{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:AEQSTMBA4B4LBFEE6RJBSU56RN","short_pith_number":"pith:AEQSTMBA","canonical_record":{"source":{"id":"2107.05330","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-12T11:43:40Z","cross_cats_sorted":[],"title_canon_sha256":"85ea7111cd6d6b718f2b925bce5dba0edf77d7aec53ee8ccd844d220b59566f9","abstract_canon_sha256":"24c6e5eaf18184dce33b3fb4d878ab86ddf23f2006fff3ddc4c72325cdd344de"},"schema_version":"1.0"},"canonical_sha256":"012129b020e078b09484f4521953be8b59a38257f4eb761c620d29800fa5d929","source":{"kind":"arxiv","id":"2107.05330","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.05330","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"arxiv_version","alias_value":"2107.05330v4","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.05330","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"pith_short_12","alias_value":"AEQSTMBA4B4L","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"pith_short_16","alias_value":"AEQSTMBA4B4LBFEE","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"pith_short_8","alias_value":"AEQSTMBA","created_at":"2026-07-05T05:47:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:AEQSTMBA4B4LBFEE6RJBSU56RN","target":"record","payload":{"canonical_record":{"source":{"id":"2107.05330","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-12T11:43:40Z","cross_cats_sorted":[],"title_canon_sha256":"85ea7111cd6d6b718f2b925bce5dba0edf77d7aec53ee8ccd844d220b59566f9","abstract_canon_sha256":"24c6e5eaf18184dce33b3fb4d878ab86ddf23f2006fff3ddc4c72325cdd344de"},"schema_version":"1.0"},"canonical_sha256":"012129b020e078b09484f4521953be8b59a38257f4eb761c620d29800fa5d929","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:55.593127Z","signature_b64":"V9q7P1PjcgE9tljwiYYBCbK3/rncw78AjduF8M71oqu3vJNnp3z+Jjt820E6N8HAZOcB6m+ZR8aGutH+gPmYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"012129b020e078b09484f4521953be8b59a38257f4eb761c620d29800fa5d929","last_reissued_at":"2026-07-05T05:47:55.592542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:55.592542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.05330","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:47:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YAD/fEGPfywDhYF1d7hzjAHC3CCW40JnuVSo2pqkGdh/3zndcE3iDLNd9XbS0Crl82LCPI14X6lBqJQvOaYSAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:32:38.641960Z"},"content_sha256":"52f71f228c1fd436334d66b4155a920ee62c484d7b250e8b1fb6194e66cfa4e4","schema_version":"1.0","event_id":"sha256:52f71f228c1fd436334d66b4155a920ee62c484d7b250e8b1fb6194e66cfa4e4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:AEQSTMBA4B4LBFEE6RJBSU56RN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sparse Personalized Federated Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Qing Wang, Xiaofeng Liu, Xu Zhang, Yanhui Geng, Yinchuan Li, Yunfeng Shao","submitted_at":"2021-07-12T11:43:40Z","abstract_excerpt":"Federated Learning (FL) is a collaborative machine learning technique to train a global model without obtaining clients' private data. The main challenges in FL are statistical diversity among clients, limited computing capability among clients' equipments, and the excessive communication overhead between the server and clients. To address these challenges, we propose a novel sparse personalized federated learning scheme via maximizing correlation (FedMac). By incorporating an approximated L1-norm and the correlation between client models and global model into standard FL loss function, the pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.05330","kind":"arxiv","version":4},"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/2107.05330/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":"2026-07-05T05:47:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N6hgyp6fiBGxTv79dWup3SnpRZi1sad/JLwX05lECPV6K+TAsO8qqlLH0RmqxWs5A4iwmU6zBr7xgmdWkXVqDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T10:32:38.642845Z"},"content_sha256":"0bb1b1e8d8f3dbd58b680a81403d6ecbd7b8384a3e1ebb7fc0ab44a54b75d45b","schema_version":"1.0","event_id":"sha256:0bb1b1e8d8f3dbd58b680a81403d6ecbd7b8384a3e1ebb7fc0ab44a54b75d45b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AEQSTMBA4B4LBFEE6RJBSU56RN/bundle.json","state_url":"https://pith.science