{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:3ODHRSSLXEXGQOIFZKOCOKV37H","short_pith_number":"pith:3ODHRSSL","schema_version":"1.0","canonical_sha256":"db8678ca4bb92e683905ca9c272abbf9d37b9d5679fe4f2afc50e977bf7dd8b2","source":{"kind":"arxiv","id":"2205.14840","version":2},"attestation_state":"computed","paper":{"title":"Maximizing Global Model Appeal in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Divyansh Jhunjhunwala, Gauri Joshi, Tian Li, Virginia Smith, Yae Jee Cho","submitted_at":"2022-05-30T04:03:31Z","abstract_excerpt":"Federated learning typically considers collaboratively training a global model using local data at edge clients. Clients may have their own individual requirements, such as having a minimal training loss threshold, which they expect to be met by the global model. However, due to client heterogeneity, the global model may not meet each client's requirements, and only a small subset may find the global model appealing. In this work, we explore the problem of the global model lacking appeal to the clients due to not being able to satisfy local requirements. We propose MaxFL, which aims to maximiz"},"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":"2205.14840","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-05-30T04:03:31Z","cross_cats_sorted":[],"title_canon_sha256":"cfe949d726ed7e5a6a2cabd23fa0689943ed8a7cd72cd5598447b71cea5b58eb","abstract_canon_sha256":"43c1be62243017fde7ce12bbefd1753396ba0fa6ffd0393271522486f3df9105"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:42.767232Z","signature_b64":"9uDQLY7eKzwiUA1zjfnaFKWJ1U9XaIQOn8OhNSOs1tn2fr+SdhG4bkhC5HZydgMnrjrO4d0Ikrkvu3Qq2TQTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db8678ca4bb92e683905ca9c272abbf9d37b9d5679fe4f2afc50e977bf7dd8b2","last_reissued_at":"2026-07-05T05:38:42.766821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:42.766821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Maximizing Global Model Appeal in Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Divyansh Jhunjhunwala, Gauri Joshi, Tian Li, Virginia Smith, Yae Jee Cho","submitted_at":"2022-05-30T04:03:31Z","abstract_excerpt":"Federated learning typically considers collaboratively training a global model using local data at edge clients. Clients may have their own individual requirements, such as having a minimal training loss threshold, which they expect to be met by the global model. However, due to client heterogeneity, the global model may not meet each client's requirements, and only a small subset may find the global model appealing. In this work, we explore the problem of the global model lacking appeal to the clients due to not being able to satisfy local requirements. We propose MaxFL, which aims to maximiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14840","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/2205.14840/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":"2205.14840","created_at":"2026-07-05T05:38:42.766880+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14840v2","created_at":"2026-07-05T05:38:42.766880+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14840","created_at":"2026-07-05T05:38:42.766880+00:00"},{"alias_kind":"pith_short_12","alias_value":"3ODHRSSLXEXG","created_at":"2026-07-05T05:38:42.766880+00:00"},{"alias_kind":"pith_short_16","alias_value":"3ODHRSSLXEXGQOIF","created_at":"2026-07-05T05:38:42.766880+00:00"},{"alias_kind":"pith_short_8","alias_value":"3ODHRSSL","created_at":"2026-07-05T05:38:42.766880+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15573","citing_title":"Response-Conditioned Parallel-to-Sequential Orchestration for Multi-Agent Systems","ref_index":74,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3ODHRSSLXEXGQOIFZKOCOKV37H","json":"https://pith.science/pith/3ODHRSSLXEXGQOIFZKOCOKV37H.json","graph_json":"https://pith.science/api/pith-number/3ODHRSSLXEXGQOIFZKOCOKV37H/graph.json","events_json":"https://pith.science/api/pith-number/3ODHRSSLXEXGQOIFZKOCOKV37H/events.json","paper":"https://pith.science/paper/3ODHRSSL"},"agent_actions":{"view_html":"https://pith.science/pith/3ODHRSSLXEXGQOIFZKOCOKV37H","download_json":"https://pith.science/pith/3ODHRSSLXEXGQOIFZKOCOKV37H.json","view_paper":"https://pith.science/paper/3ODHRSSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14840&json=true","fetch_graph":"https://pith.science/api/pith-number/3ODHRSSLXEXGQOIFZKOCOKV37H/graph.json","fetch_events":"https://pith.science/api/pith-number/3ODHRSSLXEXGQOIFZKOCOKV37H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3ODHRSSLXEXGQOIFZKOCOKV37H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3ODHRSSLXEXGQOIFZKOCOKV37H/action/storage_attestation","attest_author":"https://pith.science/pith/3ODHRSSLXEXGQOIFZKOCOKV37H/action/author_attestation","sign_citation":"https://pith.science/pith/3ODHRSSLXEXGQOIFZKOCOKV37H/action/citation_signature","submit_replication":"https://pith.science/pith/3ODHRSSLXEXGQOIFZKOCOKV37H/action/replication_record"}},"created_at":"2026-07-05T05:38:42.766880+00:00","updated_at":"2026-07-05T05:38:42.766880+00:00"}