{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/dataset/chexpert","name":"CheXpert","full_name":"CheXpert","description_markdown":"The **CheXpert** dataset contains 224,316 chest radiographs of 65,240 patients with both frontal and lateral views available. The task is to do automated chest x-ray interpretation, featuring uncertainty labels and radiologist-labeled reference standard evaluation sets.\r\n\r\nSource: [Deep Mining External Imperfect Data for Chest X-ray Disease Screening](https://arxiv.org/abs/2006.03796)\r\nImage Source: [https://stanfordmlgroup.github.io/competitions/chexpert/](https://stanfordmlgroup.github.io/competitions/chexpert/)","description_withheld":null,"homepage":"https://stanfordmlgroup.github.io/competitions/chexpert/","introduced_date":"2019-01-01","introduced_date_note":null,"introduced_by":{"paper":"/paper/chexpert-a-large-chest-radiograph-dataset","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","first_author":"Jeremy Irvin","url":null},"license":{"name":"Custom","url":"https://stanfordmlgroup.github.io/competitions/chexpert/"},"modalities":[{"name":"Images","url":"/datasets/modality/images"},{"name":"Medical","url":"/datasets/modality/medical"}],"tasks":[{"name":"Multi-Label Classification","url":"/task/multi-label-classification","datasets_with_task":"/datasets/task/multi-label-classification"},{"name":"Concept-based Classification","url":"/task/concept-based-classification","datasets_with_task":"/datasets/task/concept-based-classification"}],"languages":[{"name":"English","url":"/datasets/language/english"},{"name":"Korean","url":"/datasets/language/korean"}],"variants":["CheXpert"],"data_loaders":[{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/chexpert","frameworks":["tf","jax"]}],"num_papers_in_archive":628,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/multi-label-classification-on-chexpert","task":"Multi-Label Classification","dataset_variant":"CheXpert","rows":226,"metrics":["AVERAGE AUC ON 14 LABEL","NUM RADS BELOW CURVE"],"first_row_in_archive_order":{"model":"CFT (ensemble) Macao Polytechnic University","paper":"/paper/category-wise-fine-tuning-for-image-multi","metrics":{"AVERAGE AUC ON 14 LABEL":"0.933"},"code_links":[{"title":"maxium0526/category-wise-fine-tuning","url":"https://github.com/maxium0526/category-wise-fine-tuning"},{"title":"maxium0526/cft-chexpert","url":"https://github.com/maxium0526/cft-chexpert"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/concept-based-classification-on-chexpert","task":"Concept-based Classification","dataset_variant":"CheXpert","rows":1,"metrics":["Task Accuracy (%)","Concept Accuracy (%)"],"first_row_in_archive_order":{"model":"CGEM (ResNet-34)","paper":"/paper/concept-graph-embedding-models-for-enhanced","metrics":{"Concept Accuracy (%)":"63.52","Task Accuracy (%)":"89.25"},"code_links":[{"title":"jumpsnack/cgem","url":"https://github.com/jumpsnack/cgem"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/medical-image-deblurring-on-chexpert","task":"Medical Image Deblurring","dataset_variant":"ChexPert","rows":1,"metrics":["Average PSNR"],"first_row_in_archive_order":{"model":"MedDeblur","paper":"/paper/meddeblur-medical-image-deblurring-with","metrics":{"Average PSNR":"28.09"},"code_links":[{"title":"sharif-apu/MedDeblur","url":"https://github.com/sharif-apu/MedDeblur"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"}],"papers":{"order":"date (newest first), then slug","population":"every paper with a leaderboard row on this dataset's benchmarks (the benchmark-backed subset): the archive's own papers-using-this-dataset list was never published, so this is not that list; num_papers_in_archive is the archive's own count","page":1,"pages_in_order":1,"rows_per_page":100,"shown":10,"of":10,"counts":{"papers_with_a_benchmark_row":10,"with_a_code_link":8,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":10,"listed_where_code_ran":0,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":0,"every_run_a_failure_of_syntologys_instrument":0,"listed_with_a_run_with_no_instrument_failure":0,"listed_every_run_a_failure_of_syntologys_instrument":0,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers