{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:BSPTARO3F6FGWJ3VXSHPVHYU3S","short_pith_number":"pith:BSPTARO3","schema_version":"1.0","canonical_sha256":"0c9f3045db2f8a6b2775bc8efa9f14dcb69cee9f58479b2f8fb1653ec34df3ab","source":{"kind":"arxiv","id":"2010.12230","version":3},"attestation_state":"computed","paper":{"title":"Coping with Label Shift via Distributionally Robust Optimisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC"],"primary_cat":"cs.LG","authors_text":"Aditya Menon, Andreas Veit, Jingzhao Zhang, Sanjiv Kumar, Srinadh Bhojanapalli, Suvrit Sra","submitted_at":"2020-10-23T08:33:04Z","abstract_excerpt":"The label shift problem refers to the supervised learning setting where the train and test label distributions do not match. Existing work addressing label shift usually assumes access to an \\emph{unlabelled} test sample. This sample may be used to estimate the test label distribution, and to then train a suitably re-weighted classifier. While approaches using this idea have proven effective, their scope is limited as it is not always feasible to access the target domain; further, they require repeated retraining if the model is to be deployed in \\emph{multiple} test environments. Can one inst"},"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":"2010.12230","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-23T08:33:04Z","cross_cats_sorted":["cs.CV","math.OC"],"title_canon_sha256":"a95ad3b016207331de8b1fc88dc563e8c9a81e31c4613dc456b503ef8feebd62","abstract_canon_sha256":"01bdbed69c47e95e71afb906bbd64d1dc7baf7ce918c1baf53454ced121b685e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:06:14.184137Z","signature_b64":"g0YEPtJbNM0yu1EcIhKikcoL+8lx4JSqy4eqhWOKM6MjB+/J5apgr6UR8JlWYchc1rVRFQWdAwxKhBRSuVVyAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c9f3045db2f8a6b2775bc8efa9f14dcb69cee9f58479b2f8fb1653ec34df3ab","last_reissued_at":"2026-07-05T03:06:14.183663Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:06:14.183663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coping with Label Shift via Distributionally Robust Optimisation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","math.OC"],"primary_cat":"cs.LG","authors_text":"Aditya Menon, Andreas Veit, Jingzhao Zhang, Sanjiv Kumar, Srinadh Bhojanapalli, Suvrit Sra","submitted_at":"2020-10-23T08:33:04Z","abstract_excerpt":"The label shift problem refers to the supervised learning setting where the train and test label distributions do not match. Existing work addressing label shift usually assumes access to an \\emph{unlabelled} test sample. This sample may be used to estimate the test label distribution, and to then train a suitably re-weighted classifier. While approaches using this idea have proven effective, their scope is limited as it is not always feasible to access the target domain; further, they require repeated retraining if the model is to be deployed in \\emph{multiple} test environments. Can one inst"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12230","kind":"arxiv","version":3},"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/2010.12230/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":"2010.12230","created_at":"2026-07-05T03:06:14.183720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.12230v3","created_at":"2026-07-05T03:06:14.183720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12230","created_at":"2026-07-05T03:06:14.183720+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSPTARO3F6FG","created_at":"2026-07-05T03:06:14.183720+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSPTARO3F6FGWJ3V","created_at":"2026-07-05T03:06:14.183720+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSPTARO3","created_at":"2026-07-05T03:06:14.183720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.04788","citing_title":"Machine Learning from Explanations","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BSPTARO3F6FGWJ3VXSHPVHYU3S","json":"https://pith.science/pith/BSPTARO3F6FGWJ3VXSHPVHYU3S.json","graph_json":"https://pith.science/api/pith-number/BSPTARO3F6FGWJ3VXSHPVHYU3S/graph.json","events_json":"https://pith.science/api/pith-number/BSPTARO3F6FGWJ3VXSHPVHYU3S/events.json","paper":"https://pith.science/paper/BSPTARO3"},"agent_actions":{"view_html":"https://pith.science/pith/BSPTARO3F6FGWJ3VXSHPVHYU3S","download_json":"https://pith.science/pith/BSPTARO3F6FGWJ3VXSHPVHYU3S.json","view_paper":"https://pith.science/paper/BSPTARO3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.12230&json=true","fetch_graph":"https://pith.science/api/pith-number/BSPTARO3F6FGWJ3VXSHPVHYU3S/graph.json","fetch_events":"https://pith.science/api/pith-number/BSPTARO3F6FGWJ3VXSHPVHYU3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSPTARO3F6FGWJ3VXSHPVHYU3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSPTARO3F6FGWJ3VXSHPVHYU3S/action/storage_attestation","attest_author":"https://pith.science/pith/BSPTARO3F6FGWJ3VXSHPVHYU3S/action/author_attestation","sign_citation":"https://pith.science/pith/BSPTARO3F6FGWJ3VXSHPVHYU3S/action/citation_signature","submit_replication":"https://pith.science/pith/BSPTARO3F6FGWJ3VXSHPVHYU3S/action/replication_record"}},"created_at":"2026-07-05T03:06:14.183720+00:00","updated_at":"2026-07-05T03:06:14.183720+00:00"}