{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XGLQUF3GASCV7URD4VP2EQA6NW","short_pith_number":"pith:XGLQUF3G","schema_version":"1.0","canonical_sha256":"b9970a176604855fd223e55fa2401e6da29fd10a36ee7fb2b94ca7a3c6dc7002","source":{"kind":"arxiv","id":"2311.06917","version":1},"attestation_state":"computed","paper":{"title":"FLASH-RL: Federated Learning Addressing System and Static Heterogeneity using Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Hadjer Benmeziane, Hamza Ouarnoughi, Leila Hamdad, Smail Niar, Sofiane Bouaziz, Youcef Imine","submitted_at":"2023-11-12T18:21:00Z","abstract_excerpt":"Federated Learning (FL) has emerged as a promising Machine Learning paradigm, enabling multiple users to collaboratively train a shared model while preserving their local data. To minimize computing and communication costs associated with parameter transfer, it is common practice in FL to select a subset of clients in each training round. This selection must consider both system and static heterogeneity. Therefore, we propose FLASH-RL, a framework that utilizes Double Deep QLearning (DDQL) to address both system and static heterogeneity in FL. FLASH-RL introduces a new reputation-based utility"},"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":"2311.06917","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-12T18:21:00Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"a585b65e29b959426442aa2022b6d64393afc245991f0804d3f379a88e883ca2","abstract_canon_sha256":"ad269a077c61e196971771eaabbb7e3cd3b934f7653c0ac65104e4247927a229"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:12:05.439230Z","signature_b64":"hwHAuF6PemR1uBq03wH1rCxbDhsK4vfs0y2wRbqLqeJ/2zZnhXE6sPMEKXdOoEi/y6CJgoH8IY0CfUN7uPvZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9970a176604855fd223e55fa2401e6da29fd10a36ee7fb2b94ca7a3c6dc7002","last_reissued_at":"2026-07-05T07:12:05.438768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:12:05.438768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLASH-RL: Federated Learning Addressing System and Static Heterogeneity using Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Hadjer Benmeziane, Hamza Ouarnoughi, Leila Hamdad, Smail Niar, Sofiane Bouaziz, Youcef Imine","submitted_at":"2023-11-12T18:21:00Z","abstract_excerpt":"Federated Learning (FL) has emerged as a promising Machine Learning paradigm, enabling multiple users to collaboratively train a shared model while preserving their local data. To minimize computing and communication costs associated with parameter transfer, it is common practice in FL to select a subset of clients in each training round. This selection must consider both system and static heterogeneity. Therefore, we propose FLASH-RL, a framework that utilizes Double Deep QLearning (DDQL) to address both system and static heterogeneity in FL. FLASH-RL introduces a new reputation-based utility"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06917","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/2311.06917/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":"2311.06917","created_at":"2026-07-05T07:12:05.438823+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06917v1","created_at":"2026-07-05T07:12:05.438823+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06917","created_at":"2026-07-05T07:12:05.438823+00:00"},{"alias_kind":"pith_short_12","alias_value":"XGLQUF3GASCV","created_at":"2026-07-05T07:12:05.438823+00:00"},{"alias_kind":"pith_short_16","alias_value":"XGLQUF3GASCV7URD","created_at":"2026-07-05T07:12:05.438823+00:00"},{"alias_kind":"pith_short_8","alias_value":"XGLQUF3G","created_at":"2026-07-05T07:12:05.438823+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/XGLQUF3GASCV7URD4VP2EQA6NW","json":"https://pith.science/pith/XGLQUF3GASCV7URD4VP2EQA6NW.json","graph_json":"https://pith.science/api/pith-number/XGLQUF3GASCV7URD4VP2EQA6NW/graph.json","events_json":"https://pith.science/api/pith-number/XGLQUF3GASCV7URD4VP2EQA6NW/events.json","paper":"https://pith.science/paper/XGLQUF3G"},"agent_actions":{"view_html":"https://pith.science/pith/XGLQUF3GASCV7URD4VP2EQA6NW","download_json":"https://pith.science/pith/XGLQUF3GASCV7URD4VP2EQA6NW.json","view_paper":"https://pith.science/paper/XGLQUF3G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06917&json=true","fetch_graph":"https://pith.science/api/pith-number/XGLQUF3GASCV7URD4VP2EQA6NW/graph.json","fetch_events":"https://pith.science/api/pith-number/XGLQUF3GASCV7URD4VP2EQA6NW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XGLQUF3GASCV7URD4VP2EQA6NW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XGLQUF3GASCV7URD4VP2EQA6NW/action/storage_attestation","attest_author":"https://pith.science/pith/XGLQUF3GASCV7URD4VP2EQA6NW/action/author_attestation","sign_citation":"https://pith.science/pith/XGLQUF3GASCV7URD4VP2EQA6NW/action/citation_signature","submit_replication":"https://pith.science/pith/XGLQUF3GASCV7URD4VP2EQA6NW/action/replication_record"}},"created_at":"2026-07-05T07:12:05.438823+00:00","updated_at":"2026-07-05T07:12:05.438823+00:00"}