{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FSWFZSFVLOYEZEGQ4ZAF2OEABX","short_pith_number":"pith:FSWFZSFV","canonical_record":{"source":{"id":"2402.01350","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T12:09:20Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"d549d13bd26358969d2c949b11c0eea6c1f96ff9287c40b8ae852974011f70e8","abstract_canon_sha256":"f662989ba10e99b262b9fb443dbd6639c77f37bdf8907d1b7e0a5ae2fb276550"},"schema_version":"1.0"},"canonical_sha256":"2cac5cc8b55bb04c90d0e6405d38800dfa38dd278c1b6673a5d3c8c5114066b6","source":{"kind":"arxiv","id":"2402.01350","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01350","created_at":"2026-07-05T07:44:00Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01350v3","created_at":"2026-07-05T07:44:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01350","created_at":"2026-07-05T07:44:00Z"},{"alias_kind":"pith_short_12","alias_value":"FSWFZSFVLOYE","created_at":"2026-07-05T07:44:00Z"},{"alias_kind":"pith_short_16","alias_value":"FSWFZSFVLOYEZEGQ","created_at":"2026-07-05T07:44:00Z"},{"alias_kind":"pith_short_8","alias_value":"FSWFZSFV","created_at":"2026-07-05T07:44:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FSWFZSFVLOYEZEGQ4ZAF2OEABX","target":"record","payload":{"canonical_record":{"source":{"id":"2402.01350","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T12:09:20Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"d549d13bd26358969d2c949b11c0eea6c1f96ff9287c40b8ae852974011f70e8","abstract_canon_sha256":"f662989ba10e99b262b9fb443dbd6639c77f37bdf8907d1b7e0a5ae2fb276550"},"schema_version":"1.0"},"canonical_sha256":"2cac5cc8b55bb04c90d0e6405d38800dfa38dd278c1b6673a5d3c8c5114066b6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:00.104590Z","signature_b64":"uNDcMTTi/pM9YLS9IsoIr4Rmh8Nso0IiD7/lysH1GiQN3zcuuLXgNSQlAua6rBkM13RPg3cA9Ph3d0aLSoQzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2cac5cc8b55bb04c90d0e6405d38800dfa38dd278c1b6673a5d3c8c5114066b6","last_reissued_at":"2026-07-05T07:44:00.104154Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:00.104154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.01350","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:44:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3/BdXMvy02Xd+dZmnVZvvGfmYWLyG1EuvbyRZiWfwnaX/FhOi6DrngHTDXSxWqbb7OY+g1jZmqg9c7AQ7r2vBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:09:58.200907Z"},"content_sha256":"0e82b0a60ffce4eccecef10ec3dcdc7c133bcfb2f3b4c5731430bc87ca9624d7","schema_version":"1.0","event_id":"sha256:0e82b0a60ffce4eccecef10ec3dcdc7c133bcfb2f3b4c5731430bc87ca9624d7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FSWFZSFVLOYEZEGQ4ZAF2OEABX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"pFedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Chao Ren, Gang Wang, Han Yu, Heng Zhang, Liping Yi, Xiaoguang Liu, Xiaoxiao Li","submitted_at":"2024-02-02T12:09:20Z","abstract_excerpt":"Federated learning (FL) has been widely adopted for collaborative training on decentralized data. However, it faces the challenges of data, system, and model heterogeneity. This has inspired the emergence of model-heterogeneous personalized federated learning (MHPFL). Nevertheless, the problem of ensuring data and model privacy, while achieving good model performance and keeping communication and computation costs low remains open in MHPFL. To address this problem, we propose a model-heterogeneous personalized Federated learning with Mixture of Experts (pFedMoE) method. It assigns a shared hom"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01350","kind":"arxiv","version":3},"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/2402.01350/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":"2026-07-05T07:44:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zLzB1Axq6cvit0jxKUi+/XGKW0nUcVo/U6MbT1ibc/DxHZwfDsYPxB2K0q+pjv5WU7GRm7nrX385/soKsIwpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:09:58.201474Z"},"content_sha256":"1a6a2bd7306b44e36bc8ce399e360b58ddeaf4b429cf4d2fc9f0250a72ad5f83","schema_version":"1.0","event_id":"sha256:1a6a2bd7306b44e36bc8ce399e360b58ddeaf4b429cf4d2fc9f0250a72ad5f83"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FSWFZSFVLOYEZEGQ4ZAF2OEABX/bundle.json","state_url":"https://pith.science/pith/FSWFZSFVLOYEZEGQ4ZAF2OEABX