{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I2VKVZOEPIK7IC65SS7UVZRBQR","short_pith_number":"pith:I2VKVZOE","schema_version":"1.0","canonical_sha256":"46aaaae5c47a15f40bdd94bf4ae621845cd2c666e35ca609ed217c8f8ad1555b","source":{"kind":"arxiv","id":"2506.00440","version":1},"attestation_state":"computed","paper":{"title":"PSI-PFL: Population Stability Index for Client Selection in non-IID Personalized Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel-M. Jimenez-Gutierrez, David Solans, Mohammed Elbamby, Nicolas Kourtellis","submitted_at":"2025-05-31T07:41:42Z","abstract_excerpt":"Federated Learning (FL) enables decentralized machine learning (ML) model training while preserving data privacy by keeping data localized across clients. However, non-independent and identically distributed (non-IID) data across clients poses a significant challenge, leading to skewed model updates and performance degradation. Addressing this, we propose PSI-PFL, a novel client selection framework for Personalized Federated Learning (PFL) that leverages the Population Stability Index (PSI) to quantify and mitigate data heterogeneity (so-called non-IIDness). Our approach selects more homogeneo"},"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":"2506.00440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-31T07:41:42Z","cross_cats_sorted":[],"title_canon_sha256":"4c826e8bb4a5926629e93f313f0d3edf61e894ff02af3de23de925337312d510","abstract_canon_sha256":"7f0880d34cd41b5122e76814bc12f692372a106997a6f2b84f8275211db666c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:34.801384Z","signature_b64":"ZzALv+IbV0/1I2BG72xJ5E0JYUbgBN8aK+TquAQytP5rDXunBcu+ypPrq1JgC4eirGPSnMM0SaRF2HkeKy/nAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"46aaaae5c47a15f40bdd94bf4ae621845cd2c666e35ca609ed217c8f8ad1555b","last_reissued_at":"2026-07-05T11:13:34.800954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:34.800954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PSI-PFL: Population Stability Index for Client Selection in non-IID Personalized Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel-M. Jimenez-Gutierrez, David Solans, Mohammed Elbamby, Nicolas Kourtellis","submitted_at":"2025-05-31T07:41:42Z","abstract_excerpt":"Federated Learning (FL) enables decentralized machine learning (ML) model training while preserving data privacy by keeping data localized across clients. However, non-independent and identically distributed (non-IID) data across clients poses a significant challenge, leading to skewed model updates and performance degradation. Addressing this, we propose PSI-PFL, a novel client selection framework for Personalized Federated Learning (PFL) that leverages the Population Stability Index (PSI) to quantify and mitigate data heterogeneity (so-called non-IIDness). Our approach selects more homogeneo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00440","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/2506.00440/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":"2506.00440","created_at":"2026-07-05T11:13:34.801013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00440v1","created_at":"2026-07-05T11:13:34.801013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00440","created_at":"2026-07-05T11:13:34.801013+00:00"},{"alias_kind":"pith_short_12","alias_value":"I2VKVZOEPIK7","created_at":"2026-07-05T11:13:34.801013+00:00"},{"alias_kind":"pith_short_16","alias_value":"I2VKVZOEPIK7IC65","created_at":"2026-07-05T11:13:34.801013+00:00"},{"alias_kind":"pith_short_8","alias_value":"I2VKVZOE","created_at":"2026-07-05T11:13:34.801013+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/I2VKVZOEPIK7IC65SS7UVZRBQR","json":"https://pith.science/pith/I2VKVZOEPIK7IC65SS7UVZRBQR.json","graph_json":"https://pith.science/api/pith-number/I2VKVZOEPIK7IC65SS7UVZRBQR/graph.json","events_json":"https://pith.science/api/pith-number/I2VKVZOEPIK7IC65SS7UVZRBQR/events.json","paper":"https://pith.science/paper/I2VKVZOE"},"agent_actions":{"view_html":"https://pith.science/pith/I2VKVZOEPIK7IC65SS7UVZRBQR","download_json":"https://pith.science/pith/I2VKVZOEPIK7IC65SS7UVZRBQR.json","view_paper":"https://pith.science/paper/I2VKVZOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00440&json=true","fetch_graph":"https://pith.science/api/pith-number/I2VKVZOEPIK7IC65SS7UVZRBQR/graph.json","fetch_events":"https://pith.science/api/pith-number/I2VKVZOEPIK7IC65SS7UVZRBQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I2VKVZOEPIK7IC65SS7UVZRBQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I2VKVZOEPIK7IC65SS7UVZRBQR/action/storage_attestation","attest_author":"https://pith.science/pith/I2VKVZOEPIK7IC65SS7UVZRBQR/action/author_attestation","sign_citation":"https://pith.science/pith/I2VKVZOEPIK7IC65SS7UVZRBQR/action/citation_signature","submit_replication":"https://pith.science/pith/I2VKVZOEPIK7IC65SS7UVZRBQR/action/replication_record"}},"created_at":"2026-07-05T11:13:34.801013+00:00","updated_at":"2026-07-05T11:13:34.801013+00:00"}