{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:TKZDSYULI2K2NPJD2C2PNR5IRF","short_pith_number":"pith:TKZDSYUL","canonical_record":{"source":{"id":"2206.07832","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T22:05:36Z","cross_cats_sorted":[],"title_canon_sha256":"6c14257549a11d402d3b95eb0c8bedf26c3c79c61d7afef0cf86477b9894d3ec","abstract_canon_sha256":"df1a1e0b21305834a41ed274aa716c7313f3287cd4c3ccc971aeebc2ad8592d0"},"schema_version":"1.0"},"canonical_sha256":"9ab239628b4695a6bd23d0b4f6c7a8894d2adc043f50448477b1d3bf91509099","source":{"kind":"arxiv","id":"2206.07832","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07832","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07832v1","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07832","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"pith_short_12","alias_value":"TKZDSYULI2K2","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"pith_short_16","alias_value":"TKZDSYULI2K2NPJD","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"pith_short_8","alias_value":"TKZDSYUL","created_at":"2026-07-05T04:32:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:TKZDSYULI2K2NPJD2C2PNR5IRF","target":"record","payload":{"canonical_record":{"source":{"id":"2206.07832","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T22:05:36Z","cross_cats_sorted":[],"title_canon_sha256":"6c14257549a11d402d3b95eb0c8bedf26c3c79c61d7afef0cf86477b9894d3ec","abstract_canon_sha256":"df1a1e0b21305834a41ed274aa716c7313f3287cd4c3ccc971aeebc2ad8592d0"},"schema_version":"1.0"},"canonical_sha256":"9ab239628b4695a6bd23d0b4f6c7a8894d2adc043f50448477b1d3bf91509099","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:32:18.764294Z","signature_b64":"bJzfSWL+FAIgTuAG8PicNkGVtaUGGmES/kszfNQTJxMYopxh89ao3BEla5Ja9obvo5JET4Zca2/E4yLjWQjkCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ab239628b4695a6bd23d0b4f6c7a8894d2adc043f50448477b1d3bf91509099","last_reissued_at":"2026-07-05T04:32:18.763795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:32:18.763795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.07832","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":"2026-07-05T04:32:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qKW80QxGfsspi7b0yrmzV0mmrVYavj/4wp5ptOdT100wh9PEom6h6eMAkryo1ZQn0PqEnyidXwgIoBcWVprLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:49:58.989050Z"},"content_sha256":"e7a9265aff15e7d0d23c0fbaa55d214b63acc038c2704d6f47bc41daeb9e0f25","schema_version":"1.0","event_id":"sha256:e7a9265aff15e7d0d23c0fbaa55d214b63acc038c2704d6f47bc41daeb9e0f25"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:TKZDSYULI2K2NPJD2C2PNR5IRF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adaptive Expert Models for Personalization in Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Daniel Gillblad, Edvin Listo Zec, Martin Isaksson, Rickard C\\\"oster, \\v{S}ar\\=unas Girdzijauskas","submitted_at":"2022-06-15T22:05:36Z","abstract_excerpt":"Federated Learning (FL) is a promising framework for distributed learning when data is private and sensitive. However, the state-of-the-art solutions in this framework are not optimal when data is heterogeneous and non-Independent and Identically Distributed (non-IID). We propose a practical and robust approach to personalization in FL that adjusts to heterogeneous and non-IID data by balancing exploration and exploitation of several global models. To achieve our aim of personalization, we use a Mixture of Experts (MoE) that learns to group clients that are similar to each other, while using t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07832","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/2206.07832/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":"2026-07-05T04:32:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NrSZY7+MzJr0WcQ3d7sZEkA7iQfkQMvloCCr1nc1yc0ogj8QGwHhlD5VwfbqP3vmYf3BumEAFM75OnIJ+rgFAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:49:58.989417Z"},"content_sha256":"f0532bbb25b3ed6f64dd0b36f5adce002684928778191feca6a5fcb3dc5b9699","schema_version":"1.0","event_id":"sha256:f0532bbb25b3ed6f64dd0b36f5adce002684928778191feca6a5fcb3dc5b9699"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TKZDSYULI2K2NPJD2C2PNR5IRF/bundle.json","state_url":"https://pith.science/pith