{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:D7DTYRRBUSA7BOJJ6A6N7AJ5GC","short_pith_number":"pith:D7DTYRRB","canonical_record":{"source":{"id":"2110.06978","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-13T18:40:54Z","cross_cats_sorted":[],"title_canon_sha256":"35b5eeb75f89ea26a152c9b1bc68f652b252e007f63caa4ae148ec280923ed18","abstract_canon_sha256":"008869ca8762c871d7a95bc32e87fc3cc88dfcadc511130b0f8e3ff741891eb4"},"schema_version":"1.0"},"canonical_sha256":"1fc73c4621a481f0b929f03cdf813d30816e6c45828e43eff9fdc4cb2aae1c9a","source":{"kind":"arxiv","id":"2110.06978","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06978","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06978v2","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06978","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"pith_short_12","alias_value":"D7DTYRRBUSA7","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"pith_short_16","alias_value":"D7DTYRRBUSA7BOJJ","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"pith_short_8","alias_value":"D7DTYRRB","created_at":"2026-07-05T03:40:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:D7DTYRRBUSA7BOJJ6A6N7AJ5GC","target":"record","payload":{"canonical_record":{"source":{"id":"2110.06978","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-13T18:40:54Z","cross_cats_sorted":[],"title_canon_sha256":"35b5eeb75f89ea26a152c9b1bc68f652b252e007f63caa4ae148ec280923ed18","abstract_canon_sha256":"008869ca8762c871d7a95bc32e87fc3cc88dfcadc511130b0f8e3ff741891eb4"},"schema_version":"1.0"},"canonical_sha256":"1fc73c4621a481f0b929f03cdf813d30816e6c45828e43eff9fdc4cb2aae1c9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:40:03.424653Z","signature_b64":"9Dbj1Im1XWuEeTTfgXRDOJ0geIAXPqfvmEU7nzvBlZAFtWVa4lVfP8g3K7QvEqi86EnFoWX7zYQLBuB6SvwrBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1fc73c4621a481f0b929f03cdf813d30816e6c45828e43eff9fdc4cb2aae1c9a","last_reissued_at":"2026-07-05T03:40:03.424233Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:40:03.424233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.06978","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":"2026-07-05T03:40:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lqUqWqpoX8RZhaECddp/HdnAb+xAk65J2hv+o7UB2UR6j6wtIdnUOOUbZuxxc9ZdzD5/BGc+wcLNFEH3AYHSBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:18:34.555671Z"},"content_sha256":"792691f5e9dbbea8e10e0088799334d0adac5ca216b11e117be4fc3d6036d14a","schema_version":"1.0","event_id":"sha256:792691f5e9dbbea8e10e0088799334d0adac5ca216b11e117be4fc3d6036d14a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:D7DTYRRBUSA7BOJJ6A6N7AJ5GC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WAFFLE: Weighted Averaging for Personalized Federated Learning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Felix Grimberg, Martin Beaussart, Martin Jaggi, Mary-Anne Hartley","submitted_at":"2021-10-13T18:40:54Z","abstract_excerpt":"In federated learning, model personalization can be a very effective strategy to deal with heterogeneous training data across clients. We introduce WAFFLE (Weighted Averaging For Federated LEarning), a personalized collaborative machine learning algorithm that leverages stochastic control variates for faster convergence. WAFFLE uses the Euclidean distance between clients' updates to weigh their individual contributions and thus minimize the personalized model loss on the specific agent of interest. Through a series of experiments, we compare our new approach to two recent personalized federate"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06978","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/2110.06978/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":"2026-07-05T03:40:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dnp1hAo6BThLYDygVHxZ5Dlp4SYElDS27cZSftwynv174DrRnlSa/GU9yufb2gBb4e70JbF6nLizh3ymJgsbAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T15:18:34.556606Z"},"content_sha256":"d5d3873e619f412290b3cc3c950102762e3f5c7ac90f0b117c9767c7610599f4","schema_version":"1.0","event_id":"sha256:d5d3873e619f412290b3cc3c950102762e3f5c7ac90f0b117c9767c7610599f4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D7DTYRRBUSA7BOJJ6A6N7AJ5GC/bundle.json","state_url":"https://