{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JLSDNQ7IOM2UUCMVUZDJ3ZHOBG","short_pith_number":"pith:JLSDNQ7I","canonical_record":{"source":{"id":"2509.08942","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T19:08:17Z","cross_cats_sorted":[],"title_canon_sha256":"8a2a02512419509d38373bad9e754352fcbe2e1519d1189dd7a417ae9abd9aad","abstract_canon_sha256":"260a716f749bdbb928f62dd85acabb302a12664571d8dbae3964dddc00003666"},"schema_version":"1.0"},"canonical_sha256":"4ae436c3e873354a0995a6469de4ee0993d70a54af76e79bbb82d9e44c415001","source":{"kind":"arxiv","id":"2509.08942","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08942","created_at":"2026-07-05T12:09:25Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08942v1","created_at":"2026-07-05T12:09:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08942","created_at":"2026-07-05T12:09:25Z"},{"alias_kind":"pith_short_12","alias_value":"JLSDNQ7IOM2U","created_at":"2026-07-05T12:09:25Z"},{"alias_kind":"pith_short_16","alias_value":"JLSDNQ7IOM2UUCMV","created_at":"2026-07-05T12:09:25Z"},{"alias_kind":"pith_short_8","alias_value":"JLSDNQ7I","created_at":"2026-07-05T12:09:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JLSDNQ7IOM2UUCMVUZDJ3ZHOBG","target":"record","payload":{"canonical_record":{"source":{"id":"2509.08942","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T19:08:17Z","cross_cats_sorted":[],"title_canon_sha256":"8a2a02512419509d38373bad9e754352fcbe2e1519d1189dd7a417ae9abd9aad","abstract_canon_sha256":"260a716f749bdbb928f62dd85acabb302a12664571d8dbae3964dddc00003666"},"schema_version":"1.0"},"canonical_sha256":"4ae436c3e873354a0995a6469de4ee0993d70a54af76e79bbb82d9e44c415001","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:09:25.723498Z","signature_b64":"FKA68629lJaX1WDktgXv4lACVJrwgcH5g+evIe+wb7QFFqTmo4STzVzQls4z5G9jFbSC7PohD1WzljefBfxdDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ae436c3e873354a0995a6469de4ee0993d70a54af76e79bbb82d9e44c415001","last_reissued_at":"2026-07-05T12:09:25.723037Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:09:25.723037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.08942","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:09:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q+h6aWvgc8XaIqx7OgznWp4W3XApKj3opXVvxpYQ6BpvEG1xUM67GP0Ypx/b29JkMlkpy9xHEt07EpC2l8fSCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:44:49.219737Z"},"content_sha256":"20e74c3ee3bbf2b4dca6c69eeea4ca4a2b0129ac65f7c75b6800eafaf69b8983","schema_version":"1.0","event_id":"sha256:20e74c3ee3bbf2b4dca6c69eeea4ca4a2b0129ac65f7c75b6800eafaf69b8983"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JLSDNQ7IOM2UUCMVUZDJ3ZHOBG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Group Distributionally Robust Machine Learning under Group Level Distributional Uncertainty","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Karl Henrik Johansson, Michael J. Pencina, Michael M. Zavlanos, Nicoleta J. Economou-Zavlanos, Xenia Konti, Yi Shen, Zifan Wang","submitted_at":"2025-09-10T19:08:17Z","abstract_excerpt":"The performance of machine learning (ML) models critically depends on the quality and representativeness of the training data. In applications with multiple heterogeneous data generating sources, standard ML methods often learn spurious correlations that perform well on average but degrade performance for atypical or underrepresented groups. Prior work addresses this issue by optimizing the worst-group performance. However, these approaches typically assume that the underlying data distributions for each group can be accurately estimated using the training data, a condition that is frequently "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08942","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/2509.08942/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:09:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0NeC4zVTEvfe6z6ab/kVTzyYHjng7HQ/4RsirNxI2EMLYZs13TuNds2564Y4129jTR1eLvJqWO357suLzwH1DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:44:49.220118Z"},"content_sha256":"066b5d1ddfa55076b3fb3c175ce491fc43d3afafb4d83fb5b814480e2ec78c16","schema_version":"1.0","event_id":"sha256:066b5d1ddfa55076b3fb3c175ce491fc43d3afafb4d83fb5b814480e2ec78c16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JLSDNQ7IOM2UUCMVUZDJ3ZHOBG/bundle.json","state_url":"https://pith