"Multi-News","dataset_url":"/dataset/multi-news","rows_in_archive":1,"metrics":["NMI"],"first_row_in_archive_order":{"model":"SeqINT","paper_title":"Identifying chronological and coherent information threads using 5W1H questions and temporal relationships","paper_url":"/paper/identifying-chronological-and-coherent","paper_date":"2023-01-18","arxiv_id":null,"code_links":[{"title":"hitt08/HINT","url":"https://github.com/hitt08/HINT"}],"syntology":null}}],"datasets":[{"url":"/dataset/multi-news","name":"Multi-News","full_name":"Multi-News","num_papers_in_archive":122},{"url":"/dataset/newshead","name":"NewSHead","full_name":"","num_papers_in_archive":11}],"subtasks":[],"parent_tasks":[{"url":"/task/information-extraction","name":"Information Extraction"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":3,"of":3,"tagged_in_all":4,"items":[{"url":"/paper/effective-hierarchical-information-threading","title":"Effective Hierarchical Information Threading Using Network Community Detection","date":"2023-03-17","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/identifying-chronological-and-coherent","title":"Identifying chronological and coherent information threads using 5W1H questions and temporal relationships","date":"2023-01-18","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/growing-story-forest-online-from-massive","title":"Growing Story Forest Online from Massive Breaking News","date":"2018-03-01","arxiv_id":"1803.00189","repositories_listed":1,"syntology":null}],"syntology_records":0,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}