{"url":"/task/commonsense-causal-reasoning","name":"Commonsense Causal Reasoning","slug":"commonsense-causal-reasoning","description_markdown":"\"Commonsense Causal Reasoning is the process of capturing and understanding the causal dependencies amongst events and actions.\" Luo, Zhiyi, et al. \"Commonsense causal reasoning between short texts.\" Fifteenth International Conference on the Principles of Knowledge Representation and Reasoning. 2016.","categories":[{"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":13,"papers_with_code":7,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"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":3,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/causalchaos","name":"CausalChaos!","full_name":"CausalChaos!QA","num_papers_in_archive":1},{"url":"/dataset/cold-causal-reasoning-in-closed-daily","name":"COLD: Causal Reasoning in Closed Daily Activities","full_name":"","num_papers_in_archive":1},{"url":"/dataset/this-is-not-a-dataset","name":"This is not a Dataset","full_name":"This is not a Dataset: A Large Negation Benchmark to Challenge Large Language Models","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[],"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":7,"of":7,"tagged_in_all":13,"items":[{"url":"/paper/cladder-a-benchmark-to-assess-causal-1","title":"CLadder: Assessing Causal Reasoning in Language Models","date":"2023-12-07","arxiv_id":"2312.04350","repositories_listed":2,"syntology":{"n":19,"n_ran":15,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/cold-causal-reasoning-in-closed-daily","title":"COLD: Causal reasOning in cLosed Daily activities","date":"2024-11-29","arxiv_id":"2411.19500","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/cola-contextualized-commonsense-causal","title":"COLA: Contextualized Commonsense Causal Reasoning from the Causal Inference Perspective","date":"2023-05-09","arxiv_id":"2305.05191","repositories_listed":1,"syntology":{"n":18,"n_ran":3,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/commonsense-knowledge-augmented-pretrained-1","title":"Knowledge-Augmented Language Models for Cause-Effect Relation Classification","date":"2021-12-16","arxiv_id":"2112.08615","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/headlinecause-a-dataset-of-news-headlines-for","title":"HeadlineCause: A Dataset of News Headlines for Detecting Causalities","date":"2021-08-28","arxiv_id":"2108.12626","repositories_listed":1,"syntology":null},{"url":"/paper/doing-good-or-doing-right-exploring-the","title":"Doing Good or Doing Right? Exploring the Weakness of Commonsense Causal Reasoning Models","date":"2021-07-05","arxiv_id":"2107.01791","repositories_listed":1,"syntology":null},{"url":"/paper/visual-choice-of-plausible-alternatives-an","title":"Visual Choice of Plausible Alternatives: An Evaluation of Image-based Commonsense Causal Reasoning","date":"2018-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null}],"syntology_records":4,"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"}}