{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P6KWUUWYOLWBDPVOAZV2SQHYJK","short_pith_number":"pith:P6KWUUWY","schema_version":"1.0","canonical_sha256":"7f956a52d872ec11beae066ba940f84a9cb497817129817b023db3da81378d88","source":{"kind":"arxiv","id":"2507.10325","version":1},"attestation_state":"computed","paper":{"title":"Convergence of Agnostic Federated Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","eess.SP"],"primary_cat":"cs.LG","authors_text":"Dionysis Kalogerias, Herlock (SeyedAbolfazl) Rahimi","submitted_at":"2025-07-14T14:32:46Z","abstract_excerpt":"Federated learning (FL) enables decentralized model training without centralizing raw data. However, practical FL deployments often face a key realistic challenge: Clients participate intermittently in server aggregation and with unknown, possibly biased participation probabilities. Most existing convergence results either assume full-device participation, or rely on knowledge of (in fact uniform) client availability distributions -- assumptions that rarely hold in practice. In this work, we characterize the optimization problem that consistently adheres to the stochastic dynamics of the well-"},"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":"2507.10325","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-14T14:32:46Z","cross_cats_sorted":["cs.DC","eess.SP"],"title_canon_sha256":"581932ed59d7d489f053188562832b4362009aa86aa839745f22595f76bfb89c","abstract_canon_sha256":"3baa95234689d60d849ebdd5f354588cce8d1d0bd4db079b3f3cc9ca49a45855"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:49.508331Z","signature_b64":"6PMj/YM+IlRAnojIRIhamW1ySwbxiVsmenNRKze3OqymrwgnJg10i6taDg/JbalxGAwUimkl0PNdSYhI86+jAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f956a52d872ec11beae066ba940f84a9cb497817129817b023db3da81378d88","last_reissued_at":"2026-07-05T11:36:49.507797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:49.507797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence of Agnostic Federated Averaging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DC","eess.SP"],"primary_cat":"cs.LG","authors_text":"Dionysis Kalogerias, Herlock (SeyedAbolfazl) Rahimi","submitted_at":"2025-07-14T14:32:46Z","abstract_excerpt":"Federated learning (FL) enables decentralized model training without centralizing raw data. However, practical FL deployments often face a key realistic challenge: Clients participate intermittently in server aggregation and with unknown, possibly biased participation probabilities. Most existing convergence results either assume full-device participation, or rely on knowledge of (in fact uniform) client availability distributions -- assumptions that rarely hold in practice. In this work, we characterize the optimization problem that consistently adheres to the stochastic dynamics of the well-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10325","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/2507.10325/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":"2507.10325","created_at":"2026-07-05T11:36:49.507867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10325v1","created_at":"2026-07-05T11:36:49.507867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10325","created_at":"2026-07-05T11:36:49.507867+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6KWUUWYOLWB","created_at":"2026-07-05T11:36:49.507867+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6KWUUWYOLWBDPVO","created_at":"2026-07-05T11:36:49.507867+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6KWUUWY","created_at":"2026-07-05T11:36:49.507867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10325","citing_title":"Convergence of Agnostic Federated Averaging","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6KWUUWYOLWBDPVOAZV2SQHYJK","json":"https://pith.science/pith/P6KWUUWYOLWBDPVOAZV2SQHYJK.json","graph_json":"https://pith.science/api/pith-number/P6KWUUWYOLWBDPVOAZV2SQHYJK/graph.json","events_json":"https://pith.science/api/pith-number/P6KWUUWYOLWBDPVOAZV2SQHYJK/events.json","paper":"https://pith.science/paper/P6KWUUWY"},"agent_actions":{"view_html":"https://pith.science/pith/P6KWUUWYOLWBDPVOAZV2SQHYJK","download_json":"https://pith.science/pith/P6KWUUWYOLWBDPVOAZV2SQHYJK.json","view_paper":"https://pith.science/paper/P6KWUUWY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10325&json=true","fetch_graph":"https://pith.science/api/pith-number/P6KWUUWYOLWBDPVOAZV2SQHYJK/graph.json","fetch_events":"https://pith.science/api/pith-number/P6KWUUWYOLWBDPVOAZV2SQHYJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6KWUUWYOLWBDPVOAZV2SQHYJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6KWUUWYOLWBDPVOAZV2SQHYJK/action/storage_attestation","attest_author":"https://pith.science/pith/P6KWUUWYOLWBDPVOAZV2SQHYJK/action/author_attestation","sign_citation":"https://pith.science/pith/P6KWUUWYOLWBDPVOAZV2SQHYJK/action/citation_signature","submit_replication":"https://pith.science/pith/P6KWUUWYOLWBDPVOAZV2SQHYJK/action/replication_record"}},"created_at":"2026-07-05T11:36:49.507867+00:00","updated_at":"2026-07-05T11:36:49.507867+00:00"}