{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5JUKAADB4RYPZTZCHKKIM6YI2L","short_pith_number":"pith:5JUKAADB","canonical_record":{"source":{"id":"2302.02323","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T07:23:35Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"602943e1288dcb851cd9d58e70b980884265381e3ec3f6e4e6c87b2fb8309bfb","abstract_canon_sha256":"41cc1d7b06e709e50a6e32294056ea65aa2c9449a11ed1d5966edbc2d4215d81"},"schema_version":"1.0"},"canonical_sha256":"ea68a00061e470fccf223a94867b08d2c9f0814315d633fa4658d4647a873172","source":{"kind":"arxiv","id":"2302.02323","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02323","created_at":"2026-07-05T05:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02323v1","created_at":"2026-07-05T05:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02323","created_at":"2026-07-05T05:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"5JUKAADB4RYP","created_at":"2026-07-05T05:38:52Z"},{"alias_kind":"pith_short_16","alias_value":"5JUKAADB4RYPZTZC","created_at":"2026-07-05T05:38:52Z"},{"alias_kind":"pith_short_8","alias_value":"5JUKAADB","created_at":"2026-07-05T05:38:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5JUKAADB4RYPZTZCHKKIM6YI2L","target":"record","payload":{"canonical_record":{"source":{"id":"2302.02323","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T07:23:35Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"602943e1288dcb851cd9d58e70b980884265381e3ec3f6e4e6c87b2fb8309bfb","abstract_canon_sha256":"41cc1d7b06e709e50a6e32294056ea65aa2c9449a11ed1d5966edbc2d4215d81"},"schema_version":"1.0"},"canonical_sha256":"ea68a00061e470fccf223a94867b08d2c9f0814315d633fa4658d4647a873172","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:52.007359Z","signature_b64":"A0rPzNAm24dlspf46ci+P2kXTexa9OFtfZCUVeHEJ/53suQpO5coZZ2MczRrLGUDD/D3eXQR+jZe198U8QthDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea68a00061e470fccf223a94867b08d2c9f0814315d633fa4658d4647a873172","last_reissued_at":"2026-07-05T05:38:52.006860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:52.006860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.02323","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":"2026-07-05T05:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fODCvjdLKCBnl6Uo90IR2q2iBMsuvJvivbzXFzZ0xLEqFXk9fqmAbBeT6KV7+I+TAn/FDIP/i2i4XGyCVF6uDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:35:13.923173Z"},"content_sha256":"7ab793c5bfcf06f47211e35bb111f91fc7b1f4ba9b74c97893559dac2e72ea7b","schema_version":"1.0","event_id":"sha256:7ab793c5bfcf06f47211e35bb111f91fc7b1f4ba9b74c97893559dac2e72ea7b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5JUKAADB4RYPZTZCHKKIM6YI2L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Fair Training under Correlation Shifts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Changho Suh, Kangwook Lee, Steven Euijong Whang, Yuji Roh","submitted_at":"2023-02-05T07:23:35Z","abstract_excerpt":"Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training and deployment data distributions are identical, which is often not true in practice. In particular, when the bias between labels and sensitive groups changes, the fairness of the trained model is directly influenced and can worsen. We make two contributions for solving this problem. First, we analytically show that existing in-processing fair algorithms have fundamental limits in accuracy and group fairness. We introduce the notion of co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02323","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/2302.02323/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":"2026-07-05T05:38:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DLpJwMGUfVY+7NZWkJue47+e77PgPF4UobHD8He3cTSGjwyCm7F9CJmKQXzyOZYo0Ahlw9g0y7BIb3OSVaejBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T12:35:13.924134Z"},"content_sha256":"1a4973708b13e7db3188d9a6c23053fe1409af4f1cd9c5e044a39f8d027f043b","schema_version":"1.0","event_id":"sha256:1a4973708b13e7db3188d9a6c23053fe1409af4f1cd9c5e044a39f8d027f043b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5JUKAADB4RYPZTZCHKKIM6YI2L/bundle.json","state_url":"https://pith.science/pith/5JUKAADB4RYPZTZCHKKIM6YI2L