{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:QLDFB4X7OEWHUCW25CJGFR5QIL","short_pith_number":"pith:QLDFB4X7","schema_version":"1.0","canonical_sha256":"82c650f2ff712c7a0adae89262c7b042d41205d4b94e3536faaace2d04358a49","source":{"kind":"arxiv","id":"2311.00476","version":1},"attestation_state":"computed","paper":{"title":"Group Distributionally Robust Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alison Q. O'Neil, Konstantinos Vilouras, Pedro Sanchez, Sotirios A. Tsaftaris, Xiao Liu","submitted_at":"2023-11-01T12:25:02Z","abstract_excerpt":"Knowledge distillation enables fast and effective transfer of features learned from a bigger model to a smaller one. However, distillation objectives are susceptible to sub-population shifts, a common scenario in medical imaging analysis which refers to groups/domains of data that are underrepresented in the training set. For instance, training models on health data acquired from multiple scanners or hospitals can yield subpar performance for minority groups. In this paper, inspired by distributionally robust optimization (DRO) techniques, we address this shortcoming by proposing a group-aware"},"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":"2311.00476","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-01T12:25:02Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"570725d44bf0458524ce345e3c67ed895a163195805a9ee48b0a4866607e5e6d","abstract_canon_sha256":"54906906f0e61afffb0d5463d27e9271119ac8c3d73cbba3755e8461ef638818"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:58.383476Z","signature_b64":"gbRH6C9helTxcKWRJyP0isIwC/sMoYZ1dK9PPjN0xHQXyqtyCF9bgf7Fwe0aMm22MD3qZLWRgi1bj9jHZ8gtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"82c650f2ff712c7a0adae89262c7b042d41205d4b94e3536faaace2d04358a49","last_reissued_at":"2026-07-05T07:07:58.382997Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:58.382997Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Group Distributionally Robust Knowledge Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alison Q. O'Neil, Konstantinos Vilouras, Pedro Sanchez, Sotirios A. Tsaftaris, Xiao Liu","submitted_at":"2023-11-01T12:25:02Z","abstract_excerpt":"Knowledge distillation enables fast and effective transfer of features learned from a bigger model to a smaller one. However, distillation objectives are susceptible to sub-population shifts, a common scenario in medical imaging analysis which refers to groups/domains of data that are underrepresented in the training set. For instance, training models on health data acquired from multiple scanners or hospitals can yield subpar performance for minority groups. In this paper, inspired by distributionally robust optimization (DRO) techniques, we address this shortcoming by proposing a group-aware"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.00476","kind":"arxiv","version":1},"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/2311.00476/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":"2311.00476","created_at":"2026-07-05T07:07:58.383086+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.00476v1","created_at":"2026-07-05T07:07:58.383086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.00476","created_at":"2026-07-05T07:07:58.383086+00:00"},{"alias_kind":"pith_short_12","alias_value":"QLDFB4X7OEWH","created_at":"2026-07-05T07:07:58.383086+00:00"},{"alias_kind":"pith_short_16","alias_value":"QLDFB4X7OEWHUCW2","created_at":"2026-07-05T07:07:58.383086+00:00"},{"alias_kind":"pith_short_8","alias_value":"QLDFB4X7","created_at":"2026-07-05T07:07:58.383086+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/QLDFB4X7OEWHUCW25CJGFR5QIL","json":"https://pith.science/pith/QLDFB4X7OEWHUCW25CJGFR5QIL.json","graph_json":"https://pith.science/api/pith-number/QLDFB4X7OEWHUCW25CJGFR5QIL/graph.json","events_json":"https://pith.science/api/pith-number/QLDFB4X7OEWHUCW25CJGFR5QIL/events.json","paper":"https://pith.science/paper/QLDFB4X7"},"agent_actions":{"view_html":"https://pith.science/pith/QLDFB4X7OEWHUCW25CJGFR5QIL","download_json":"https://pith.science/pith/QLDFB4X7OEWHUCW25CJGFR5QIL.json","view_paper":"https://pith.science/paper/QLDFB4X7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.00476&json=true","fetch_graph":"https://pith.science/api/pith-number/QLDFB4X7OEWHUCW25CJGFR5QIL/graph.json","fetch_events":"https://pith.science/api/pith-number/QLDFB4X7OEWHUCW25CJGFR5QIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QLDFB4X7OEWHUCW25CJGFR5QIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QLDFB4X7OEWHUCW25CJGFR5QIL/action/storage_attestation","attest_author":"https://pith.science/pith/QLDFB4X7OEWHUCW25CJGFR5QIL/action/author_attestation","sign_citation":"https://pith.science/pith/QLDFB4X7OEWHUCW25CJGFR5QIL/action/citation_signature","submit_replication":"https://pith.science/pith/QLDFB4X7OEWHUCW25CJGFR5QIL/action/replication_record"}},"created_at":"2026-07-05T07:07:58.383086+00:00","updated_at":"2026-07-05T07:07:58.383086+00:00"}