{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:25F3SWJP4LUHW3SX2LU5MIB7OL","short_pith_number":"pith:25F3SWJP","canonical_record":{"source":{"id":"2505.02540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T10:26:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa2f02e692653c3d60ff779522e8bb81537d37199a270adf9824420a6da1743b","abstract_canon_sha256":"6cab67a58a9019a9428a850894fa792ffc8854a3792946042ccee7c76a2e8f63"},"schema_version":"1.0"},"canonical_sha256":"d74bb9592fe2e87b6e57d2e9d6203f72f09a024af29ddae302ca0cb2c28f6dd9","source":{"kind":"arxiv","id":"2505.02540","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02540","created_at":"2026-06-05T01:15:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02540v1","created_at":"2026-06-05T01:15:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02540","created_at":"2026-06-05T01:15:13Z"},{"alias_kind":"pith_short_12","alias_value":"25F3SWJP4LUH","created_at":"2026-06-05T01:15:13Z"},{"alias_kind":"pith_short_16","alias_value":"25F3SWJP4LUHW3SX","created_at":"2026-06-05T01:15:13Z"},{"alias_kind":"pith_short_8","alias_value":"25F3SWJP","created_at":"2026-06-05T01:15:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:25F3SWJP4LUHW3SX2LU5MIB7OL","target":"record","payload":{"canonical_record":{"source":{"id":"2505.02540","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T10:26:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"aa2f02e692653c3d60ff779522e8bb81537d37199a270adf9824420a6da1743b","abstract_canon_sha256":"6cab67a58a9019a9428a850894fa792ffc8854a3792946042ccee7c76a2e8f63"},"schema_version":"1.0"},"canonical_sha256":"d74bb9592fe2e87b6e57d2e9d6203f72f09a024af29ddae302ca0cb2c28f6dd9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:13.534544Z","signature_b64":"SVTLlkm8m+jNNx02bk52xqncywAmb2fUUt5vkIpgR1VyBCyuEntbKRHZOLQVk87QE/0b8Bg0Mfd2RfoAo4PNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d74bb9592fe2e87b6e57d2e9d6203f72f09a024af29ddae302ca0cb2c28f6dd9","last_reissued_at":"2026-06-05T01:15:13.533749Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:13.533749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.02540","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AgZvgCcC6bMCWCNUjZFoC8hZmEsLrIGnrW1PfiVk1RFS0UZg4nPQUjz3FReIiSGERYfNLHJTcYCgM8NrRHm1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T18:05:56.045924Z"},"content_sha256":"5badd59453176008fb353b813ac94308677462e8c3337fac9f18bbcecbf22a90","schema_version":"1.0","event_id":"sha256:5badd59453176008fb353b813ac94308677462e8c3337fac9f18bbcecbf22a90"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:25F3SWJP4LUHW3SX2LU5MIB7OL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lazy But Effective: Collaborative Personalized Federated Learning with Heterogeneous Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Boi Faltings, Ljubomir Rokvic, Panayiotis Danassis","submitted_at":"2025-05-05T10:26:35Z","abstract_excerpt":"In Federated Learning, heterogeneity in client data distributions often means that a single global model does not have the best performance for individual clients. Consider for example training a next-word prediction model for keyboards: user-specific language patterns due to demographics (dialect, age, etc.), language proficiency, and writing style result in a highly non-IID dataset across clients. Other examples are medical images taken with different machines, or driving data from different vehicle types. To address this, we propose a simple yet effective personalized federated learning fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02540","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/2505.02540/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":"2026-06-05T01:15:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nGMr1TSWTkNFahEeVT38Qvs3lUihTG1+32i9PFC1BuaEAJdqFVJmtJ9ikvYgB0HQD2QLN7W+eNvv044jWQvADg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T18:05:56.046307Z"},"content_sha256":"e2f01bd0bbe298f782511c4dc8f614a6839f1d7c8c113d041fd3f59487ed4d40","schema_version":"1.0","event_id":"sha256:e2f01bd0bbe298f782511c4dc8f614a6839f1d7c8c113d041fd3f59487ed4d40"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/25F3SWJP4LUHW3SX2LU5MIB7OL/bundle.json","state_url":"https://pith.science/pith/25F3SWJP4LUHW3SX2LU5MIB7OL