{"url":"/task/diagnostic","name":"Diagnostic","slug":"diagnostic","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":4513,"papers_with_code":1213,"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":1,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/ptb-xl","name":"PTB-XL","full_name":"","num_papers_in_archive":7}],"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":30,"of":1213,"tagged_in_all":4513,"items":[{"url":"/paper/revisiting-foreground-background-imbalance-in","title":"Is Heuristic Sampling Necessary in Training Deep Object Detectors?","date":"2019-09-11","arxiv_id":"1909.04868","repositories_listed":14,"syntology":null},{"url":"/paper/the-ham10000-dataset-a-large-collection-of","title":"The HAM10000 dataset, a large collection of multi-source dermatoscopic images of common pigmented skin lesions","date":"2018-03-28","arxiv_id":"1803.10417","repositories_listed":13,"syntology":{"n":4,"n_ran":0,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/glue-a-multi-task-benchmark-and-analysis","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","date":"2018-04-20","arxiv_id":"1804.07461","repositories_listed":11,"syntology":{"n":14,"n_ran":5,"n_unverified":9,"n_pointer_only":1}},{"url":"/paper/hallusionbench-you-see-what-you-think-or-you","title":"HallusionBench: An Advanced Diagnostic Suite for Entangled Language Hallucination and Visual Illusion in Large Vision-Language Models","date":"2023-10-23","arxiv_id":"2310.14566","repositories_listed":9,"syntology":{"n":8,"n_ran":2,"n_unverified":6,"n_pointer_only":1}},{"url":"/paper/on-the-limits-of-cross-domain-generalization","title":"On the limits of cross-domain generalization in automated X-ray prediction","date":"2020-02-06","arxiv_id":"2002.02497","repositories_listed":9,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/pareto-smoothed-importance-sampling","title":"Pareto Smoothed Importance Sampling","date":"2015-07-09","arxiv_id":"1507.02646","repositories_listed":9,"syntology":{"n":3,"n_ran":2,"n_unverified":1,"n_pointer_only":3}},{"url":"/paper/nas-bench-102-extending-the-scope-of","title":"NAS-Bench-201: Extending the Scope of Reproducible Neural Architecture Search","date":"2020-01-02","arxiv_id":"2001.00326","repositories_listed":6,"syntology":{"n":20,"n_ran":6,"n_unverified":14,"n_pointer_only":0}},{"url":"/paper/recurrent-relational-networks","title":"Recurrent Relational Networks","date":"2017-11-21","arxiv_id":"1711.08028","repositories_listed":6,"syntology":null},{"url":"/paper/pocovid-net-automatic-detection-of-covid-19","title":"POCOVID-Net: Automatic Detection of COVID-19 From a New Lung Ultrasound Imaging Dataset (POCUS)","date":"2020-04-25","arxiv_id":"2004.12084","repositories_listed":5,"syntology":null},{"url":"/paper/conditional-density-estimation-tools-in","title":"Conditional Density Estimation Tools in Python and R with Applications to Photometric Redshifts and Likelihood-Free Cosmological Inference","date":"2019-08-30","arxiv_id":"1908.11523","repositories_listed":5,"syntology":{"n":6,"n_ran":0,"n_unverified":6,"n_pointer_only":0}},{"url":"/paper/clutrr-a-diagnostic-benchmark-for-inductive","title":"CLUTRR: A Diagnostic Benchmark for Inductive Reasoning from Text","date":"2019-08-16","arxiv_id":"1908.06177","repositories_listed":5,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/clevr-a-diagnostic-dataset-for-compositional","title":"CLEVR: A Diagnostic Dataset for Compositional Language and Elementary Visual Reasoning","date":"2016-12-20","arxiv_id":"1612.06890","repositories_listed":5,"syntology":{"n":5,"n_ran":2,"n_unverified":3,"n_pointer_only":4}},{"url":"/paper/jana-jointly-amortized-neural-approximation","title":"JANA: Jointly Amortized Neural Approximation of Complex Bayesian Models","date":"2023-02-17","arxiv_id":"2302.09125","repositories_listed":4,"syntology":{"n":11,"n_ran":0,"n_unverified":11,"n_pointer_only":0}},{"url":"/paper/vision-and-language-or-vision-for-language-on","title":"Vision-and-Language or Vision-for-Language? On Cross-Modal Influence in Multimodal