/pith/AEQSTMBA4B4LBFEE6RJBSU56RN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AEQSTMBA4B4LBFEE6RJBSU56RN/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":"2026-08-07T10:32:38Z","links":{"resolver":"https://pith.science/pith/AEQSTMBA4B4LBFEE6RJBSU56RN","bundle":"https://pith.science/pith/AEQSTMBA4B4LBFEE6RJBSU56RN/bundle.json","state":"https://pith.science/pith/AEQSTMBA4B4LBFEE6RJBSU56RN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AEQSTMBA4B4LBFEE6RJBSU56RN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:AEQSTMBA4B4LBFEE6RJBSU56RN","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":"24c6e5eaf18184dce33b3fb4d878ab86ddf23f2006fff3ddc4c72325cdd344de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-12T11:43:40Z","title_canon_sha256":"85ea7111cd6d6b718f2b925bce5dba0edf77d7aec53ee8ccd844d220b59566f9"},"schema_version":"1.0","source":{"id":"2107.05330","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.05330","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"arxiv_version","alias_value":"2107.05330v4","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.05330","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"pith_short_12","alias_value":"AEQSTMBA4B4L","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"pith_short_16","alias_value":"AEQSTMBA4B4LBFEE","created_at":"2026-07-05T05:47:55Z"},{"alias_kind":"pith_short_8","alias_value":"AEQSTMBA","created_at":"2026-07-05T05:47:55Z"}],"graph_snapshots":[{"event_id":"sha256:0bb1b1e8d8f3dbd58b680a81403d6ecbd7b8384a3e1ebb7fc0ab44a54b75d45b","target":"graph","created_at":"2026-07-05T05:47:55Z","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/2107.05330/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Learning (FL) is a collaborative machine learning technique to train a global model without obtaining clients' private data. The main challenges in FL are statistical diversity among clients, limited computing capability among clients' equipments, and the excessive communication overhead between the server and clients. To address these challenges, we propose a novel sparse personalized federated learning scheme via maximizing correlation (FedMac). By incorporating an approximated L1-norm and the correlation between client models and global model into standard FL loss function, the pe","authors_text":"Qing Wang, Xiaofeng Liu, Xu Zhang, Yanhui Geng, Yinchuan Li, Yunfeng Shao","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-12T11:43:40Z","title":"Sparse Personalized Federated Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.05330","kind":"arxiv","version":4},"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":"sha256:52f71f228c1fd436334d66b4155a920ee62c484d7b250e8b1fb6194e66cfa4e4","target":"record","created_at":"2026-07-05T05:47:55Z","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":"24c6e5eaf18184dce33b3fb4d878ab86ddf23f2006fff3ddc4c72325cdd344de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-12T11:43:40Z","title_canon_sha256":"85ea7111cd6d6b718f2b925bce5dba0edf77d7aec53ee8ccd844d220b59566f9"},"schema_version":"1.0","source":{"id":"2107.05330","kind":"arxiv","version":4}},"canonical_sha256":"012129b020e078b09484f4521953be8b59a38257f4eb761c620d29800fa5d929","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"012129b020e078b09484f4521953be8b59a38257f4eb761c620d29800fa5d929","first_computed_at":"2026-07-05T05:47:55.592542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:55.592542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V9q7P1PjcgE9tljwiYYBCbK3/rncw78AjduF8M71oqu3vJNnp3z+Jjt820E6N8HAZOcB6m+ZR8aGutH+gPmYBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:55.593127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.05330","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52f71f228c1fd436334d66b4155a920ee62c484d7b250e8b1fb6194e66cfa4e4","sha256:0bb1b1e8d8f3dbd58b680a81403d6ecbd7b8384a3e1ebb7fc0ab44a54b75d45b"],"state_sha256":"8915f23d719182fc3fecce668ec67adecfe431f6f66de6a5177616f2d0460579"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nzs3L2XuhAdhKfES3TFgPl+RotPUhsusilsRbfqGsn9A3POaQcflE5j3Wqx4mXiCcM4Ro5dzDM8+y/snTWfvCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T10:32:38.648347Z","bundle_sha256":"7a4348e2ba3056913decc633087a571715626e06894c74e9a5355f2183672523"}}