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/25F3SWJP4LUHW3SX2LU5MIB7OL/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":"2026-06-10T18:05:56Z","links":{"resolver":"https://pith.science/pith/25F3SWJP4LUHW3SX2LU5MIB7OL","bundle":"https://pith.science/pith/25F3SWJP4LUHW3SX2LU5MIB7OL/bundle.json","state":"https://pith.science/pith/25F3SWJP4LUHW3SX2LU5MIB7OL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/25F3SWJP4LUHW3SX2LU5MIB7OL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:25F3SWJP4LUHW3SX2LU5MIB7OL","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":"6cab67a58a9019a9428a850894fa792ffc8854a3792946042ccee7c76a2e8f63","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T10:26:35Z","title_canon_sha256":"aa2f02e692653c3d60ff779522e8bb81537d37199a270adf9824420a6da1743b"},"schema_version":"1.0","source":{"id":"2505.02540","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.02540","created_at":"2026-06-05T01:15:13Z"},{"alias_kind":"arxiv_version","alias_value":"2505.02540v1","created_at":"2026-06-05T01:15:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.02540","created_at":"2026-06-05T01:15:13Z"},{"alias_kind":"pith_short_12","alias_value":"25F3SWJP4LUH","created_at":"2026-06-05T01:15:13Z"},{"alias_kind":"pith_short_16","alias_value":"25F3SWJP4LUHW3SX","created_at":"2026-06-05T01:15:13Z"},{"alias_kind":"pith_short_8","alias_value":"25F3SWJP","created_at":"2026-06-05T01:15:13Z"}],"graph_snapshots":[{"event_id":"sha256:e2f01bd0bbe298f782511c4dc8f614a6839f1d7c8c113d041fd3f59487ed4d40","target":"graph","created_at":"2026-06-05T01:15:13Z","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/2505.02540/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In Federated Learning, heterogeneity in client data distributions often means that a single global model does not have the best performance for individual clients. Consider for example training a next-word prediction model for keyboards: user-specific language patterns due to demographics (dialect, age, etc.), language proficiency, and writing style result in a highly non-IID dataset across clients. Other examples are medical images taken with different machines, or driving data from different vehicle types. To address this, we propose a simple yet effective personalized federated learning fra","authors_text":"Boi Faltings, Ljubomir Rokvic, Panayiotis Danassis","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T10:26:35Z","title":"Lazy But Effective: Collaborative Personalized Federated Learning with Heterogeneous Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.02540","kind":"arxiv","version":1},"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":"sha256:5badd59453176008fb353b813ac94308677462e8c3337fac9f18bbcecbf22a90","target":"record","created_at":"2026-06-05T01:15:13Z","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":"6cab67a58a9019a9428a850894fa792ffc8854a3792946042ccee7c76a2e8f63","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-05T10:26:35Z","title_canon_sha256":"aa2f02e692653c3d60ff779522e8bb81537d37199a270adf9824420a6da1743b"},"schema_version":"1.0","source":{"id":"2505.02540","kind":"arxiv","version":1}},"canonical_sha256":"d74bb9592fe2e87b6e57d2e9d6203f72f09a024af29ddae302ca0cb2c28f6dd9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d74bb9592fe2e87b6e57d2e9d6203f72f09a024af29ddae302ca0cb2c28f6dd9","first_computed_at":"2026-06-05T01:15:13.533749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:13.533749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SVTLlkm8m+jNNx02bk52xqncywAmb2fUUt5vkIpgR1VyBCyuEntbKRHZOLQVk87QE/0b8Bg0Mfd2RfoAo4PNAg==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:13.534544Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.02540","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5badd59453176008fb353b813ac94308677462e8c3337fac9f18bbcecbf22a90","sha256:e2f01bd0bbe298f782511c4dc8f614a6839f1d7c8c113d041fd3f59487ed4d40"],"state_sha256":"6fbb85644840306293b20b49752ef38adddd85daf82d49f61ee297b28c938d36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ik9LQsGDnfrSah6MygHSmCXnHvTcEmGl7hsHFWZyZKsn+ec4Zy5X7PgQ5P0dXdMDHhxXvKqPCKhaktqUPMZaDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T18:05:56.048373Z","bundle_sha256":"81e1103787c0641b0acd0b7e710cbb43eb7efca9264d2af0bbba866387539e50"}}