.science/pith/JLSDNQ7IOM2UUCMVUZDJ3ZHOBG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JLSDNQ7IOM2UUCMVUZDJ3ZHOBG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T21:44:49Z","links":{"resolver":"https://pith.science/pith/JLSDNQ7IOM2UUCMVUZDJ3ZHOBG","bundle":"https://pith.science/pith/JLSDNQ7IOM2UUCMVUZDJ3ZHOBG/bundle.json","state":"https://pith.science/pith/JLSDNQ7IOM2UUCMVUZDJ3ZHOBG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JLSDNQ7IOM2UUCMVUZDJ3ZHOBG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JLSDNQ7IOM2UUCMVUZDJ3ZHOBG","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"260a716f749bdbb928f62dd85acabb302a12664571d8dbae3964dddc00003666","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T19:08:17Z","title_canon_sha256":"8a2a02512419509d38373bad9e754352fcbe2e1519d1189dd7a417ae9abd9aad"},"schema_version":"1.0","source":{"id":"2509.08942","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.08942","created_at":"2026-07-05T12:09:25Z"},{"alias_kind":"arxiv_version","alias_value":"2509.08942v1","created_at":"2026-07-05T12:09:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.08942","created_at":"2026-07-05T12:09:25Z"},{"alias_kind":"pith_short_12","alias_value":"JLSDNQ7IOM2U","created_at":"2026-07-05T12:09:25Z"},{"alias_kind":"pith_short_16","alias_value":"JLSDNQ7IOM2UUCMV","created_at":"2026-07-05T12:09:25Z"},{"alias_kind":"pith_short_8","alias_value":"JLSDNQ7I","created_at":"2026-07-05T12:09:25Z"}],"graph_snapshots":[{"event_id":"sha256:066b5d1ddfa55076b3fb3c175ce491fc43d3afafb4d83fb5b814480e2ec78c16","target":"graph","created_at":"2026-07-05T12:09:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2509.08942/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The performance of machine learning (ML) models critically depends on the quality and representativeness of the training data. In applications with multiple heterogeneous data generating sources, standard ML methods often learn spurious correlations that perform well on average but degrade performance for atypical or underrepresented groups. Prior work addresses this issue by optimizing the worst-group performance. However, these approaches typically assume that the underlying data distributions for each group can be accurately estimated using the training data, a condition that is frequently ","authors_text":"Karl Henrik Johansson, Michael J. Pencina, Michael M. Zavlanos, Nicoleta J. Economou-Zavlanos, Xenia Konti, Yi Shen, Zifan Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T19:08:17Z","title":"Group Distributionally Robust Machine Learning under Group Level Distributional Uncertainty"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.08942","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:20e74c3ee3bbf2b4dca6c69eeea4ca4a2b0129ac65f7c75b6800eafaf69b8983","target":"record","created_at":"2026-07-05T12:09:25Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"260a716f749bdbb928f62dd85acabb302a12664571d8dbae3964dddc00003666","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-10T19:08:17Z","title_canon_sha256":"8a2a02512419509d38373bad9e754352fcbe2e1519d1189dd7a417ae9abd9aad"},"schema_version":"1.0","source":{"id":"2509.08942","kind":"arxiv","version":1}},"canonical_sha256":"4ae436c3e873354a0995a6469de4ee0993d70a54af76e79bbb82d9e44c415001","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ae436c3e873354a0995a6469de4ee0993d70a54af76e79bbb82d9e44c415001","first_computed_at":"2026-07-05T12:09:25.723037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:09:25.723037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FKA68629lJaX1WDktgXv4lACVJrwgcH5g+evIe+wb7QFFqTmo4STzVzQls4z5G9jFbSC7PohD1WzljefBfxdDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:09:25.723498Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.08942","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20e74c3ee3bbf2b4dca6c69eeea4ca4a2b0129ac65f7c75b6800eafaf69b8983","sha256:066b5d1ddfa55076b3fb3c175ce491fc43d3afafb4d83fb5b814480e2ec78c16"],"state_sha256":"5c8833d5c97af193a84eeab10760168ab92f20ddeedc22f89a7d80179e18e684"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B3ZohnwaAbzaIIKOyZQ1tyt8LOT34+NY5zjy3KG8VKCGAsE52yRER4WP+zrwGHCuLaDRdNSkZznqtaXIx7c7Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:44:49.222959Z","bundle_sha256":"5315eea843477c8ec4cf28b7370df9a5d7d0546877fbf3feec506c1dcdd16b5c"}}