{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KYOGJCWFOJKSDZ5QKBBJXIMBZM","short_pith_number":"pith:KYOGJCWF","schema_version":"1.0","canonical_sha256":"561c648ac5725521e7b050429ba181cb32344f14d387d4ee7230c26cc1ef4e2b","source":{"kind":"arxiv","id":"2506.21036","version":1},"attestation_state":"computed","paper":{"title":"An Information-Theoretic Analysis for Federated Learning under Concept Drift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Fu Peng, Meng Zhang, Ming Tang","submitted_at":"2025-06-26T06:25:15Z","abstract_excerpt":"Recent studies in federated learning (FL) commonly train models on static datasets. However, real-world data often arrives as streams with shifting distributions, causing performance degradation known as concept drift. This paper analyzes FL performance under concept drift using information theory and proposes an algorithm to mitigate the performance degradation. We model concept drift as a Markov chain and introduce the \\emph{Stationary Generalization Error} to assess a model's capability to capture characteristics of future unseen data. Its upper bound is derived using KL divergence and mutu"},"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":"2506.21036","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-26T06:25:15Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"7631265634d9ea09001f5edd66e4e383af58f2dac3f94e410edc9fe015a8e12c","abstract_canon_sha256":"f8763a8d4729fed1850b287c8aa972fb126853819d689d1a4244d39309b26563"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:38.478641Z","signature_b64":"xvl4xNsF6pKkJqWWMd72gaP9A9M00T15nwEPKkE7HGpgLwwnDpR+m1T0s5l4qpbPwP7CS85qqNLZjcBDVcPeDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"561c648ac5725521e7b050429ba181cb32344f14d387d4ee7230c26cc1ef4e2b","last_reissued_at":"2026-07-05T11:27:38.478138Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:38.478138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Information-Theoretic Analysis for Federated Learning under Concept Drift","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Fu Peng, Meng Zhang, Ming Tang","submitted_at":"2025-06-26T06:25:15Z","abstract_excerpt":"Recent studies in federated learning (FL) commonly train models on static datasets. However, real-world data often arrives as streams with shifting distributions, causing performance degradation known as concept drift. This paper analyzes FL performance under concept drift using information theory and proposes an algorithm to mitigate the performance degradation. We model concept drift as a Markov chain and introduce the \\emph{Stationary Generalization Error} to assess a model's capability to capture characteristics of future unseen data. Its upper bound is derived using KL divergence and mutu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21036","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/2506.21036/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":"2506.21036","created_at":"2026-07-05T11:27:38.478193+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21036v1","created_at":"2026-07-05T11:27:38.478193+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21036","created_at":"2026-07-05T11:27:38.478193+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYOGJCWFOJKS","created_at":"2026-07-05T11:27:38.478193+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYOGJCWFOJKSDZ5Q","created_at":"2026-07-05T11:27:38.478193+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYOGJCWF","created_at":"2026-07-05T11:27:38.478193+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/KYOGJCWFOJKSDZ5QKBBJXIMBZM","json":"https://pith.science/pith/KYOGJCWFOJKSDZ5QKBBJXIMBZM.json","graph_json":"https://pith.science/api/pith-number/KYOGJCWFOJKSDZ5QKBBJXIMBZM/graph.json","events_json":"https://pith.science/api/pith-number/KYOGJCWFOJKSDZ5QKBBJXIMBZM/events.json","paper":"https://pith.science/paper/KYOGJCWF"},"agent_actions":{"view_html":"https://pith.science/pith/KYOGJCWFOJKSDZ5QKBBJXIMBZM","download_json":"https://pith.science/pith/KYOGJCWFOJKSDZ5QKBBJXIMBZM.json","view_paper":"https://pith.science/paper/KYOGJCWF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21036&json=true","fetch_graph":"https://pith.science/api/pith-number/KYOGJCWFOJKSDZ5QKBBJXIMBZM/graph.json","fetch_events":"https://pith.science/api/pith-number/KYOGJCWFOJKSDZ5QKBBJXIMBZM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYOGJCWFOJKSDZ5QKBBJXIMBZM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYOGJCWFOJKSDZ5QKBBJXIMBZM/action/storage_attestation","attest_author":"https://pith.science/pith/KYOGJCWFOJKSDZ5QKBBJXIMBZM/action/author_attestation","sign_citation":"https://pith.science/pith/KYOGJCWFOJKSDZ5QKBBJXIMBZM/action/citation_signature","submit_replication":"https://pith.science/pith/KYOGJCWFOJKSDZ5QKBBJXIMBZM/action/replication_record"}},"created_at":"2026-07-05T11:27:38.478193+00:00","updated_at":"2026-07-05T11:27:38.478193+00:00"}