{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/shifts-2-0-extending-the-dataset-of-real","title":"Shifts 2.0: Extending The Dataset of Real Distributional Shifts","arxiv_id":"2206.15407","date":"2022-06-30","proceeding":null,"authors":["Andrey Malinin","Andreas Athanasopoulos","Muhamed Barakovic","Meritxell Bach Cuadra","Mark J. F. Gales","Cristina Granziera","Mara Graziani","Nikolay Kartashev","Konstantinos Kyriakopoulos","Po-Jui Lu","Nataliia Molchanova","Antonis Nikitakis","Vatsal Raina","Francesco La Rosa","Eli Sivena","Vasileios Tsarsitalidis","Efi Tsompopoulou","Elena Volf"],"abstract":"Distributional shift, or the mismatch between training and deployment data, is a significant obstacle to the usage of machine learning in high-stakes industrial applications, such as autonomous driving and medicine. This creates a need to be able to assess how robustly ML models generalize as well as the quality of their uncertainty estimates. Standard ML baseline datasets do not allow these properties to be assessed, as the training, validation and test data are often identically distributed. Recently, a range of dedicated benchmarks have appeared, featuring both distributionally matched and shifted data. Among these benchmarks, the Shifts dataset stands out in terms of the diversity of tasks as well as the data modalities it features. While most of the benchmarks are heavily dominated by 2D image classification tasks, Shifts contains tabular weather forecasting, machine translation, and vehicle motion prediction tasks. This enables the robustness properties of models to be assessed on a diverse set of industrial-scale tasks and either universal or directly applicable task-specific conclusions to be reached. In this paper, we extend the Shifts Dataset with two datasets sourced from industrial, high-risk applications of high societal importance. Specifically, we consider the tasks of segmentation of white matter Multiple Sclerosis lesions in 3D magnetic resonance brain images and the estimation of power consumption in marine cargo vessels. Both tasks feature ubiquitous distributional shifts and a strict safety requirement due to the high cost of errors. These new datasets will allow researchers to further explore robust generalization and uncertainty estimation in new situations. In this work, we provide a description of the dataset and baseline results for both tasks.","url_abs":"https://arxiv.org/abs/2206.15407v2","url_pdf":"https://arxiv.org/pdf/2206.15407v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"shifts-2-0-extending-the-dataset-of-real","repo_url":"https://github.com/shifts-project/shifts","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}},{"paper_slug":"shifts-2-0-extending-the-dataset-of-real","repo_url":"https://github.com/yandex-research/shifts","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"autonomous-driving","task_name":"Autonomous Driving"},{"task_slug":"image-classification","task_name":"Image Classification"},{"task_slug":"machine-translation","task_name":"Machine Translation"},{"task_slug":"weather-forecasting","task_name":"Weather Forecasting"},{"task_slug":"image-classification","task_name":"image-classification"},{"task_slug":"motion-prediction","task_name":"motion prediction"}],"methods":[{"method_slug":"test","method_name":"Test"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2206.15407","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.15407"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/yandex-research/shifts","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/shifts-project/shifts","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":19},"by_repo_kind":{"official":{"samples":19,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"32f31d880069ea9d","entry":"calc_aucs","repo":"shifts-project/shifts","repo_kind":"official","path":"weather/assessment.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/weather/assessment.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"32f31d880069ea9d"}},{"code_sha256_prefix":"2787e52d21a2bf7e","entry":"calc_uncertainty_regection_curve","repo":"shifts-project/shifts","repo_kind":"official","path":"weather/assessment.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/weather/assessment.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2787e52d21a2bf7e"}},{"code_sha256_prefix":"a99c182ce1216b6f","entry":"construct_full_dev_sets","repo":"shifts-project/shifts","repo_kind":"official","path":"sdc/sdc/cache_metadata.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/sdc/sdc/cache_metadata.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a99c182ce1216b6f"}},{"code_sha256_prefix":"65521763be938fc5","entry":"construct_model_name_helper","repo":"shifts-project/shifts","repo_kind":"official","path":"sdc/plot_retention_curves.