Transformers","date":"2021-09-09","arxiv_id":"2109.04448","repositories_listed":4,"syntology":{"n":7,"n_ran":0,"n_unverified":7,"n_pointer_only":0}},{"url":"/paper/nats-bench-benchmarking-nas-algorithms-for","title":"NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size","date":"2020-08-28","arxiv_id":"2009.00437","repositories_listed":4,"syntology":{"n":4,"n_ran":4,"n_unverified":0,"n_pointer_only":2}},{"url":"/paper/exploring-automatic-diagnosis-of-covid-19","title":"Exploring Automatic Diagnosis of COVID-19 from Crowdsourced Respiratory Sound Data","date":"2020-06-10","arxiv_id":"2006.05919","repositories_listed":4,"syntology":null},{"url":"/paper/evaluation-of-retinal-image-quality","title":"Evaluation of Retinal Image Quality Assessment Networks in Different Color-spaces","date":"2019-07-10","arxiv_id":"1907.05345","repositories_listed":4,"syntology":null},{"url":"/paper/auditor-an-r-package-for-model-agnostic","title":"auditor: an R Package for Model-Agnostic Visual Validation and Diagnostics","date":"2018-09-19","arxiv_id":"1809.07763","repositories_listed":4,"syntology":null},{"url":"/paper/voxel-based-differentiable-x-ray-rendering","title":"Differentiable Voxel-based X-ray Rendering Improves Sparse-View 3D CBCT Reconstruction","date":"2024-11-28","arxiv_id":"2411.19224","repositories_listed":3,"syntology":{"n":17,"n_ran":2,"n_unverified":15,"n_pointer_only":0}},{"url":"/paper/ratescore-a-metric-for-radiology-report","title":"RaTEScore: A Metric for Radiology Report Generation","date":"2024-06-24","arxiv_id":"2406.16845","repositories_listed":3,"syntology":null},{"url":"/paper/zero-1-to-3-domain-level-zero-shot-cognitive","title":"Zero-1-to-3: Domain-level Zero-shot Cognitive Diagnosis via One Batch of Early-bird Students towards Three Diagnostic Objectives","date":"2023-12-20","arxiv_id":"2312.13434","repositories_listed":3,"syntology":null},{"url":"/paper/mvbench-a-comprehensive-multi-modal-video","title":"MVBench: A Comprehensive Multi-modal Video Understanding Benchmark","date":"2023-11-28","arxiv_id":"2311.17005","repositories_listed":3,"syntology":{"n":10,"n_ran":7,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/2309-06085","title":"BHASA: A Holistic Southeast Asian Linguistic and Cultural Evaluation Suite for Large Language Models","date":"2023-09-12","arxiv_id":"2309.06085","repositories_listed":3,"syntology":null},{"url":"/paper/augmenting-chest-x-ray-datasets-with-non","title":"Augmenting Chest X-ray Datasets with Non-Expert Annotations","date":"2023-09-05","arxiv_id":"2309.02244","repositories_listed":3,"syntology":null},{"url":"/paper/segment-anything-in-medical-images","title":"Segment Anything in Medical Images","date":"2023-04-24","arxiv_id":"2304.12306","repositories_listed":3,"syntology":{"n":14,"n_ran":6,"n_unverified":8,"n_pointer_only":5}},{"url":"/paper/robust-and-efficient-medical-imaging-with","title":"Robust and Efficient Medical Imaging with Self-Supervision","date":"2022-05-19","arxiv_id":"2205.09723","repositories_listed":3,"syntology":{"n":28,"n_ran":5,"n_unverified":23,"n_pointer_only":0}},{"url":"/paper/online-forecasting-and-anomaly-detection","title":"Online Forecasting and Anomaly Detection Based on the ARIMA Model","date":"2021-04-02","arxiv_id":null,"repositories_listed":3,"syntology":null},{"url":"/paper/hatecheck-functional-tests-for-hate-speech","title":"HateCheck: Functional Tests for Hate Speech Detection Models","date":"2020-12-31","arxiv_id":"2012.15606","repositories_listed":3,"syntology":null},{"url":"/paper/covid-ct-md-covid-19-computed-tomography-ct","title":"COVID-CT-MD: COVID-19 Computed Tomography (CT) Scan Dataset Applicable in Machine Learning and Deep Learning","date":"2020-09-28","arxiv_id":"2009.14623","repositories_listed":3,"syntology":null},{"url":"/paper/generalized-word-shift-graphs-a-method-for","title":"Generalized Word Shift Graphs: A Method for Visualizing and Explaining Pairwise Comparisons Between Texts","date":"2020-08-05","arxiv_id":"2008.02250","repositories_listed":3,"syntology":null}],"syntology_records":16,"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"}}