with at least one leaderboard row on this dataset's benchmarks; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"paper":"/paper/concept-graph-embedding-models-for-enhanced","slug":"concept-graph-embedding-models-for-enhanced","title":"Concept Graph Embedding Models for Enhanced Accuracy and Interpretability","date":"2024-08-13","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/masks-and-manuscripts-advancing-medical-pre","slug":"masks-and-manuscripts-advancing-medical-pre","title":"Masks and Manuscripts: Advancing Medical Pre-training with End-to-End Masking and Narrative Structuring","date":"2024-07-23","arxiv_id":"2407.16264","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/category-wise-fine-tuning-for-image-multi","slug":"category-wise-fine-tuning-for-image-multi","title":"Category-Wise Fine-Tuning for Image Multi-label Classification with Partial Labels","date":"2023-11-27","arxiv_id":null,"rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/meddeblur-medical-image-deblurring-with","slug":"meddeblur-medical-image-deblurring-with","title":"MedDeblur: Medical Image Deblurring with Residual Dense Spatial-Asymmetric Attention","date":"2022-12-27","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/projective-transformation-rectification-for","slug":"projective-transformation-rectification-for","title":"Image Projective Transformation Rectification with Synthetic Data for Smartphone-captured Chest X-ray Photos Classification","date":"2022-10-12","arxiv_id":"2210.05954","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/anatomy-x-net-a-semi-supervised-anatomy-aware","slug":"anatomy-x-net-a-semi-supervised-anatomy-aware","title":"Anatomy-XNet: An Anatomy Aware Convolutional Neural Network for Thoracic Disease Classification in Chest X-rays","date":"2021-06-10","arxiv_id":"2106.05915","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/robust-deep-auc-maximization-a-new-surrogate","slug":"robust-deep-auc-maximization-a-new-surrogate","title":"Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification","date":"2020-12-06","arxiv_id":"2012.03173","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/chexclusion-fairness-gaps-in-deep-chest-x-ray","slug":"chexclusion-fairness-gaps-in-deep-chest-x-ray","title":"CheXclusion: Fairness gaps in deep chest X-ray classifiers","date":"2020-02-14","arxiv_id":"2003.00827","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/interpreting-chest-x-rays-via-cnns-that","slug":"interpreting-chest-x-rays-via-cnns-that","title":"Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labels","date":"2019-11-15","arxiv_id":"1911.06475","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/chexpert-a-large-chest-radiograph-dataset","slug":"chexpert-a-large-chest-radiograph-dataset","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","date":"2019-01-21","arxiv_id":"1901.07031","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/chexpert-a-large-chest-radiograph-dataset#ran","syntology_url":"https://syntology.ai/paper/1901.07031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07031"}}}}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/concept-graph-embedding-models-for-enhanced","slug":"concept-graph-embedding-models-for-enhanced","title":"Concept Graph Embedding Models for Enhanced Accuracy and Interpretability","date":"2024-08-13","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/masks-and-manuscripts-advancing-medical-pre","slug":"masks-and-manuscripts-advancing-medical-pre","title":"Masks and Manuscripts: Advancing Medical Pre-training with End-to-End Masking and Narrative Structuring","date":"2024-07-23","arxiv_id":"2407.16264","rows_on_this_dataset":1,"code_links":0,"syntology":null},{"paper":"/paper/category-wise-fine-tuning-for-image-multi","slug":"category-wise-fine-tuning-for-image-multi","title":"Category-Wise Fine-Tuning for Image Multi-label Classification with Partial