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5JUKAADB4RYPZTZCHKKIM6YI2L/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":"2026-08-17T12:35:13Z","links":{"resolver":"https://pith.science/pith/5JUKAADB4RYPZTZCHKKIM6YI2L","bundle":"https://pith.science/pith/5JUKAADB4RYPZTZCHKKIM6YI2L/bundle.json","state":"https://pith.science/pith/5JUKAADB4RYPZTZCHKKIM6YI2L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5JUKAADB4RYPZTZCHKKIM6YI2L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5JUKAADB4RYPZTZCHKKIM6YI2L","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":"41cc1d7b06e709e50a6e32294056ea65aa2c9449a11ed1d5966edbc2d4215d81","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T07:23:35Z","title_canon_sha256":"602943e1288dcb851cd9d58e70b980884265381e3ec3f6e4e6c87b2fb8309bfb"},"schema_version":"1.0","source":{"id":"2302.02323","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.02323","created_at":"2026-07-05T05:38:52Z"},{"alias_kind":"arxiv_version","alias_value":"2302.02323v1","created_at":"2026-07-05T05:38:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.02323","created_at":"2026-07-05T05:38:52Z"},{"alias_kind":"pith_short_12","alias_value":"5JUKAADB4RYP","created_at":"2026-07-05T05:38:52Z"},{"alias_kind":"pith_short_16","alias_value":"5JUKAADB4RYPZTZC","created_at":"2026-07-05T05:38:52Z"},{"alias_kind":"pith_short_8","alias_value":"5JUKAADB","created_at":"2026-07-05T05:38:52Z"}],"graph_snapshots":[{"event_id":"sha256:1a4973708b13e7db3188d9a6c23053fe1409af4f1cd9c5e044a39f8d027f043b","target":"graph","created_at":"2026-07-05T05:38:52Z","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/2302.02323/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model fairness is an essential element for Trustworthy AI. While many techniques for model fairness have been proposed, most of them assume that the training and deployment data distributions are identical, which is often not true in practice. In particular, when the bias between labels and sensitive groups changes, the fairness of the trained model is directly influenced and can worsen. We make two contributions for solving this problem. First, we analytically show that existing in-processing fair algorithms have fundamental limits in accuracy and group fairness. We introduce the notion of co","authors_text":"Changho Suh, Kangwook Lee, Steven Euijong Whang, Yuji Roh","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T07:23:35Z","title":"Improving Fair Training under Correlation Shifts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.02323","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":"sha256:7ab793c5bfcf06f47211e35bb111f91fc7b1f4ba9b74c97893559dac2e72ea7b","target":"record","created_at":"2026-07-05T05:38:52Z","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":"41cc1d7b06e709e50a6e32294056ea65aa2c9449a11ed1d5966edbc2d4215d81","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-02-05T07:23:35Z","title_canon_sha256":"602943e1288dcb851cd9d58e70b980884265381e3ec3f6e4e6c87b2fb8309bfb"},"schema_version":"1.0","source":{"id":"2302.02323","kind":"arxiv","version":1}},"canonical_sha256":"ea68a00061e470fccf223a94867b08d2c9f0814315d633fa4658d4647a873172","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea68a00061e470fccf223a94867b08d2c9f0814315d633fa4658d4647a873172","first_computed_at":"2026-07-05T05:38:52.006860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:38:52.006860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A0rPzNAm24dlspf46ci+P2kXTexa9OFtfZCUVeHEJ/53suQpO5coZZ2MczRrLGUDD/D3eXQR+jZe198U8QthDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:38:52.007359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.02323","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ab793c5bfcf06f47211e35bb111f91fc7b1f4ba9b74c97893559dac2e72ea7b","sha256:1a4973708b13e7db3188d9a6c23053fe1409af4f1cd9c5e044a39f8d027f043b"],"state_sha256":"23a9f51e33f55cd11bac03d25b97aab840839a1dcdfe7019370c2e7aaf4bb97a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BriCbAxf/SFtfaDJ8//11aZvuJb5b8Rfdspp/ld6jVRFicW8Q5IzzhQjqMIXqkZN8fozETn0RGjhxNvEVm4KAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T12:35:13.979193Z","bundle_sha256":"be1eeab62afa77ca4739f5f72d084bcfd64bfb5195d51e64d753af0ccc6f0e7b"}}