pith.science/pith/D7DTYRRBUSA7BOJJ6A6N7AJ5GC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D7DTYRRBUSA7BOJJ6A6N7AJ5GC/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":"2026-08-05T15:18:34Z","links":{"resolver":"https://pith.science/pith/D7DTYRRBUSA7BOJJ6A6N7AJ5GC","bundle":"https://pith.science/pith/D7DTYRRBUSA7BOJJ6A6N7AJ5GC/bundle.json","state":"https://pith.science/pith/D7DTYRRBUSA7BOJJ6A6N7AJ5GC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D7DTYRRBUSA7BOJJ6A6N7AJ5GC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:D7DTYRRBUSA7BOJJ6A6N7AJ5GC","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":"008869ca8762c871d7a95bc32e87fc3cc88dfcadc511130b0f8e3ff741891eb4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-13T18:40:54Z","title_canon_sha256":"35b5eeb75f89ea26a152c9b1bc68f652b252e007f63caa4ae148ec280923ed18"},"schema_version":"1.0","source":{"id":"2110.06978","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06978","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06978v2","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06978","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"pith_short_12","alias_value":"D7DTYRRBUSA7","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"pith_short_16","alias_value":"D7DTYRRBUSA7BOJJ","created_at":"2026-07-05T03:40:03Z"},{"alias_kind":"pith_short_8","alias_value":"D7DTYRRB","created_at":"2026-07-05T03:40:03Z"}],"graph_snapshots":[{"event_id":"sha256:d5d3873e619f412290b3cc3c950102762e3f5c7ac90f0b117c9767c7610599f4","target":"graph","created_at":"2026-07-05T03:40:03Z","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/2110.06978/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In federated learning, model personalization can be a very effective strategy to deal with heterogeneous training data across clients. We introduce WAFFLE (Weighted Averaging For Federated LEarning), a personalized collaborative machine learning algorithm that leverages stochastic control variates for faster convergence. WAFFLE uses the Euclidean distance between clients' updates to weigh their individual contributions and thus minimize the personalized model loss on the specific agent of interest. Through a series of experiments, we compare our new approach to two recent personalized federate","authors_text":"Felix Grimberg, Martin Beaussart, Martin Jaggi, Mary-Anne Hartley","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-13T18:40:54Z","title":"WAFFLE: Weighted Averaging for Personalized Federated Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06978","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":"sha256:792691f5e9dbbea8e10e0088799334d0adac5ca216b11e117be4fc3d6036d14a","target":"record","created_at":"2026-07-05T03:40:03Z","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":"008869ca8762c871d7a95bc32e87fc3cc88dfcadc511130b0f8e3ff741891eb4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-13T18:40:54Z","title_canon_sha256":"35b5eeb75f89ea26a152c9b1bc68f652b252e007f63caa4ae148ec280923ed18"},"schema_version":"1.0","source":{"id":"2110.06978","kind":"arxiv","version":2}},"canonical_sha256":"1fc73c4621a481f0b929f03cdf813d30816e6c45828e43eff9fdc4cb2aae1c9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1fc73c4621a481f0b929f03cdf813d30816e6c45828e43eff9fdc4cb2aae1c9a","first_computed_at":"2026-07-05T03:40:03.424233Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:40:03.424233Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Dbj1Im1XWuEeTTfgXRDOJ0geIAXPqfvmEU7nzvBlZAFtWVa4lVfP8g3K7QvEqi86EnFoWX7zYQLBuB6SvwrBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:40:03.424653Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.06978","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:792691f5e9dbbea8e10e0088799334d0adac5ca216b11e117be4fc3d6036d14a","sha256:d5d3873e619f412290b3cc3c950102762e3f5c7ac90f0b117c9767c7610599f4"],"state_sha256":"d8ef44985a4791527ea5fa282233f5dfb8c4ce74ebf7b0ee74fba04b51249bda"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pBuEPXZwTxM8CaTiAaS3dgNEOP7O7xpEXaeGBzRd6POII8nDUB55zlazt1/VaCkgALJzwkW0eS9brZMz0PUJAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T15:18:34.563276Z","bundle_sha256":"8e79adc756033d48b2ab3cd024e4120034c091341a855aad43fb24fbbc7dd8c7"}}