{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:GC3TUYHXJ3THCIMUBE73JITLQT","short_pith_number":"pith:GC3TUYHX","canonical_record":{"source":{"id":"2506.07861","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T15:24:56Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"2f7aa8ac83b5ac9faaa58455d4bb5d4c0ed4e93de8f94452933836094096f291","abstract_canon_sha256":"4fea2075bcb331f740a7620a515c9f6277b3a4ef0ab3af04b4ce2fe40e0588e7"},"schema_version":"1.0"},"canonical_sha256":"30b73a60f74ee6712194093fb4a26b84f20ea1d5d00a6f1f85bdd52b6d681378","source":{"kind":"arxiv","id":"2506.07861","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07861","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07861v1","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07861","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"GC3TUYHXJ3TH","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"GC3TUYHXJ3THCIMU","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"GC3TUYHX","created_at":"2026-07-05T11:18:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:GC3TUYHXJ3THCIMUBE73JITLQT","target":"record","payload":{"canonical_record":{"source":{"id":"2506.07861","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T15:24:56Z","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"title_canon_sha256":"2f7aa8ac83b5ac9faaa58455d4bb5d4c0ed4e93de8f94452933836094096f291","abstract_canon_sha256":"4fea2075bcb331f740a7620a515c9f6277b3a4ef0ab3af04b4ce2fe40e0588e7"},"schema_version":"1.0"},"canonical_sha256":"30b73a60f74ee6712194093fb4a26b84f20ea1d5d00a6f1f85bdd52b6d681378","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:18:34.634716Z","signature_b64":"nxAJUdFK31dh6f3k0ANlYCDc5eznV5zWrAn5N72Ai7eS/QH5c6x+np7EQVbsGGc3qtK8Whdu4sdzHDwzTJWFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30b73a60f74ee6712194093fb4a26b84f20ea1d5d00a6f1f85bdd52b6d681378","last_reissued_at":"2026-07-05T11:18:34.634230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:18:34.634230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.07861","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":"2026-07-05T11:18:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sA0JTYiqKWFATsBV6eg+vf56jmNudL3yNC/Ns9jQDnomiwqGMT4mpY3mp8/1UOf3IhOni8sCpCVmnysQuJRLAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:57:56.890934Z"},"content_sha256":"a3d785b98ac4be91b2427732a4366f60cb802c187ae5083724d93321f1e9fb6c","schema_version":"1.0","event_id":"sha256:a3d785b98ac4be91b2427732a4366f60cb802c187ae5083724d93321f1e9fb6c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:GC3TUYHXJ3THCIMUBE73JITLQT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.IT","math.IT"],"primary_cat":"cs.LG","authors_text":"Firas Laakom, Haobo Chen, J\\\"urgen Schmidhuber, Yuheng Bu","submitted_at":"2025-06-09T15:24:56Z","abstract_excerpt":"Despite substantial progress in promoting fairness in high-stake applications using machine learning models, existing methods often modify the training process, such as through regularizers or other interventions, but lack formal guarantees that fairness achieved during training will generalize to unseen data. Although overfitting with respect to prediction performance has been extensively studied, overfitting in terms of fairness loss has received far less attention. This paper proposes a theoretical framework for analyzing fairness generalization error through an information-theoretic lens. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07861","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/2506.07861/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":"2026-07-05T11:18:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y/mjpCMvcYlX+HCVVBnHHH1AZGQZssHyY4tpqb60qqPJLPxCngXQcn/iFfR1eY76r68U1XY19PupS4/5dffyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T15:57:56.891429Z"},"content_sha256":"8f5982ac1fd92f5d326e6fd78d742e69a9189b9b8e5c8458dbe0fe8e17acd856","schema_version":"1.0","event_id":"sha256:8f5982ac1fd92f5d326e6fd78d742e69a9189b9b8e5c8458dbe0fe8e17acd856"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GC3TUYHXJ3THCIMUBE73JITLQT/bundle.json","state_url":"https://pith.science/pith/GC3TUYHXJ3THCIMUBE73JITLQT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