Labels","date":"2023-11-27","arxiv_id":null,"rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/meddeblur-medical-image-deblurring-with","slug":"meddeblur-medical-image-deblurring-with","title":"MedDeblur: Medical Image Deblurring with Residual Dense Spatial-Asymmetric Attention","date":"2022-12-27","arxiv_id":null,"rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/projective-transformation-rectification-for","slug":"projective-transformation-rectification-for","title":"Image Projective Transformation Rectification with Synthetic Data for Smartphone-captured Chest X-ray Photos Classification","date":"2022-10-12","arxiv_id":"2210.05954","rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/anatomy-x-net-a-semi-supervised-anatomy-aware","slug":"anatomy-x-net-a-semi-supervised-anatomy-aware","title":"Anatomy-XNet: An Anatomy Aware Convolutional Neural Network for Thoracic Disease Classification in Chest X-rays","date":"2021-06-10","arxiv_id":"2106.05915","rows_on_this_dataset":2,"code_links":0,"syntology":null},{"paper":"/paper/robust-deep-auc-maximization-a-new-surrogate","slug":"robust-deep-auc-maximization-a-new-surrogate","title":"Large-scale Robust Deep AUC Maximization: A New Surrogate Loss and Empirical Studies on Medical Image Classification","date":"2020-12-06","arxiv_id":"2012.03173","rows_on_this_dataset":1,"code_links":4,"syntology":null},{"paper":"/paper/chexclusion-fairness-gaps-in-deep-chest-x-ray","slug":"chexclusion-fairness-gaps-in-deep-chest-x-ray","title":"CheXclusion: Fairness gaps in deep chest X-ray classifiers","date":"2020-02-14","arxiv_id":"2003.00827","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/interpreting-chest-x-rays-via-cnns-that","slug":"interpreting-chest-x-rays-via-cnns-that","title":"Interpreting chest X-rays via CNNs that exploit hierarchical disease dependencies and uncertainty labels","date":"2019-11-15","arxiv_id":"1911.06475","rows_on_this_dataset":2,"code_links":2,"syntology":null},{"paper":"/paper/chexpert-a-large-chest-radiograph-dataset","slug":"chexpert-a-large-chest-radiograph-dataset","title":"CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison","date":"2019-01-21","arxiv_id":"1901.07031","rows_on_this_dataset":1,"code_links":12,"syntology":{"read_at":"2026-10-05T00:36:11+00:00","samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"official":null,"claim":"Per-sample execution on synthesized fixtures; not a correctness claim.","sample_list":"/paper/chexpert-a-large-chest-radiograph-dataset#ran","syntology_url":"https://syntology.ai/paper/1901.07031","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1901.07031"}}}}],"papers_where_code_ran":0,"papers_where_code_ran_first_page":null,"papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this dataset or check it against this dataset's benchmarks.","pages":[],"row_route":"each paper's syntology object carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers","syntology_totals":{"read_at":"2026-10-05T00:36:11+00:00","papers_with_samples":1,"samples_harvested":1,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":1,"pointer_only_for_licence":1,"papers_with_no_sample_that_ran":1,"papers_with_a_sample_that_ran":0,"papers_with_a_run_with_no_instrument_failure":0,"papers_where_every_run_was_an_instrument_failure":0,"note":"the per-paper counts of every listed paper (all pages), summed; not a rate"},"key_notes":{"samples_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","samples_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":1,"papers_placed":0,"judged_by":{"model":"Claude Sonnet 4.5","models_as_recorded":["global.anthropic.claude-sonnet-4-5-20250929-v1:0"],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[{"leaderboard":"/sota/multi-label-classification-on-chexpert","since_archive":"/sota/multi-label-classification-on-chexpert#since-judged","papers_judged":1,"placed":0}]},"papers_note":"The archive never published its papers-using-dataset list; these are papers with a leaderboard row on this dataset's benchmarks.","record_sha256":"91d1d7f27fac690f7c9527cfce28b892e37a464d03314bfefa0c28c4fb9ed133","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}