{"url":"/task/answerability-prediction","name":"answerability prediction","slug":"answerability-prediction","description_markdown":null,"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":9,"papers_with_code":6,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[{"leaderboard":"/sota/answerability-prediction-on-peerqa","slug":"answerability-prediction-on-peerqa","dataset":"PeerQA","dataset_url":"/dataset/peerqa","rows_in_archive":6,"metrics":["Macro F1"],"first_row_in_archive_order":{"model":"Mistral-IT-v02-7B-32k","paper_title":"Mistral 7B","paper_url":"/paper/mistral-7b","paper_date":"2023-10-10","arxiv_id":"2310.06825","code_links":[{"title":"mistralai/mistral-src","url":"https://github.com/mistralai/mistral-src"},{"title":"facebookresearch/fairseq2","url":"https://github.com/facebookresearch/fairseq2"},{"title":"mgmalek/efficient_cross_entropy","url":"https://github.com/mgmalek/efficient_cross_entropy"},{"title":"ninglab/ecellm","url":"https://github.com/ninglab/ecellm"},{"title":"knowlab/bi-weekly-paper-presentation","url":"https://github.com/knowlab/bi-weekly-paper-presentation"},{"title":"pwc-1/Paper-9","url":"https://github.com/pwc-1/Paper-9/tree/main/2/mistral"}],"syntology":{"n":11,"n_ran":9,"n_unverified":2,"n_pointer_only":1}}}],"datasets":[{"url":"/dataset/peerqa","name":"PeerQA","full_name":"","num_papers_in_archive":12}],"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":6,"of":6,"tagged_in_all":9,"items":[{"url":"/paper/language-models-are-few-shot-learners","title":"Language Models are Few-Shot Learners","date":"2020-05-28","arxiv_id":"2005.14165","repositories_listed":67,"syntology":{"n":65,"n_ran":15,"n_unverified":50,"n_pointer_only":4}},{"url":"/paper/gpt-4-technical-report-1","title":"GPT-4 Technical Report","date":"2023-03-15","arxiv_id":"2303.08774","repositories_listed":11,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/mistral-7b","title":"Mistral 7B","date":"2023-10-10","arxiv_id":"2310.06825","repositories_listed":6,"syntology":{"n":11,"n_ran":9,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/the-llama-3-herd-of-models","title":"The Llama 3 Herd of Models","date":"2024-07-31","arxiv_id":"2407.21783","repositories_listed":5,"syntology":{"n":9,"n_ran":2,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/peerqa-a-scientific-question-answering","title":"PeerQA: A Scientific Question Answering Dataset from Peer Reviews","date":"2025-02-19","arxiv_id":"2502.13668","repositories_listed":1,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/towards-reliable-and-factual-response","title":"Towards Reliable and Factual Response Generation: Detecting Unanswerable Questions in Information-Seeking Conversations","date":"2024-01-21","arxiv_id":"2401.11452","repositories_listed":1,"syntology":null}],"syntology_records":5,"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"}}