{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:INGKD4TJR3WH2QVUTSABTY33X5","short_pith_number":"pith:INGKD4TJ","schema_version":"1.0","canonical_sha256":"434ca1f2698eec7d42b49c8019e37bbf7baee5f66b3e17fa6faac45ca262823b","source":{"kind":"arxiv","id":"2206.15407","version":2},"attestation_state":"computed","paper":{"title":"Shifts 2.0: Extending The Dataset of Real Distributional Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Athanasopoulos, Andrey Malinin, Antonis Nikitakis, Cristina Granziera, Efi Tsompopoulou, Elena Volf, Eli Sivena, Francesco La Rosa, Konstantinos Kyriakopoulos, Mara Graziani, Mark J. F. Gales, Meritxell Bach Cuadra, Muhamed Barakovic, Nataliia Molchanova, Nikolay Kartashev, Po-Jui Lu, Vasileios Tsarsitalidis, Vatsal Raina","submitted_at":"2022-06-30T16:51:52Z","abstract_excerpt":"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 "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2206.15407","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-06-30T16:51:52Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"944cb761dc30733ce51e4612d92bb830aab9c3d1d263adcb84a1bef0a6bce5da","abstract_canon_sha256":"255c3a9e32f33ab16e6868c3303536a8be2c30378e1bc972aab6346a2f922de0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:57:47.390929Z","signature_b64":"2T3dNyqLHDQQaFiOLYhLkKY2UkoHWiQIrotCVk/xETV8p/u9uyZRoAIR/LO/1Ujl6NZgXYhkN/poa2y4P8shCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"434ca1f2698eec7d42b49c8019e37bbf7baee5f66b3e17fa6faac45ca262823b","last_reissued_at":"2026-07-05T04:57:47.390431Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:57:47.390431Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Shifts 2.0: Extending The Dataset of Real Distributional Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andreas Athanasopoulos, Andrey Malinin, Antonis Nikitakis, Cristina Granziera, Efi Tsompopoulou, Elena Volf, Eli Sivena, Francesco La Rosa, Konstantinos Kyriakopoulos, Mara Graziani, Mark J. F. Gales, Meritxell Bach Cuadra, Muhamed Barakovic, Nataliia Molchanova, Nikolay Kartashev, Po-Jui Lu, Vasileios Tsarsitalidis, Vatsal Raina","submitted_at":"2022-06-30T16:51:52Z","abstract_excerpt":"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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15407","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.15407/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2206.15407","created_at":"2026-07-05T04:57:47.390490+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.15407v2","created_at":"2026-07-05T04:57:47.390490+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15407","created_at":"2026-07-05T04:57:47.390490+00:00"},{"alias_kind":"pith_short_12","alias_value":"INGKD4TJR3WH","created_at":"2026-07-05T04:57:47.390490+00:00"},{"alias_kind":"pith_short_16","alias_value":"INGKD4TJR3WH2QVU","created_at":"2026-07-05T04:57:47.390490+00:00"},{"alias_kind":"pith_short_8","alias_value":"INGKD4TJ","created_at":"2026-07-05T04:57:47.390490+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30410","citing_title":"Beyond IID: How General Are Tabular Foundation Models, Really?","ref_index":176,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INGKD4TJR3WH2QVUTSABTY33X5","json":"https://pith.science/pith/INGKD4TJR3WH2QVUTSABTY33X5.json","graph_json":"https://pith.science/api/pith-number/INGKD4TJR3WH2QVUTSABTY33X5/graph.json","events_json":"https://pith.science/api/pith-number/INGKD4TJR3WH2QVUTSABTY33X5/events.json","paper":"https://pith.science/paper/INGKD4TJ"},"agent_actions":{"view_html":"https://pith.science/pith/INGKD4TJR3WH2QVUTSABTY33X5","download_json":"https://pith.science/pith/INGKD4TJR3WH2QVUTSABTY33X5.json","view_paper":"https://pith.science/paper/INGKD4TJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.15407&json=true","fetch_graph":"https://pith.science/api/pith-number/INGKD4TJR3WH2QVUTSABTY33X5/graph.json","fetch_events":"https://pith.science/api/pith-number/INGKD4TJR3WH2QVUTSABTY33X5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INGKD4TJR3WH2QVUTSABTY33X5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INGKD4TJR3WH2QVUTSABTY33X5/action/storage_attestation","attest_author":"https://pith.science/pith/INGKD4TJR3WH2QVUTSABTY33X5/action/author_attestation","sign_citation":"https://pith.science/pith/INGKD4TJR3WH2QVUTSABTY33X5/action/citation_signature","submit_replication":"https://pith.science/pith/INGKD4TJR3WH2QVUTSABTY33X5/action/replication_record"}},"created_at":"2026-07-05T04:57:47.390490+00:00","updated_at":"2026-07-05T04:57:47.390490+00:00"}