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/sdc/plot_retention_curves.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"65521763be938fc5"}},{"code_sha256_prefix":"fc31ff56fab222ef","entry":"dice_metric","repo":"shifts-project/shifts","repo_kind":"official","path":"mswml/metrics.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/mswml/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"fc31ff56fab222ef"}},{"code_sha256_prefix":"a7902a9714cafd0b","entry":"dice_norm_metric","repo":"shifts-project/shifts","repo_kind":"official","path":"mswml/metrics.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/mswml/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"a7902a9714cafd0b"}},{"code_sha256_prefix":"d992fc481289f284","entry":"ensemble_uncertainties_classification","repo":"shifts-project/shifts","repo_kind":"official","path":"weather/uncertainty.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/weather/uncertainty.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d992fc481289f284"}},{"code_sha256_prefix":"e4c7c0e0df8531fc","entry":"entropy_of_expected","repo":"shifts-project/shifts","repo_kind":"official","path":"mswml/uncertainty.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/mswml/uncertainty.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"e4c7c0e0df8531fc"}},{"code_sha256_prefix":"8c257ee78c6af4b0","entry":"entropy_of_expected_class","repo":"shifts-project/shifts","repo_kind":"official","path":"weather/uncertainty.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/weather/uncertainty.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8c257ee78c6af4b0"}},{"code_sha256_prefix":"ac5749939a4c2e43","entry":"expected_entropy_class","repo":"shifts-project/shifts","repo_kind":"official","path":"weather/uncertainty.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/weather/uncertainty.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ac5749939a4c2e43"}},{"code_sha256_prefix":"b36ada5e86b4525d","entry":"filter_top_d_plans","repo":"shifts-project/shifts","repo_kind":"official","path":"sdc/sdc/analyze_metadata.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/sdc/sdc/analyze_metadata.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"b36ada5e86b4525d"}},{"code_sha256_prefix":"0c9ae6c1b138f23e","entry":"get_plotting_style_metric_name","repo":"shifts-project/shifts","repo_kind":"official","path":"sdc/plot_retention_curves.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/sdc/plot_retention_curves.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"0c9ae6c1b138f23e"}},{"code_sha256_prefix":"83495554aedb7d95","entry":"get_sparsification_factor","repo":"shifts-project/shifts","repo_kind":"official","path":"sdc/plot_retention_curves.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/sdc/plot_retention_curves.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"83495554aedb7d95"}},{"code_sha256_prefix":"1f5326db4a7bbe88","entry":"load_dataset_key_to_arrs","repo":"shifts-project/shifts","repo_kind":"official","path":"sdc/sdc/cache_metadata.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/sdc/sdc/cache_metadata.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"1f5326db4a7bbe88"}},{"code_sha256_prefix":"9f7420e10d09842f","entry":"load_request_df","repo":"shifts-project/shifts","repo_kind":"official","path":"sdc/sdc/cache_metadata.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/sdc/sdc/cache_metadata.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9f7420e10d09842f"}},{"code_sha256_prefix":"8c63b918b61bb33d","entry":"ndsc_aac_metric","repo":"shifts-project/shifts","repo_kind":"official","path":"mswml/metrics.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/mswml/metrics.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"8c63b918b61bb33d"}},{"code_sha256_prefix":"d2ee41704e0bf321","entry":"prr_classification","repo":"shifts-project/shifts","repo_kind":"official","path":"weather/assessment.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/weather/assessment.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"d2ee41704e0bf321"}},{"code_sha256_prefix":"2d472c7f8fa5769d","entry":"renyi_entropy_of_expected","repo":"shifts-project/shifts","repo_kind":"official","path":"mswml/uncertainty.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/mswml/uncertainty.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"2d472c7f8fa5769d"}},{"code_sha256_prefix":"936046ea2d77b177","entry":"renyi_expected_entropy","repo":"shifts-project/shifts","repo_kind":"official","path":"mswml/uncertainty.py","file_url":"https://github.com/shifts-project/shifts/blob/HEAD/mswml/uncertainty.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"936046ea2d77b177"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}