{"url":"/task/articles","name":"Articles","slug":"articles","description_markdown":null,"categories":[{"name":"Adversarial","url":"/area/adversarial"},{"name":"Audio","url":"/area/audio"},{"name":"Computer Code","url":"/area/computer-code"},{"name":"Computer Vision","url":"/area/computer-vision"},{"name":"Graphs","url":"/area/graphs"},{"name":"Knowledge Base","url":"/area/knowledge-base"},{"name":"Medical","url":"/area/medical"},{"name":"Methodology","url":"/area/methodology"},{"name":"Music","url":"/area/music"},{"name":"Playing Games","url":"/area/playing-games"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":4012,"papers_with_code":1123,"benchmarks":0,"benchmark_tables_in_archive":2,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":2,"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":0,"subtasks":0,"parent_tasks":2},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[{"url":"/task/2d-classification","name":"2D Classification"},{"url":"/task/2d-human-pose-estimation","name":"2D Human Pose Estimation"}],"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":30,"of":1123,"tagged_in_all":4012,"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/transformer-xl-attentive-language-models","title":"Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context","date":"2019-01-09","arxiv_id":"1901.02860","repositories_listed":37,"syntology":{"n":143,"n_ran":63,"n_unverified":80,"n_pointer_only":43}},{"url":"/paper/squad-100000-questions-for-machine","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","date":"2016-06-16","arxiv_id":"1606.05250","repositories_listed":21,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}},{"url":"/paper/a-contextual-bandit-approach-to-personalized","title":"A Contextual-Bandit Approach to Personalized News Article Recommendation","date":"2010-02-28","arxiv_id":"1003.0146","repositories_listed":12,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":1}},{"url":"/paper/reading-wikipedia-to-answer-open-domain","title":"Reading Wikipedia to Answer Open-Domain Questions","date":"2017-03-31","arxiv_id":"1704.00051","repositories_listed":10,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/wikihow-a-large-scale-text-summarization","title":"WikiHow: A Large Scale Text Summarization Dataset","date":"2018-10-18","arxiv_id":"1810.09305","repositories_listed":9,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/man-is-to-computer-programmer-as-woman-is-to","title":"Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings","date":"2016-07-21","arxiv_id":"1607.06520","repositories_listed":8,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/knowledge-graphs-meet-multi-modal-learning-a","title":"Knowledge Graphs Meet Multi-Modal Learning: A Comprehensive Survey","date":"2024-02-08","arxiv_id":"2402.05391","repositories_listed":6,"syntology":{"n":18,"n_ran":9,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/image-based-table-recognition-data-model-and","title":"Image-based table recognition: data, model, and evaluation","date":"2019-11-25","arxiv_id":"1911.10683","repositories_listed":6,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/scientific-statement-classification-over","title":"Scientific Statement Classification over arXiv.org","date":"2019-08-29","arxiv_id":"1908.10993","repositories_listed":6,"syntology":null},{"url":"/paper/190807836","title":"PubLayNet: largest dataset ever for document layout analysis","date":"2019-08-16","arxiv_id":"1908.07836","repositories_listed":6,"syntology":{"n":13,"n_ran":7,"n_unverified":6,"n_pointer_only":13}},{"url":"/paper/wikimatrix-mining-135m-parallel-sentences-in","title":"WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipedia","date":"2019-07-10","arxiv_id":"1907.05791","repositories_listed":6,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/newsroom-a-dataset-of-13-million-summaries","title":"Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies","date":"2018-04-30","arxiv_id":"1804.11283","repositories_listed":6,"syntology":null},{"url":"/paper/large-scale-domain-specific-pretraining-for","title":"BiomedCLIP: a multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","date":"2023-03-02","arxiv_id":"2303.00915","repositories_listed":5,"syntology":null},{"url":"/paper/multi-task-identification-of-entities","title":"Multi-Task Identification of Entities, Relations, and Coreference for Scientific Knowledge Graph Construction","date":"2018-08-29","arxiv_id":"1808.09602","repositories_listed":5,"syntology":null},{"url":"/paper/the-matrix-calculus-you-need-for-deep","title":"The Matrix Calculus You Need For Deep Learning","date":"2018-02-05","arxiv_id":"1802.01528","repositories_listed":5,"syntology":null},{"url":"/paper/nsina-a-news-corpus-for-sinhala","title":"NSINA: A News Corpus for Sinhala","date":"2024-03-25","arxiv_id":"2403.16571","repositories_listed":4,"syntology":null},{"url":"/paper/detectgpt-zero-shot-machine-generated-text","title":"DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature","date":"2023-01-26","arxiv_id":"2301.11305","repositories_listed":4,"syntology":{"n":9,"n_ran":3,"n_unverified":6,"n_pointer_only":2}},{"url":"/paper/pairwise-multi-class-document-classification","title":"Pairwise Multi-Class Document Classification for Semantic Relations between Wikipedia Articles","date":"2020-03-22","arxiv_id":"2003.09881","repositories_listed":4,"syntology":null},{"url":"/paper/dp-lstm-differential-privacy-inspired-lstm","title":"DP-LSTM: Differential Privacy-inspired LSTM for Stock Prediction Using Financial News","date":"2019-12-20","arxiv_id":"1912.10806","repositories_listed":4,"syntology":null},{"url":"/paper/mlqa-evaluating-cross-lingual-extractive","title":"MLQA: Evaluating Cross-lingual Extractive Question Answering","date":"2019-10-16","arxiv_id":"1910.07475","repositories_listed":4,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/benchmarking-zero-shot-text-classification","title":"Benchmarking Zero-shot Text Classification: Datasets, Evaluation and Entailment Approach","date":"2019-08-31","arxiv_id":"1909.00161","repositories_listed":4,"syntology":{"n":6,"n_ran":2,"n_unverified":4,"n_pointer_only":3}},{"url":"/paper/gan-qp-a-novel-gan-framework-without-gradient","title":"GAN-QP: A Novel GAN Framework without Gradient Vanishing and Lipschitz Constraint","date":"2018-11-18","arxiv_id":"1811.07296","repositories_listed":4,"syntology":null},{"url":"/paper/biosentvec-creating-sentence-embeddings-for","title":"BioSentVec: creating sentence embeddings for biomedical texts","date":"2018-10-22","arxiv_id":"1810.09302","repositories_listed":4,"syntology":null},{"url":"/paper/clinical-concept-embeddings-learned-from","title":"Clinical Concept Embeddings Learned from Massive Sources of Multimodal Medical Data","date":"2018-04-04","arxiv_id":"1804.01486","repositories_listed":4,"syntology":null},{"url":"/paper/generating-wikipedia-by-summarizing-long","title":"Generating Wikipedia by Summarizing Long Sequences","date":"2018-01-30","arxiv_id":"1801.10198","repositories_listed":4,"syntology":null},{"url":"/paper/generating-news-headlines-with-recurrent","title":"Generating News Headlines with Recurrent Neural Networks","date":"2015-12-05","arxiv_id":"1512.01712","repositories_listed":4,"syntology":null},{"url":"/paper/fast-rhetorical-structure-theory-discourse","title":"Fast Rhetorical Structure Theory Discourse Parsing","date":"2015-05-10","arxiv_id":"1505.02425","repositories_listed":4,"syntology":null},{"url":"/paper/scrambled-text-training-language-models-to","title":"Scrambled text: training Language Models to correct OCR errors using synthetic data","date":"2024-09-29","arxiv_id":"2409.19735","repositories_listed":3,"syntology":null},{"url":"/paper/muse-machine-unlearning-six-way-evaluation","title":"MUSE: Machine Unlearning Six-Way Evaluation for Language Models","date":"2024-07-08","arxiv_id":"2407.06460","repositories_listed":3,"syntology":null}],"syntology_records":14,"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"}}