{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ST73KXVZ2J2RPOEQNRVCE4FTJW","short_pith_number":"pith:ST73KXVZ","schema_version":"1.0","canonical_sha256":"94ffb55eb9d27517b8906c6a2270b34daaa1333534e0e01438eb1c499b883d65","source":{"kind":"arxiv","id":"2302.02931","version":2},"attestation_state":"computed","paper":{"title":"Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditi Raghunathan, Amrith Setlur, Benjamin Eysenbach, Chelsea Finn, Don Dennis, Sergey Levine, Virginia Smith","submitted_at":"2023-02-06T17:07:16Z","abstract_excerpt":"Training machine learning models robust to distribution shifts is critical for real-world applications. Some robust training algorithms (e.g., Group DRO) specialize to group shifts and require group information on all training points. Other methods (e.g., CVaR DRO) that do not need group annotations can be overly conservative, since they naively upweight high loss points which may form a contrived set that does not correspond to any meaningful group in the real world (e.g., when the high loss points are randomly mislabeled training points). In this work, we address limitations in prior approac"},"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":"2302.02931","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-02-06T17:07:16Z","cross_cats_sorted":[],"title_canon_sha256":"311d3127384720846302eca4eda0bfb313539f3a0139171458d86ed490dac56d","abstract_canon_sha256":"3eb1d3ca1603e3b8df97c07690534d790661f104d0d200954794003b8413bdfc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:59:51.000605Z","signature_b64":"0xbfEAdskwBWpMm0xAOFqEd9HIFUO4nEHpoNHnoiYvv+SyUZJaLq+EnVPJMfgaTI7A0/LKEIgVCyYZHfMJeDDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94ffb55eb9d27517b8906c6a2270b34daaa1333534e0e01438eb1c499b883d65","last_reissued_at":"2026-07-05T06:59:51.000123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:59:51.000123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditi Raghunathan, Amrith Setlur, Benjamin Eysenbach, Chelsea Finn, Don Dennis, Sergey Levine, Virginia Smith","submitted_at":"2023-02-06T17:07:16Z","abstract_excerpt":"Training machine learning models robust to distribution shifts is critical for real-world applications. Some robust training algorithms (e.g., Group DRO) specialize to group shifts and require group information on all training points. Other methods (e.g., CVaR DRO) that do not need group annotations can be overly conservative, since they naively upweight high loss points which may form a contrived set that does not correspond to any meaningful group in the real world (e.g., when the high loss points are randomly mislabeled training points). In this work, we address limitations in prior approac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02931","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/2302.02931/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":"2302.02931","created_at":"2026-07-05T06:59:51.000180+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.02931v2","created_at":"2026-07-05T06:59:51.000180+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02931","created_at":"2026-07-05T06:59:51.000180+00:00"},{"alias_kind":"pith_short_12","alias_value":"ST73KXVZ2J2R","created_at":"2026-07-05T06:59:51.000180+00:00"},{"alias_kind":"pith_short_16","alias_value":"ST73KXVZ2J2RPOEQ","created_at":"2026-07-05T06:59:51.000180+00:00"},{"alias_kind":"pith_short_8","alias_value":"ST73KXVZ","created_at":"2026-07-05T06:59:51.000180+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ST73KXVZ2J2RPOEQNRVCE4FTJW","json":"https://pith.science/pith/ST73KXVZ2J2RPOEQNRVCE4FTJW.json","graph_json":"https://pith.science/api/pith-number/ST73KXVZ2J2RPOEQNRVCE4FTJW/graph.json","events_json":"https://pith.science/api/pith-number/ST73KXVZ2J2RPOEQNRVCE4FTJW/events.json","paper":"https://pith.science/paper/ST73KXVZ"},"agent_actions":{"view_html":"https://pith.science/pith/ST73KXVZ2J2RPOEQNRVCE4FTJW","download_json":"https://pith.science/pith/ST73KXVZ2J2RPOEQNRVCE4FTJW.json","view_paper":"https://pith.science/paper/ST73KXVZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.02931&json=true","fetch_graph":"https://pith.science/api/pith-number/ST73KXVZ2J2RPOEQNRVCE4FTJW/graph.json","fetch_events":"https://pith.science/api/pith-number/ST73KXVZ2J2RPOEQNRVCE4FTJW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ST73KXVZ2J2RPOEQNRVCE4FTJW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ST73KXVZ2J2RPOEQNRVCE4FTJW/action/storage_attestation","attest_author":"https://pith.science/pith/ST73KXVZ2J2RPOEQNRVCE4FTJW/action/author_attestation","sign_citation":"https://pith.science/pith/ST73KXVZ2J2RPOEQNRVCE4FTJW/action/citation_signature","submit_replication":"https://pith.science/pith/ST73KXVZ2J2RPOEQNRVCE4FTJW/action/replication_record"}},"created_at":"2026-07-05T06:59:51.000180+00:00","updated_at":"2026-07-05T06:59:51.000180+00:00"}