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FSWFZSFVLOYEZEGQ4ZAF2OEABX/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":"2026-08-09T20:09:58Z","links":{"resolver":"https://pith.science/pith/FSWFZSFVLOYEZEGQ4ZAF2OEABX","bundle":"https://pith.science/pith/FSWFZSFVLOYEZEGQ4ZAF2OEABX/bundle.json","state":"https://pith.science/pith/FSWFZSFVLOYEZEGQ4ZAF2OEABX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FSWFZSFVLOYEZEGQ4ZAF2OEABX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FSWFZSFVLOYEZEGQ4ZAF2OEABX","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":"f662989ba10e99b262b9fb443dbd6639c77f37bdf8907d1b7e0a5ae2fb276550","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T12:09:20Z","title_canon_sha256":"d549d13bd26358969d2c949b11c0eea6c1f96ff9287c40b8ae852974011f70e8"},"schema_version":"1.0","source":{"id":"2402.01350","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.01350","created_at":"2026-07-05T07:44:00Z"},{"alias_kind":"arxiv_version","alias_value":"2402.01350v3","created_at":"2026-07-05T07:44:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.01350","created_at":"2026-07-05T07:44:00Z"},{"alias_kind":"pith_short_12","alias_value":"FSWFZSFVLOYE","created_at":"2026-07-05T07:44:00Z"},{"alias_kind":"pith_short_16","alias_value":"FSWFZSFVLOYEZEGQ","created_at":"2026-07-05T07:44:00Z"},{"alias_kind":"pith_short_8","alias_value":"FSWFZSFV","created_at":"2026-07-05T07:44:00Z"}],"graph_snapshots":[{"event_id":"sha256:1a6a2bd7306b44e36bc8ce399e360b58ddeaf4b429cf4d2fc9f0250a72ad5f83","target":"graph","created_at":"2026-07-05T07:44:00Z","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/2402.01350/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated learning (FL) has been widely adopted for collaborative training on decentralized data. However, it faces the challenges of data, system, and model heterogeneity. This has inspired the emergence of model-heterogeneous personalized federated learning (MHPFL). Nevertheless, the problem of ensuring data and model privacy, while achieving good model performance and keeping communication and computation costs low remains open in MHPFL. To address this problem, we propose a model-heterogeneous personalized Federated learning with Mixture of Experts (pFedMoE) method. It assigns a shared hom","authors_text":"Chao Ren, Gang Wang, Han Yu, Heng Zhang, Liping Yi, Xiaoguang Liu, Xiaoxiao Li","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T12:09:20Z","title":"pFedMoE: Data-Level Personalization with Mixture of Experts for Model-Heterogeneous Personalized Federated Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.01350","kind":"arxiv","version":3},"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":"sha256:0e82b0a60ffce4eccecef10ec3dcdc7c133bcfb2f3b4c5731430bc87ca9624d7","target":"record","created_at":"2026-07-05T07:44:00Z","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":"f662989ba10e99b262b9fb443dbd6639c77f37bdf8907d1b7e0a5ae2fb276550","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-02T12:09:20Z","title_canon_sha256":"d549d13bd26358969d2c949b11c0eea6c1f96ff9287c40b8ae852974011f70e8"},"schema_version":"1.0","source":{"id":"2402.01350","kind":"arxiv","version":3}},"canonical_sha256":"2cac5cc8b55bb04c90d0e6405d38800dfa38dd278c1b6673a5d3c8c5114066b6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cac5cc8b55bb04c90d0e6405d38800dfa38dd278c1b6673a5d3c8c5114066b6","first_computed_at":"2026-07-05T07:44:00.104154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:44:00.104154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uNDcMTTi/pM9YLS9IsoIr4Rmh8Nso0IiD7/lysH1GiQN3zcuuLXgNSQlAua6rBkM13RPg3cA9Ph3d0aLSoQzAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:44:00.104590Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.01350","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e82b0a60ffce4eccecef10ec3dcdc7c133bcfb2f3b4c5731430bc87ca9624d7","sha256:1a6a2bd7306b44e36bc8ce399e360b58ddeaf4b429cf4d2fc9f0250a72ad5f83"],"state_sha256":"f905f88c2d0f8053aa9796f7460a8abd83414eec62940519c4593d93f75c3ae2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4vWMjpgVEb2H0DXLGQ81PQdFzJhdCShop79ZZWcZG8A8Hdbb28NuJL05bf15ustWX/DWj7dv57R3Wr5g4hqBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:09:58.206508Z","bundle_sha256":"7b1b19db631c87839743f42815432ea51c8eff42e266ac1e878485848c21e6ed"}}