{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CPMMQ2WGJS7FIE4K2MC2EUJYZP","short_pith_number":"pith:CPMMQ2WG","schema_version":"1.0","canonical_sha256":"13d8c86ac64cbe54138ad305a25138cbf24c7dc3845344b9d1c6287032816419","source":{"kind":"arxiv","id":"2507.05852","version":1},"attestation_state":"computed","paper":{"title":"Prototype-Guided and Lightweight Adapters for Inherent Interpretation and Generalisation in Federated Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kerol Djoumessi, Philipp Berens, Samuel Ofosu Mensah","submitted_at":"2025-07-08T10:30:08Z","abstract_excerpt":"Federated learning (FL) provides a promising paradigm for collaboratively training machine learning models across distributed data sources while maintaining privacy. Nevertheless, real-world FL often faces major challenges including communication overhead during the transfer of large model parameters and statistical heterogeneity, arising from non-identical independent data distributions across clients. In this work, we propose an FL framework that 1) provides inherent interpretations using prototypes, and 2) tackles statistical heterogeneity by utilising lightweight adapter modules to act as "},"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":"2507.05852","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-08T10:30:08Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3b352c6e901b80ccbcf35cad25bfba61c3e3a1478d5c3ede3e1a40dc766b2b80","abstract_canon_sha256":"835f82d3ff51ffd195b971cb1577b5f20ab2f43ca01517ee1a02312384553d70"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:37.206405Z","signature_b64":"MBsvi/qDS2SXQp10REPGpQDWxvN98DAEyKDN7CMQ0JtiqljNLnLRVQtnGsbmILgabI48RxobTsLAyEr5u+E+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"13d8c86ac64cbe54138ad305a25138cbf24c7dc3845344b9d1c6287032816419","last_reissued_at":"2026-07-05T11:33:37.205988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:37.205988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prototype-Guided and Lightweight Adapters for Inherent Interpretation and Generalisation in Federated Learning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Kerol Djoumessi, Philipp Berens, Samuel Ofosu Mensah","submitted_at":"2025-07-08T10:30:08Z","abstract_excerpt":"Federated learning (FL) provides a promising paradigm for collaboratively training machine learning models across distributed data sources while maintaining privacy. Nevertheless, real-world FL often faces major challenges including communication overhead during the transfer of large model parameters and statistical heterogeneity, arising from non-identical independent data distributions across clients. In this work, we propose an FL framework that 1) provides inherent interpretations using prototypes, and 2) tackles statistical heterogeneity by utilising lightweight adapter modules to act as "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05852","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/2507.05852/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":"2507.05852","created_at":"2026-07-05T11:33:37.206046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05852v1","created_at":"2026-07-05T11:33:37.206046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05852","created_at":"2026-07-05T11:33:37.206046+00:00"},{"alias_kind":"pith_short_12","alias_value":"CPMMQ2WGJS7F","created_at":"2026-07-05T11:33:37.206046+00:00"},{"alias_kind":"pith_short_16","alias_value":"CPMMQ2WGJS7FIE4K","created_at":"2026-07-05T11:33:37.206046+00:00"},{"alias_kind":"pith_short_8","alias_value":"CPMMQ2WG","created_at":"2026-07-05T11:33:37.206046+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/CPMMQ2WGJS7FIE4K2MC2EUJYZP","json":"https://pith.science/pith/CPMMQ2WGJS7FIE4K2MC2EUJYZP.json","graph_json":"https://pith.science/api/pith-number/CPMMQ2WGJS7FIE4K2MC2EUJYZP/graph.json","events_json":"https://pith.science/api/pith-number/CPMMQ2WGJS7FIE4K2MC2EUJYZP/events.json","paper":"https://pith.science/paper/CPMMQ2WG"},"agent_actions":{"view_html":"https://pith.science/pith/CPMMQ2WGJS7FIE4K2MC2EUJYZP","download_json":"https://pith.science/pith/CPMMQ2WGJS7FIE4K2MC2EUJYZP.json","view_paper":"https://pith.science/paper/CPMMQ2WG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05852&json=true","fetch_graph":"https://pith.science/api/pith-number/CPMMQ2WGJS7FIE4K2MC2EUJYZP/graph.json","fetch_events":"https://pith.science/api/pith-number/CPMMQ2WGJS7FIE4K2MC2EUJYZP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CPMMQ2WGJS7FIE4K2MC2EUJYZP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CPMMQ2WGJS7FIE4K2MC2EUJYZP/action/storage_attestation","attest_author":"https://pith.science/pith/CPMMQ2WGJS7FIE4K2MC2EUJYZP/action/author_attestation","sign_citation":"https://pith.science/pith/CPMMQ2WGJS7FIE4K2MC2EUJYZP/action/citation_signature","submit_replication":"https://pith.science/pith/CPMMQ2WGJS7FIE4K2MC2EUJYZP/action/replication_record"}},"created_at":"2026-07-05T11:33:37.206046+00:00","updated_at":"2026-07-05T11:33:37.206046+00:00"}