{"url":"/task/overall-test","name":"Overall - Test","slug":"overall-test","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":34,"papers_with_code":11,"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":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/jeebench","name":"JEEBench","full_name":"","num_papers_in_archive":15},{"url":"/dataset/feedbackqa","name":"FeedbackQA","full_name":"","num_papers_in_archive":2}],"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":11,"of":11,"tagged_in_all":34,"items":[{"url":"/paper/comparative-study-of-deep-learning-methods","title":"Comparative study of deep learning methods for the automatic segmentation of lung, lesion and lesion type in CT scans of COVID-19 patients","date":"2020-07-29","arxiv_id":"2007.15546","repositories_listed":3,"syntology":null},{"url":"/paper/freelb-enhanced-adversarial-training-for","title":"FreeLB: Enhanced Adversarial Training for Natural Language Understanding","date":"2019-09-25","arxiv_id":"1909.11764","repositories_listed":2,"syntology":null},{"url":"/paper/deep-modeling-and-optimization-of-medical","title":"Deep Modeling and Optimization of Medical Image Classification","date":"2025-05-29","arxiv_id":"2505.23040","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-training-of-deep-neural-operator","title":"Efficient Training of Deep Neural Operator Networks via Randomized Sampling","date":"2024-09-20","arxiv_id":"2409.13280","repositories_listed":1,"syntology":null},{"url":"/paper/watt-weight-average-test-time-adaption-of","title":"WATT: Weight Average Test-Time Adaptation of CLIP","date":"2024-06-19","arxiv_id":"2406.13875","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/small-language-models-fine-tuned-to","title":"Small Language Models Fine-tuned to Coordinate Larger Language Models improve Complex Reasoning","date":"2023-10-21","arxiv_id":"2310.18338","repositories_listed":1,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":7}},{"url":"/paper/transferable-availability-poisoning-attacks","title":"Transferable Availability Poisoning Attacks","date":"2023-10-08","arxiv_id":"2310.05141","repositories_listed":1,"syntology":null},{"url":"/paper/have-llms-advanced-enough-a-challenging","title":"Have LLMs Advanced Enough? A Challenging Problem Solving Benchmark For Large Language Models","date":"2023-05-24","arxiv_id":"2305.15074","repositories_listed":1,"syntology":{"n":2,"n_ran":0,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/amplifying-membership-exposure-via-data","title":"Amplifying Membership Exposure via Data Poisoning","date":"2022-11-01","arxiv_id":"2211.00463","repositories_listed":1,"syntology":null},{"url":"/paper/using-interactive-feedback-to-improve-the-1","title":"Using Interactive Feedback to Improve the Accuracy and Explainability of Question Answering Systems Post-Deployment","date":"2022-04-06","arxiv_id":"2204.03025","repositories_listed":1,"syntology":null},{"url":"/paper/localizing-open-ontology-qa-semantic-parsers","title":"Localizing Open-Ontology QA Semantic Parsers in a Day Using Machine Translation","date":"2020-10-10","arxiv_id":"2010.05106","repositories_listed":1,"syntology":null}],"syntology_records":3,"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"}}