{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:6A4GPJWOH7VOTZ7UUGD55TPBO3","short_pith_number":"pith:6A4GPJWO","canonical_record":{"source":{"id":"2502.03340","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T16:33:36Z","cross_cats_sorted":[],"title_canon_sha256":"f52c73ac9bb74355f3ffdad780497ebed564b6a3eb42892dfa3f3b044c8f9d01","abstract_canon_sha256":"c6c67d40f553da38cf0faa6f7a4603fe26ef39681544660c38a9352d1aa8e8a9"},"schema_version":"1.0"},"canonical_sha256":"f03867a6ce3feae9e7f4a187decde176e819ef59fac2a3c6ba5e8359323fff0f","source":{"kind":"arxiv","id":"2502.03340","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03340","created_at":"2026-07-05T10:57:33Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03340v2","created_at":"2026-07-05T10:57:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03340","created_at":"2026-07-05T10:57:33Z"},{"alias_kind":"pith_short_12","alias_value":"6A4GPJWOH7VO","created_at":"2026-07-05T10:57:33Z"},{"alias_kind":"pith_short_16","alias_value":"6A4GPJWOH7VOTZ7U","created_at":"2026-07-05T10:57:33Z"},{"alias_kind":"pith_short_8","alias_value":"6A4GPJWO","created_at":"2026-07-05T10:57:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:6A4GPJWOH7VOTZ7UUGD55TPBO3","target":"record","payload":{"canonical_record":{"source":{"id":"2502.03340","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T16:33:36Z","cross_cats_sorted":[],"title_canon_sha256":"f52c73ac9bb74355f3ffdad780497ebed564b6a3eb42892dfa3f3b044c8f9d01","abstract_canon_sha256":"c6c67d40f553da38cf0faa6f7a4603fe26ef39681544660c38a9352d1aa8e8a9"},"schema_version":"1.0"},"canonical_sha256":"f03867a6ce3feae9e7f4a187decde176e819ef59fac2a3c6ba5e8359323fff0f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:33.514546Z","signature_b64":"i1UQ1ai6rpMhce3ghUQEbispiks+O1CbaQIkTzrQyok7+X677K3G6ebEOuNe3TJkv5s8LNfCAoB5RNQh6005Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f03867a6ce3feae9e7f4a187decde176e819ef59fac2a3c6ba5e8359323fff0f","last_reissued_at":"2026-07-05T10:57:33.514039Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:33.514039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.03340","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:57:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GjYbIqkwrgKp8wRDMk/ZaB5rlanjFL9mRc31YinwKGoJoo945MVPrsz47060FqYxcgtaOXz65M45yAMEzh3rBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T11:31:40.511974Z"},"content_sha256":"ec4e9011424a9a61bc31c6a2c390d789730b4ebd1eb42fbf803086238bc0d62f","schema_version":"1.0","event_id":"sha256:ec4e9011424a9a61bc31c6a2c390d789730b4ebd1eb42fbf803086238bc0d62f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:6A4GPJWOH7VOTZ7UUGD55TPBO3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Interaction-Aware Gaussian Weighting for Clustered Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alessandro Licciardi, Barbara Caputo, Davide Leo, Eros Fan\\`i, Marco Ciccone","submitted_at":"2025-02-05T16:33:36Z","abstract_excerpt":"Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy. However, conventional FL struggles with data heterogeneity and class imbalance, which degrade model performance. Clustered FL balances personalization and decentralized training by grouping clients with analogous data distributions, enabling improved accuracy while adhering to privacy constraints. This approach effectively mitigates the adverse impact of heterogeneity in FL. In this work, we propose a novel clustered FL method, FedGWC (Federated Gaussian Weighting Clustering), which groups cli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03340","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/2502.03340/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:57:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O2RSPEYOAIJv0RWgFn0uZaXih7vmxsAyJEsx6wuJ1J78tIYhyAGxpvuwMna5+ggDT7wALcP/6PWngvjp2ZO+Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T11:31:40.512358Z"},"content_sha256":"6b81d07a48744e7c88e32ad5b4940403009a2a38d2a9ad0277a4e6b8a135c529","schema_version":"1.0","event_id":"sha256:6b81d07a48744e7c88e32ad5b4940403009a2a38d2a9ad0277a4e6b8a135c529"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6A4GPJWOH7VOTZ7UUGD55TPBO3/bundle.json","state_url":"https://pith.science/pith/6A4GPJWOH7VOTZ7UUGD55TPBO3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6A4GPJWOH7VOTZ7UUGD55TPBO3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-24T11:31:40Z","links":{"resolver":"https://pith.science/pith/6A4GPJWOH7VOTZ7UUGD55TPBO3","bundle":"https://pith.science/pith/6A4GPJWOH7VOTZ7UUGD55TPBO3/bundle.json","state":"https://pith.science/pith/6A4GPJWOH7VOTZ7UUGD55TPBO3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6A4GPJWOH7VOTZ7UUGD55TPBO3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:6A4GPJWOH7VOTZ7UUGD55TPBO3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c6c67d40f553da38cf0faa6f7a4603fe26ef39681544660c38a9352d1aa8e8a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T16:33:36Z","title_canon_sha256":"f52c73ac9bb74355f3ffdad780497ebed564b6a3eb42892dfa3f3b044c8f9d01"},"schema_version":"1.0","source":{"id":"2502.03340","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03340","created_at":"2026-07-05T10:57:33Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03340v2","created_at":"2026-07-05T10:57:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03340","created_at":"2026-07-05T10:57:33Z"},{"alias_kind":"pith_short_12","alias_value":"6A4GPJWOH7VO","created_at":"2026-07-05T10:57:33Z"},{"alias_kind":"pith_short_16","alias_value":"6A4GPJWOH7VOTZ7U","created_at":"2026-07-05T10:57:33Z"},{"alias_kind":"pith_short_8","alias_value":"6A4GPJWO","created_at":"2026-07-05T10:57:33Z"}],"graph_snapshots":[{"event_id":"sha256:6b81d07a48744e7c88e32ad5b4940403009a2a38d2a9ad0277a4e6b8a135c529","target":"graph","created_at":"2026-07-05T10:57:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2502.03340/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Learning (FL) emerged as a decentralized paradigm to train models while preserving privacy. However, conventional FL struggles with data heterogeneity and class imbalance, which degrade model performance. Clustered FL balances personalization and decentralized training by grouping clients with analogous data distributions, enabling improved accuracy while adhering to privacy constraints. This approach effectively mitigates the adverse impact of heterogeneity in FL. In this work, we propose a novel clustered FL method, FedGWC (Federated Gaussian Weighting Clustering), which groups cli","authors_text":"Alessandro Licciardi, Barbara Caputo, Davide Leo, Eros Fan\\`i, Marco Ciccone","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T16:33:36Z","title":"Interaction-Aware Gaussian Weighting for Clustered Federated Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03340","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:ec4e9011424a9a61bc31c6a2c390d789730b4ebd1eb42fbf803086238bc0d62f","target":"record","created_at":"2026-07-05T10:57:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c6c67d40f553da38cf0faa6f7a4603fe26ef39681544660c38a9352d1aa8e8a9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-02-05T16:33:36Z","title_canon_sha256":"f52c73ac9bb74355f3ffdad780497ebed564b6a3eb42892dfa3f3b044c8f9d01"},"schema_version":"1.0","source":{"id":"2502.03340","kind":"arxiv","version":2}},"canonical_sha256":"f03867a6ce3feae9e7f4a187decde176e819ef59fac2a3c6ba5e8359323fff0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f03867a6ce3feae9e7f4a187decde176e819ef59fac2a3c6ba5e8359323fff0f","first_computed_at":"2026-07-05T10:57:33.514039Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:57:33.514039Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i1UQ1ai6rpMhce3ghUQEbispiks+O1CbaQIkTzrQyok7+X677K3G6ebEOuNe3TJkv5s8LNfCAoB5RNQh6005Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:57:33.514546Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03340","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec4e9011424a9a61bc31c6a2c390d789730b4ebd1eb42fbf803086238bc0d62f","sha256:6b81d07a48744e7c88e32ad5b4940403009a2a38d2a9ad0277a4e6b8a135c529"],"state_sha256":"7b97bf72833ad2a01cfa05c56771082803bfebc96f76c2ac4e2913c92e494a6d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xz+Y/WdmmmWeQ65eOuk03Oilc72LvMy4P1IoqJLlqBiegyjktaC/9FRgQ/2a7kVi7kiaIL4OCzIQPLNQCu/kAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T11:31:40.514874Z","bundle_sha256":"aa7fd88b883c578da84f14643c2ed2ee94ab450601e8f62d5497e6d11035a3a3"}}