{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AACFGT2TEHFPHGDGD7BNXD2A4Y","short_pith_number":"pith:AACFGT2T","schema_version":"1.0","canonical_sha256":"0004534f5321caf398661fc2db8f40e612927fd5e681a721c37237ec10dd8233","source":{"kind":"arxiv","id":"2503.10218","version":1},"attestation_state":"computed","paper":{"title":"Moss: Proxy Model-based Full-Weight Aggregation in Federated Learning with Heterogeneous Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Ding Li, Xiangqun Chen, Yao Guo, Yifeng Cai, Ziqi Zhang","submitted_at":"2025-03-13T10:00:58Z","abstract_excerpt":"Modern Federated Learning (FL) has become increasingly essential for handling highly heterogeneous mobile devices. Current approaches adopt a partial model aggregation paradigm that leads to sub-optimal model accuracy and higher training overhead. In this paper, we challenge the prevailing notion of partial-model aggregation and propose a novel \"full-weight aggregation\" method named Moss, which aggregates all weights within heterogeneous models to preserve comprehensive knowledge. Evaluation across various applications demonstrates that Moss significantly accelerates training, reduces on-devic"},"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":"2503.10218","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-13T10:00:58Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"a65bf83e956ed77582d22b72c058030165a2cd4c1623fe3f6bb958238e2bbf06","abstract_canon_sha256":"9a6fa045327e3d6fce43344b5138fc7508b798e2fe3a58508086cf463ce20a92"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:40.691271Z","signature_b64":"Byj5QdLJGYxkQFGoOY3lBAxbhQARf88HGLNuGuvs0lMxOQLvoDl8wpQKaQfOMxnqvFwZJuRrgP4X2ImhJ9E4BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0004534f5321caf398661fc2db8f40e612927fd5e681a721c37237ec10dd8233","last_reissued_at":"2026-07-05T10:30:40.690248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:40.690248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Moss: Proxy Model-based Full-Weight Aggregation in Federated Learning with Heterogeneous Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Ding Li, Xiangqun Chen, Yao Guo, Yifeng Cai, Ziqi Zhang","submitted_at":"2025-03-13T10:00:58Z","abstract_excerpt":"Modern Federated Learning (FL) has become increasingly essential for handling highly heterogeneous mobile devices. Current approaches adopt a partial model aggregation paradigm that leads to sub-optimal model accuracy and higher training overhead. In this paper, we challenge the prevailing notion of partial-model aggregation and propose a novel \"full-weight aggregation\" method named Moss, which aggregates all weights within heterogeneous models to preserve comprehensive knowledge. Evaluation across various applications demonstrates that Moss significantly accelerates training, reduces on-devic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.10218","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/2503.10218/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":"2503.10218","created_at":"2026-07-05T10:30:40.690416+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.10218v1","created_at":"2026-07-05T10:30:40.690416+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.10218","created_at":"2026-07-05T10:30:40.690416+00:00"},{"alias_kind":"pith_short_12","alias_value":"AACFGT2TEHFP","created_at":"2026-07-05T10:30:40.690416+00:00"},{"alias_kind":"pith_short_16","alias_value":"AACFGT2TEHFPHGDG","created_at":"2026-07-05T10:30:40.690416+00:00"},{"alias_kind":"pith_short_8","alias_value":"AACFGT2T","created_at":"2026-07-05T10:30:40.690416+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/AACFGT2TEHFPHGDGD7BNXD2A4Y","json":"https://pith.science/pith/AACFGT2TEHFPHGDGD7BNXD2A4Y.json","graph_json":"https://pith.science/api/pith-number/AACFGT2TEHFPHGDGD7BNXD2A4Y/graph.json","events_json":"https://pith.science/api/pith-number/AACFGT2TEHFPHGDGD7BNXD2A4Y/events.json","paper":"https://pith.science/paper/AACFGT2T"},"agent_actions":{"view_html":"https://pith.science/pith/AACFGT2TEHFPHGDGD7BNXD2A4Y","download_json":"https://pith.science/pith/AACFGT2TEHFPHGDGD7BNXD2A4Y.json","view_paper":"https://pith.science/paper/AACFGT2T","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.10218&json=true","fetch_graph":"https://pith.science/api/pith-number/AACFGT2TEHFPHGDGD7BNXD2A4Y/graph.json","fetch_events":"https://pith.science/api/pith-number/AACFGT2TEHFPHGDGD7BNXD2A4Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AACFGT2TEHFPHGDGD7BNXD2A4Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AACFGT2TEHFPHGDGD7BNXD2A4Y/action/storage_attestation","attest_author":"https://pith.science/pith/AACFGT2TEHFPHGDGD7BNXD2A4Y/action/author_attestation","sign_citation":"https://pith.science/pith/AACFGT2TEHFPHGDGD7BNXD2A4Y/action/citation_signature","submit_replication":"https://pith.science/pith/AACFGT2TEHFPHGDGD7BNXD2A4Y/action/replication_record"}},"created_at":"2026-07-05T10:30:40.690416+00:00","updated_at":"2026-07-05T10:30:40.690416+00:00"}