{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6BB5CQQIFHO45MEOEEPN3WAYC6","short_pith_number":"pith:6BB5CQQI","schema_version":"1.0","canonical_sha256":"f043d1420829ddceb08e211eddd81817a17ea1848b5d0ce752885c0280d39e4a","source":{"kind":"arxiv","id":"2508.18060","version":1},"attestation_state":"computed","paper":{"title":"FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonios Makris, Dusan Jakovetic, Emmanouil Kritharakis, Konstantinos Tserpes","submitted_at":"2025-08-25T14:20:19Z","abstract_excerpt":"Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy by keeping local datasets on-device. In this work, we address FL settings where clients may behave adversarially, exhibiting Byzantine attacks, while the central server is trusted and equipped with a reference dataset. We propose FedGreed, a resilient aggregation strategy for federated learning that does not require any assumptions about the fraction of adversarial participants. FedGreed orders clients' local model updates based on their loss metrics evaluated against a trusted da"},"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":"2508.18060","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-25T14:20:19Z","cross_cats_sorted":[],"title_canon_sha256":"3b7ae0c17e7ca90cb528fa73a19e73f6f2f85b3d080c5a172ed7ee555957c118","abstract_canon_sha256":"a9c7f4ea008bcc56b0a69142b717a6ed026c6c03a7f0cbe7093ab11b1916c2fd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:52.930028Z","signature_b64":"5oAjmgGy7d2hmzQmDHfYA517Qn5WQTwI5D/YnQUyE2ASn1zSoJFLPglP0HgZoEaQq91q698A3IK3x79H7zz9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f043d1420829ddceb08e211eddd81817a17ea1848b5d0ce752885c0280d39e4a","last_reissued_at":"2026-07-05T11:58:52.929570Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:52.929570Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FedGreed: A Byzantine-Robust Loss-Based Aggregation Method for Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Antonios Makris, Dusan Jakovetic, Emmanouil Kritharakis, Konstantinos Tserpes","submitted_at":"2025-08-25T14:20:19Z","abstract_excerpt":"Federated Learning (FL) enables collaborative model training across multiple clients while preserving data privacy by keeping local datasets on-device. In this work, we address FL settings where clients may behave adversarially, exhibiting Byzantine attacks, while the central server is trusted and equipped with a reference dataset. We propose FedGreed, a resilient aggregation strategy for federated learning that does not require any assumptions about the fraction of adversarial participants. FedGreed orders clients' local model updates based on their loss metrics evaluated against a trusted da"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18060","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/2508.18060/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":"2508.18060","created_at":"2026-07-05T11:58:52.929636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18060v1","created_at":"2026-07-05T11:58:52.929636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18060","created_at":"2026-07-05T11:58:52.929636+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BB5CQQIFHO4","created_at":"2026-07-05T11:58:52.929636+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BB5CQQIFHO45MEO","created_at":"2026-07-05T11:58:52.929636+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BB5CQQI","created_at":"2026-07-05T11:58:52.929636+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/6BB5CQQIFHO45MEOEEPN3WAYC6","json":"https://pith.science/pith/6BB5CQQIFHO45MEOEEPN3WAYC6.json","graph_json":"https://pith.science/api/pith-number/6BB5CQQIFHO45MEOEEPN3WAYC6/graph.json","events_json":"https://pith.science/api/pith-number/6BB5CQQIFHO45MEOEEPN3WAYC6/events.json","paper":"https://pith.science/paper/6BB5CQQI"},"agent_actions":{"view_html":"https://pith.science/pith/6BB5CQQIFHO45MEOEEPN3WAYC6","download_json":"https://pith.science/pith/6BB5CQQIFHO45MEOEEPN3WAYC6.json","view_paper":"https://pith.science/paper/6BB5CQQI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18060&json=true","fetch_graph":"https://pith.science/api/pith-number/6BB5CQQIFHO45MEOEEPN3WAYC6/graph.json","fetch_events":"https://pith.science/api/pith-number/6BB5CQQIFHO45MEOEEPN3WAYC6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BB5CQQIFHO45MEOEEPN3WAYC6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BB5CQQIFHO45MEOEEPN3WAYC6/action/storage_attestation","attest_author":"https://pith.science/pith/6BB5CQQIFHO45MEOEEPN3WAYC6/action/author_attestation","sign_citation":"https://pith.science/pith/6BB5CQQIFHO45MEOEEPN3WAYC6/action/citation_signature","submit_replication":"https://pith.science/pith/6BB5CQQIFHO45MEOEEPN3WAYC6/action/replication_record"}},"created_at":"2026-07-05T11:58:52.929636+00:00","updated_at":"2026-07-05T11:58:52.929636+00:00"}