{"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/cats-vs-dogs","name":"Cats and Dogs","full_name":null,"description_markdown":"A large set of images of cats and dogs. \r\n\r\nHomepage: https://www.microsoft.com/en-us/download/details.aspx?id=54765\r\n\r\nSource code: tfds.image_classification.CatsVsDogs\r\n\r\nVersions:\r\n\r\n4.0.0 (default): New split API (https://tensorflow.org/datasets/splits)\r\nDownload size: 786.68 MiB\r\n\r\n\r\nSource: https://www.tensorflow.org/datasets/catalog/cats_vs_dogs","description_withheld":null,"homepage":"https://www.microsoft.com/en-us/download/details.aspx?id=54765","introduced_date":null,"introduced_date_note":null,"introduced_by":null,"license":null,"modalities":[{"name":"Images","url":"/datasets/modality/images"}],"tasks":[{"name":"Image Classification","url":"/task/image-classification","datasets_with_task":"/datasets/task/image-classification"},{"name":"Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly","url":"/task/unsupervised-anomaly-detection-with-specified-4","datasets_with_task":"/datasets/task/unsupervised-anomaly-detection-with-specified-4"},{"name":"Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly","url":"/task/unsupervised-anomaly-detection-with-specified-5","datasets_with_task":"/datasets/task/unsupervised-anomaly-detection-with-specified-5"},{"name":"Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly","url":"/task/unsupervised-anomaly-detection-with-specified-6","datasets_with_task":"/datasets/task/unsupervised-anomaly-detection-with-specified-6"},{"name":"Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly","url":"/task/unsupervised-anomaly-detection-with-specified-7","datasets_with_task":"/datasets/task/unsupervised-anomaly-detection-with-specified-7"}],"languages":[],"variants":["cats_vs_dogs"],"data_loaders":[{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/microsoft/cats_vs_dogs","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/huggingface/datasets","url":"https://huggingface.co/datasets/cats_vs_dogs","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/activeloopai/Hub","url":"https://docs.activeloop.ai/datasets/kaggle-cats-and-dogs-dataset","frameworks":["tf","pytorch"]},{"repo":"https://github.com/tensorflow/datasets","url":"https://www.tensorflow.org/datasets/catalog/cats_vs_dogs","frameworks":["tf","pytorch","jax"]},{"repo":"https://github.com/Graviti-AI/datasets","url":"https://gas.graviti.com/dataset/graviti/DogsVsCats","frameworks":["tf","pytorch"]}],"num_papers_in_archive":13,"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28"},"benchmarks":[{"leaderboard":"/sota/unsupervised-anomaly-detection-with-specified-12","task":"Unsupervised Anomaly Detection with Specified Settings -- 0.1% anomaly","dataset_variant":"Cats and Dogs","rows":6,"metrics":["AUC-ROC"],"first_row_in_archive_order":{"model":"RSRAE","paper":"/paper/robust-subspace-recovery-layer-for","metrics":{"AUC-ROC":"0.982"},"code_links":[{"title":"dmzou/RSRAE","url":"https://github.com/dmzou/RSRAE"},{"title":"marrrcin/rsrlayer-pytorch","url":"https://github.com/marrrcin/rsrlayer-pytorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-anomaly-detection-with-specified-24","task":"Unsupervised Anomaly Detection with Specified Settings -- 20% anomaly","dataset_variant":"Cats and Dogs","rows":6,"metrics":["AUC-ROC"],"first_row_in_archive_order":{"model":"Shell-Renormalized","paper":"/paper/shell-theory-a-statistical-model-of-reality","metrics":{"AUC-ROC":"0.953"},"code_links":[{"title":"wen-yan-lin/shell-theory","url":"https://github.com/wen-yan-lin/shell-theory"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-anomaly-detection-with-specified-26","task":"Unsupervised Anomaly Detection with Specified Settings -- 10% anomaly","dataset_variant":"Cats and Dogs","rows":6,"metrics":["AUC-ROC"],"first_row_in_archive_order":{"model":"Shell-Renormalized","paper":"/paper/shell-theory-a-statistical-model-of-reality","metrics":{"AUC-ROC":"0.996"},"code_links":[{"title":"wen-yan-lin/shell-theory","url":"https://github.com/wen-yan-lin/shell-theory"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/unsupervised-anomaly-detection-with-specified-19","task":"Unsupervised Anomaly Detection with Specified Settings -- 1% anomaly","dataset_variant":"Cats and Dogs","rows":5,"metrics":["AUC-ROC"],"first_row_in_archive_order":{"model":"RSRAE","paper":"/paper/robust-subspace-recovery-layer-for","metrics":{"AUC-ROC":"0.981"},"code_links":[{"title":"dmzou/RSRAE","url":"https://github.com/dmzou/RSRAE"},{"title":"marrrcin/rsrlayer-pytorch","url":"https://github.com/marrrcin/rsrlayer-pytorch"}]},"note":"rows are the archive's own order at snapshot; nothing here re-ranks them"},{"leaderboard":"/sota/image-classification-on-cats-vs-dogs-1","task":"Image