{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IURVOLR2GUGCMMOF52PUAWKB5U","short_pith_number":"pith:IURVOLR2","schema_version":"1.0","canonical_sha256":"4523572e3a350c2631c5ee9f405941ed29e9788e82ec350c2e90a7a4ed7780e2","source":{"kind":"arxiv","id":"2312.17430","version":2},"attestation_state":"computed","paper":{"title":"LEFL: Low Entropy Client Sampling in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Jannesari, Pablo Munoz, Waqwoya Abebe","submitted_at":"2023-12-29T01:44:20Z","abstract_excerpt":"Federated learning (FL) is a machine learning paradigm where multiple clients collaborate to optimize a single global model using their private data. The global model is maintained by a central server that orchestrates the FL training process through a series of training rounds. In each round, the server samples clients from a client pool before sending them its latest global model parameters for further optimization. Naive sampling strategies implement random client sampling and fail to factor client data distributions for privacy reasons. Hence we propose LEFL, an alternative sampling strate"},"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":"2312.17430","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-12-29T01:44:20Z","cross_cats_sorted":[],"title_canon_sha256":"cdadc30d6f4ab36a2875ad46c57be9a963ca315d32dc4b1caedce7eed3b9ec3e","abstract_canon_sha256":"173ed7e0a8901a177a7ae3e354edbd20ae7bbc38af6ae06506eefe627b10b332"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:22.234693Z","signature_b64":"aBLgugzp8SLdZd47zE09B4r/wQ6DsXggycuCzQMw30nW0En29CpYNVy/mnEksQwnW0xer5d8EhS6O2cVyXF/DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4523572e3a350c2631c5ee9f405941ed29e9788e82ec350c2e90a7a4ed7780e2","last_reissued_at":"2026-07-05T07:44:22.234174Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:22.234174Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LEFL: Low Entropy Client Sampling in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ali Jannesari, Pablo Munoz, Waqwoya Abebe","submitted_at":"2023-12-29T01:44:20Z","abstract_excerpt":"Federated learning (FL) is a machine learning paradigm where multiple clients collaborate to optimize a single global model using their private data. The global model is maintained by a central server that orchestrates the FL training process through a series of training rounds. In each round, the server samples clients from a client pool before sending them its latest global model parameters for further optimization. Naive sampling strategies implement random client sampling and fail to factor client data distributions for privacy reasons. Hence we propose LEFL, an alternative sampling strate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17430","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/2312.17430/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":"2312.17430","created_at":"2026-07-05T07:44:22.234228+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.17430v2","created_at":"2026-07-05T07:44:22.234228+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17430","created_at":"2026-07-05T07:44:22.234228+00:00"},{"alias_kind":"pith_short_12","alias_value":"IURVOLR2GUGC","created_at":"2026-07-05T07:44:22.234228+00:00"},{"alias_kind":"pith_short_16","alias_value":"IURVOLR2GUGCMMOF","created_at":"2026-07-05T07:44:22.234228+00:00"},{"alias_kind":"pith_short_8","alias_value":"IURVOLR2","created_at":"2026-07-05T07:44:22.234228+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.02887","citing_title":"Overcoming Challenges of Partial Client Participation in Federated Learning : A Comprehensive Review","ref_index":2023,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IURVOLR2GUGCMMOF52PUAWKB5U","json":"https://pith.science/pith/IURVOLR2GUGCMMOF52PUAWKB5U.json","graph_json":"https://pith.science/api/pith-number/IURVOLR2GUGCMMOF52PUAWKB5U/graph.json","events_json":"https://pith.science/api/pith-number/IURVOLR2GUGCMMOF52PUAWKB5U/events.json","paper":"https://pith.science/paper/IURVOLR2"},"agent_actions":{"view_html":"https://pith.science/pith/IURVOLR2GUGCMMOF52PUAWKB5U","download_json":"https://pith.science/pith/IURVOLR2GUGCMMOF52PUAWKB5U.json","view_paper":"https://pith.science/paper/IURVOLR2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.17430&json=true","fetch_graph":"https://pith.science/api/pith-number/IURVOLR2GUGCMMOF52PUAWKB5U/graph.json","fetch_events":"https://pith.science/api/pith-number/IURVOLR2GUGCMMOF52PUAWKB5U/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IURVOLR2GUGCMMOF52PUAWKB5U/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IURVOLR2GUGCMMOF52PUAWKB5U/action/storage_attestation","attest_author":"https://pith.science/pith/IURVOLR2GUGCMMOF52PUAWKB5U/action/author_attestation","sign_citation":"https://pith.science/pith/IURVOLR2GUGCMMOF52PUAWKB5U/action/citation_signature","submit_replication":"https://pith.science/pith/IURVOLR2GUGCMMOF52PUAWKB5U/action/replication_record"}},"created_at":"2026-07-05T07:44:22.234228+00:00","updated_at":"2026-07-05T07:44:22.234228+00:00"}