/TKZDSYULI2K2NPJD2C2PNR5IRF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TKZDSYULI2K2NPJD2C2PNR5IRF/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":"2026-07-06T13:49:58Z","links":{"resolver":"https://pith.science/pith/TKZDSYULI2K2NPJD2C2PNR5IRF","bundle":"https://pith.science/pith/TKZDSYULI2K2NPJD2C2PNR5IRF/bundle.json","state":"https://pith.science/pith/TKZDSYULI2K2NPJD2C2PNR5IRF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TKZDSYULI2K2NPJD2C2PNR5IRF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:TKZDSYULI2K2NPJD2C2PNR5IRF","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":"df1a1e0b21305834a41ed274aa716c7313f3287cd4c3ccc971aeebc2ad8592d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T22:05:36Z","title_canon_sha256":"6c14257549a11d402d3b95eb0c8bedf26c3c79c61d7afef0cf86477b9894d3ec"},"schema_version":"1.0","source":{"id":"2206.07832","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.07832","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"arxiv_version","alias_value":"2206.07832v1","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.07832","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"pith_short_12","alias_value":"TKZDSYULI2K2","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"pith_short_16","alias_value":"TKZDSYULI2K2NPJD","created_at":"2026-07-05T04:32:18Z"},{"alias_kind":"pith_short_8","alias_value":"TKZDSYUL","created_at":"2026-07-05T04:32:18Z"}],"graph_snapshots":[{"event_id":"sha256:f0532bbb25b3ed6f64dd0b36f5adce002684928778191feca6a5fcb3dc5b9699","target":"graph","created_at":"2026-07-05T04:32:18Z","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/2206.07832/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Learning (FL) is a promising framework for distributed learning when data is private and sensitive. However, the state-of-the-art solutions in this framework are not optimal when data is heterogeneous and non-Independent and Identically Distributed (non-IID). We propose a practical and robust approach to personalization in FL that adjusts to heterogeneous and non-IID data by balancing exploration and exploitation of several global models. To achieve our aim of personalization, we use a Mixture of Experts (MoE) that learns to group clients that are similar to each other, while using t","authors_text":"Daniel Gillblad, Edvin Listo Zec, Martin Isaksson, Rickard C\\\"oster, \\v{S}ar\\=unas Girdzijauskas","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T22:05:36Z","title":"Adaptive Expert Models for Personalization in Federated Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.07832","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:e7a9265aff15e7d0d23c0fbaa55d214b63acc038c2704d6f47bc41daeb9e0f25","target":"record","created_at":"2026-07-05T04:32:18Z","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":"df1a1e0b21305834a41ed274aa716c7313f3287cd4c3ccc971aeebc2ad8592d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-15T22:05:36Z","title_canon_sha256":"6c14257549a11d402d3b95eb0c8bedf26c3c79c61d7afef0cf86477b9894d3ec"},"schema_version":"1.0","source":{"id":"2206.07832","kind":"arxiv","version":1}},"canonical_sha256":"9ab239628b4695a6bd23d0b4f6c7a8894d2adc043f50448477b1d3bf91509099","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ab239628b4695a6bd23d0b4f6c7a8894d2adc043f50448477b1d3bf91509099","first_computed_at":"2026-07-05T04:32:18.763795Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:18.763795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bJzfSWL+FAIgTuAG8PicNkGVtaUGGmES/kszfNQTJxMYopxh89ao3BEla5Ja9obvo5JET4Zca2/E4yLjWQjkCA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:18.764294Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.07832","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e7a9265aff15e7d0d23c0fbaa55d214b63acc038c2704d6f47bc41daeb9e0f25","sha256:f0532bbb25b3ed6f64dd0b36f5adce002684928778191feca6a5fcb3dc5b9699"],"state_sha256":"4aee9770c79862dc8e46e86912d067e5e9b03234f5072cab514129dfc2793f1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZZ+9mX0bpbxSbkb31TVjyiazontEzGavJxr0QU3HA4lQzzO0O30HIDwae/paKVkQ4+tFU8t6sPNnUThNZ1fjAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T13:49:58.991345Z","bundle_sha256":"3ab4587708f0169deef0f14454d5fcd5758c200bff76abeb96900b6ddf44ed1d"}}