GC3TUYHXJ3THCIMUBE73JITLQT/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":"2026-08-08T15:57:56Z","links":{"resolver":"https://pith.science/pith/GC3TUYHXJ3THCIMUBE73JITLQT","bundle":"https://pith.science/pith/GC3TUYHXJ3THCIMUBE73JITLQT/bundle.json","state":"https://pith.science/pith/GC3TUYHXJ3THCIMUBE73JITLQT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GC3TUYHXJ3THCIMUBE73JITLQT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GC3TUYHXJ3THCIMUBE73JITLQT","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":"4fea2075bcb331f740a7620a515c9f6277b3a4ef0ab3af04b4ce2fe40e0588e7","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T15:24:56Z","title_canon_sha256":"2f7aa8ac83b5ac9faaa58455d4bb5d4c0ed4e93de8f94452933836094096f291"},"schema_version":"1.0","source":{"id":"2506.07861","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.07861","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"arxiv_version","alias_value":"2506.07861v1","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.07861","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_12","alias_value":"GC3TUYHXJ3TH","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_16","alias_value":"GC3TUYHXJ3THCIMU","created_at":"2026-07-05T11:18:34Z"},{"alias_kind":"pith_short_8","alias_value":"GC3TUYHX","created_at":"2026-07-05T11:18:34Z"}],"graph_snapshots":[{"event_id":"sha256:8f5982ac1fd92f5d326e6fd78d742e69a9189b9b8e5c8458dbe0fe8e17acd856","target":"graph","created_at":"2026-07-05T11:18:34Z","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/2506.07861/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite substantial progress in promoting fairness in high-stake applications using machine learning models, existing methods often modify the training process, such as through regularizers or other interventions, but lack formal guarantees that fairness achieved during training will generalize to unseen data. Although overfitting with respect to prediction performance has been extensively studied, overfitting in terms of fairness loss has received far less attention. This paper proposes a theoretical framework for analyzing fairness generalization error through an information-theoretic lens. ","authors_text":"Firas Laakom, Haobo Chen, J\\\"urgen Schmidhuber, Yuheng Bu","cross_cats":["cs.AI","cs.IT","math.IT"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T15:24:56Z","title":"Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.07861","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:a3d785b98ac4be91b2427732a4366f60cb802c187ae5083724d93321f1e9fb6c","target":"record","created_at":"2026-07-05T11:18:34Z","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":"4fea2075bcb331f740a7620a515c9f6277b3a4ef0ab3af04b4ce2fe40e0588e7","cross_cats_sorted":["cs.AI","cs.IT","math.IT"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-09T15:24:56Z","title_canon_sha256":"2f7aa8ac83b5ac9faaa58455d4bb5d4c0ed4e93de8f94452933836094096f291"},"schema_version":"1.0","source":{"id":"2506.07861","kind":"arxiv","version":1}},"canonical_sha256":"30b73a60f74ee6712194093fb4a26b84f20ea1d5d00a6f1f85bdd52b6d681378","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"30b73a60f74ee6712194093fb4a26b84f20ea1d5d00a6f1f85bdd52b6d681378","first_computed_at":"2026-07-05T11:18:34.634230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:18:34.634230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nxAJUdFK31dh6f3k0ANlYCDc5eznV5zWrAn5N72Ai7eS/QH5c6x+np7EQVbsGGc3qtK8Whdu4sdzHDwzTJWFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:18:34.634716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.07861","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3d785b98ac4be91b2427732a4366f60cb802c187ae5083724d93321f1e9fb6c","sha256:8f5982ac1fd92f5d326e6fd78d742e69a9189b9b8e5c8458dbe0fe8e17acd856"],"state_sha256":"e5fc100718b5a0e172b097efab736ed64dff0de1dfae0cf26e3ca408fe062f04"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Kggwan5wwufTSgRfV4ae5kvi3o1rn78h6LTSJC82Egl7Pa4BELMezAJTOmqKzXfxeLWCi6YJSN8/ErVbCGaCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T15:57:56.895781Z","bundle_sha256":"494915331e4d19e2c79d7acf863438b5eca5026546e2138c6919e82f192df6de"}}