Classification","dataset_variant":"cats_vs_dogs","rows":1,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"µ2Net+ (ViT-L/16)","paper":"/paper/a-continual-development-methodology-for-large","metrics":{"Accuracy":"99.83"},"code_links":[{"title":"google-research/google-research","url":"https://github.com/google-research/google-research/tree/master/muNet"}]},"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":7,"of":7,"counts":{"papers_with_a_benchmark_row":7,"with_a_code_link":5,"where_syntology_ran_a_sample":0,"not_listed_spam_title":0,"listed":7,"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/locally-varying-distance-transform-for","slug":"locally-varying-distance-transform-for","title":"Locally varying distance transform for unsupervised visual anomaly detection","date":"2022-10-23","arxiv_id":null,"rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/a-continual-development-methodology-for-large","slug":"a-continual-development-methodology-for-large","title":"A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems","date":"2022-09-15","arxiv_id":"2209.07326","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/shell-theory-a-statistical-model-of-reality","slug":"shell-theory-a-statistical-model-of-reality","title":"Shell Theory: A Statistical Model of Reality","date":"2021-05-28","arxiv_id":null,"rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/deep-unsupervised-anomaly-detection","slug":"deep-unsupervised-anomaly-detection","title":"Deep unsupervised anomaly detection","date":"2021-01-05","arxiv_id":null,"rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/robust-subspace-recovery-layer-for","slug":"robust-subspace-recovery-layer-for","title":"Robust Subspace Recovery Layer for Unsupervised Anomaly Detection","date":"2019-03-30","arxiv_id":"1904.00152","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/deep-autoencoding-gaussian-mixture-model-for","slug":"deep-autoencoding-gaussian-mixture-model-for","title":"Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection","date":"2018-01-01","arxiv_id":null,"rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/isolation-forest","slug":"isolation-forest","title":"Isolation forest","date":"2008-12-15","arxiv_id":null,"rows_on_this_dataset":4,"code_links":0,"syntology":null}],"full_list":"papers_with_a_benchmark_row: every listed paper, in this order"},"papers_with_a_benchmark_row":[{"paper":"/paper/locally-varying-distance-transform-for","slug":"locally-varying-distance-transform-for","title":"Locally varying distance transform for unsupervised visual anomaly detection","date":"2022-10-23","arxiv_id":null,"rows_on_this_dataset":4,"code_links":1,"syntology":null},{"paper":"/paper/a-continual-development-methodology-for-large","slug":"a-continual-development-methodology-for-large","title":"A Continual Development Methodology for Large-scale Multitask Dynamic ML Systems","date":"2022-09-15","arxiv_id":"2209.07326","rows_on_this_dataset":1,"code_links":1,"syntology":null},{"paper":"/paper/shell-theory-a-statistical-model-of-reality","slug":"shell-theory-a-statistical-model-of-reality","title":"Shell Theory: A Statistical Model of Reality","date":"2021-05-28","arxiv_id":null,"rows_on_this_dataset":3,"code_links":1,"syntology":null},{"paper":"/paper/deep-unsupervised-anomaly-detection","slug":"deep-unsupervised-anomaly-detection","title":"Deep unsupervised anomaly detection","date":"2021-01-05","arxiv_id":null,"rows_on_this_dataset":4,"code_links":0,"syntology":null},{"paper":"/paper/robust-subspace-recovery-layer-for","slug":"robust-subspace-recovery-layer-for","title":"Robust Subspace Recovery Layer for Unsupervised Anomaly Detection","date":"2019-03-30","arxiv_id":"1904.00152","rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/deep-autoencoding-gaussian-mixture-model-for","slug":"deep-autoencoding-gaussian-mixture-model-for","title":"Deep Autoencoding Gaussian Mixture Model for Unsupervised Anomaly Detection","date":"2018-01-01","arxiv_id":null,"rows_on_this_dataset":4,"code_links":2,"syntology":null},{"paper":"/paper/isolation-forest","slug":"isolation-forest","title":"Isolation forest","date":"2008-12-15","arxiv_id":null,"rows_on_this_dataset":4,"code_links":0,"syntology":null}],"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":0,"samples_harvested":0,"samples_ran":0,"samples_constructed":0,"samples_ran_checked":0,"samples_ran_instrument_failed":0,"samples_unverified":0,"pointer_only_for_licence":0,"papers_with_no_sample_that_ran":0,"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":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"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":[]},"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":"87fe779a7c0caed7508c513294f641b57cf5ce495c1777fa85794a14e832427d","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}