{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FWU2DX3UM6ZN3VMB2R7SHFTYTJ","short_pith_number":"pith:FWU2DX3U","schema_version":"1.0","canonical_sha256":"2da9a1df7467b2ddd581d47f2396789a7c6f1d73d9eaa630b38ba79026a18f65","source":{"kind":"arxiv","id":"2502.07750","version":2},"attestation_state":"computed","paper":{"title":"PFedDST: Personalized Federated Learning with Decentralized Selection Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Baocheng Geng, Keren Li, Mengchen Fan, Qing Tian, Tianyun Zhang","submitted_at":"2025-02-11T18:25:48Z","abstract_excerpt":"Distributed Learning (DL) enables the training of machine learning models across multiple devices, yet it faces challenges like non-IID data distributions and device capability disparities, which can impede training efficiency. Communication bottlenecks further complicate traditional Federated Learning (FL) setups. To mitigate these issues, we introduce the Personalized Federated Learning with Decentralized Selection Training (PFedDST) framework. PFedDST enhances model training by allowing devices to strategically evaluate and select peers based on a comprehensive communication score. This sco"},"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":"2502.07750","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-02-11T18:25:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ea09f51ef29386b268c3a78199500f32774150d0a00cd076ac918d8f138f88f8","abstract_canon_sha256":"37b67c0426228df97dca5862869f546b7090018680e60d41e93c6ab689ac3834"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:41.686912Z","signature_b64":"qQyg6XwLZSTUX8F8zwpNE0IrYys8zNZ61h3r80DsvKtTiJQhB6C83Yq6Xxm1EjCPyNzq/Bkg/QC8YpO8z4yFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2da9a1df7467b2ddd581d47f2396789a7c6f1d73d9eaa630b38ba79026a18f65","last_reissued_at":"2026-07-05T10:16:41.686370Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:41.686370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PFedDST: Personalized Federated Learning with Decentralized Selection Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Baocheng Geng, Keren Li, Mengchen Fan, Qing Tian, Tianyun Zhang","submitted_at":"2025-02-11T18:25:48Z","abstract_excerpt":"Distributed Learning (DL) enables the training of machine learning models across multiple devices, yet it faces challenges like non-IID data distributions and device capability disparities, which can impede training efficiency. Communication bottlenecks further complicate traditional Federated Learning (FL) setups. To mitigate these issues, we introduce the Personalized Federated Learning with Decentralized Selection Training (PFedDST) framework. PFedDST enhances model training by allowing devices to strategically evaluate and select peers based on a comprehensive communication score. This sco"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07750","kind":"arxiv","version":2},"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/2502.07750/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":"2502.07750","created_at":"2026-07-05T10:16:41.686429+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.07750v2","created_at":"2026-07-05T10:16:41.686429+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07750","created_at":"2026-07-05T10:16:41.686429+00:00"},{"alias_kind":"pith_short_12","alias_value":"FWU2DX3UM6ZN","created_at":"2026-07-05T10:16:41.686429+00:00"},{"alias_kind":"pith_short_16","alias_value":"FWU2DX3UM6ZN3VMB","created_at":"2026-07-05T10:16:41.686429+00:00"},{"alias_kind":"pith_short_8","alias_value":"FWU2DX3U","created_at":"2026-07-05T10:16:41.686429+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.19131","citing_title":"Evidential Trust-Aware Model Personalization in Decentralized Federated Learning for Wearable IoT","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12168","citing_title":"On What We Can Learn from Low-Resolution Data","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05040","citing_title":"Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FWU2DX3UM6ZN3VMB2R7SHFTYTJ","json":"https://pith.science/pith/FWU2DX3UM6ZN3VMB2R7SHFTYTJ.json","graph_json":"https://pith.science/api/pith-number/FWU2DX3UM6ZN3VMB2R7SHFTYTJ/graph.json","events_json":"https://pith.science/api/pith-number/FWU2DX3UM6ZN3VMB2R7SHFTYTJ/events.json","paper":"https://pith.science/paper/FWU2DX3U"},"agent_actions":{"view_html":"https://pith.science/pith/FWU2DX3UM6ZN3VMB2R7SHFTYTJ","download_json":"https://pith.science/pith/FWU2DX3UM6ZN3VMB2R7SHFTYTJ.json","view_paper":"https://pith.science/paper/FWU2DX3U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.07750&json=true","fetch_graph":"https://pith.science/api/pith-number/FWU2DX3UM6ZN3VMB2R7SHFTYTJ/graph.json","fetch_events":"https://pith.science/api/pith-number/FWU2DX3UM6ZN3VMB2R7SHFTYTJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FWU2DX3UM6ZN3VMB2R7SHFTYTJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FWU2DX3UM6ZN3VMB2R7SHFTYTJ/action/storage_attestation","attest_author":"https://pith.science/pith/FWU2DX3UM6ZN3VMB2R7SHFTYTJ/action/author_attestation","sign_citation":"https://pith.science/pith/FWU2DX3UM6ZN3VMB2R7SHFTYTJ/action/citation_signature","submit_replication":"https://pith.science/pith/FWU2DX3UM6ZN3VMB2R7SHFTYTJ/action/replication_record"}},"created_at":"2026-07-05T10:16:41.686429+00:00","updated_at":"2026-07-05T10:16:41.686429+00:00"}