{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U3LG5OCAWIC4VAUMN2GMTOVGQJ","short_pith_number":"pith:U3LG5OCA","schema_version":"1.0","canonical_sha256":"a6d66eb840b205ca828c6e8cc9baa6827ac3f870e5452061bdbe7436d990b338","source":{"kind":"arxiv","id":"2506.09824","version":3},"attestation_state":"computed","paper":{"title":"A Weighted Loss Approach to Robust Federated Learning under Data Heterogeneity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Diana Nurbakova, Elod Egyed-Zsigmond, Johan Erbani, Pierre-Edouard Portier, Sonia Ben Mokhtar","submitted_at":"2025-06-11T15:04:43Z","abstract_excerpt":"Federated learning (FL) is a machine learning paradigm that enables multiple data holders to collaboratively train a machine learning model without sharing their training data with external parties. In this paradigm, workers locally update a model and share with a central server their updated gradients (or model parameters). While FL seems appealing from a privacy perspective, it opens a number of threats from a security perspective as (Byzantine) participants can contribute poisonous gradients (or model parameters) harming model convergence. Byzantine-resilient FL addresses this issue by ensu"},"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":"2506.09824","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-06-11T15:04:43Z","cross_cats_sorted":[],"title_canon_sha256":"4c2bc9c202642b5c8fa51a4f3090c0e6f8fb8bcaa93007e49f713c8b1808d407","abstract_canon_sha256":"f081fb4c582087e5ef4bf61f8c19bc70078940cc77a5061cafdca8d32e06729c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:17.580308Z","signature_b64":"xVPl5E3nomd6NZGIJGKsUL3pn3ebJGWYMfqwPVvqUp11CZKrmnBsuHQAVFffQlTGeBWzyhheP1BssIgtpOEMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a6d66eb840b205ca828c6e8cc9baa6827ac3f870e5452061bdbe7436d990b338","last_reissued_at":"2026-07-05T12:05:17.579787Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:17.579787Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Weighted Loss Approach to Robust Federated Learning under Data Heterogeneity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Diana Nurbakova, Elod Egyed-Zsigmond, Johan Erbani, Pierre-Edouard Portier, Sonia Ben Mokhtar","submitted_at":"2025-06-11T15:04:43Z","abstract_excerpt":"Federated learning (FL) is a machine learning paradigm that enables multiple data holders to collaboratively train a machine learning model without sharing their training data with external parties. In this paradigm, workers locally update a model and share with a central server their updated gradients (or model parameters). While FL seems appealing from a privacy perspective, it opens a number of threats from a security perspective as (Byzantine) participants can contribute poisonous gradients (or model parameters) harming model convergence. Byzantine-resilient FL addresses this issue by ensu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09824","kind":"arxiv","version":3},"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/2506.09824/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":"2506.09824","created_at":"2026-07-05T12:05:17.579853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09824v3","created_at":"2026-07-05T12:05:17.579853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09824","created_at":"2026-07-05T12:05:17.579853+00:00"},{"alias_kind":"pith_short_12","alias_value":"U3LG5OCAWIC4","created_at":"2026-07-05T12:05:17.579853+00:00"},{"alias_kind":"pith_short_16","alias_value":"U3LG5OCAWIC4VAUM","created_at":"2026-07-05T12:05:17.579853+00:00"},{"alias_kind":"pith_short_8","alias_value":"U3LG5OCA","created_at":"2026-07-05T12:05:17.579853+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/U3LG5OCAWIC4VAUMN2GMTOVGQJ","json":"https://pith.science/pith/U3LG5OCAWIC4VAUMN2GMTOVGQJ.json","graph_json":"https://pith.science/api/pith-number/U3LG5OCAWIC4VAUMN2GMTOVGQJ/graph.json","events_json":"https://pith.science/api/pith-number/U3LG5OCAWIC4VAUMN2GMTOVGQJ/events.json","paper":"https://pith.science/paper/U3LG5OCA"},"agent_actions":{"view_html":"https://pith.science/pith/U3LG5OCAWIC4VAUMN2GMTOVGQJ","download_json":"https://pith.science/pith/U3LG5OCAWIC4VAUMN2GMTOVGQJ.json","view_paper":"https://pith.science/paper/U3LG5OCA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09824&json=true","fetch_graph":"https://pith.science/api/pith-number/U3LG5OCAWIC4VAUMN2GMTOVGQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/U3LG5OCAWIC4VAUMN2GMTOVGQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U3LG5OCAWIC4VAUMN2GMTOVGQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U3LG5OCAWIC4VAUMN2GMTOVGQJ/action/storage_attestation","attest_author":"https://pith.science/pith/U3LG5OCAWIC4VAUMN2GMTOVGQJ/action/author_attestation","sign_citation":"https://pith.science/pith/U3LG5OCAWIC4VAUMN2GMTOVGQJ/action/citation_signature","submit_replication":"https://pith.science/pith/U3LG5OCAWIC4VAUMN2GMTOVGQJ/action/replication_record"}},"created_at":"2026-07-05T12:05:17.579853+00:00","updated_at":"2026-07-05T12:05:17.579853+00:00"}