{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:HMYIJ7URVJ7D6QTFZES6CEOEIL","short_pith_number":"pith:HMYIJ7UR","canonical_record":{"source":{"id":"1906.06268","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T16:09:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9c1e3139ba19713c8ef7ad67c3d3feeb2b23233ec479791ae9af13dd3990bd33","abstract_canon_sha256":"b78c47c894a324fc31023929b7b125887dcf479b63e8df3f16d7e99ff945890c"},"schema_version":"1.0"},"canonical_sha256":"3b3084fe91aa7e3f4265c925e111c442cd2de29732bc9ae9f36fa28481d7bd3d","source":{"kind":"arxiv","id":"1906.06268","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.06268","created_at":"2026-07-05T02:12:39Z"},{"alias_kind":"arxiv_version","alias_value":"1906.06268v2","created_at":"2026-07-05T02:12:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06268","created_at":"2026-07-05T02:12:39Z"},{"alias_kind":"pith_short_12","alias_value":"HMYIJ7URVJ7D","created_at":"2026-07-05T02:12:39Z"},{"alias_kind":"pith_short_16","alias_value":"HMYIJ7URVJ7D6QTF","created_at":"2026-07-05T02:12:39Z"},{"alias_kind":"pith_short_8","alias_value":"HMYIJ7UR","created_at":"2026-07-05T02:12:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:HMYIJ7URVJ7D6QTFZES6CEOEIL","target":"record","payload":{"canonical_record":{"source":{"id":"1906.06268","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T16:09:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9c1e3139ba19713c8ef7ad67c3d3feeb2b23233ec479791ae9af13dd3990bd33","abstract_canon_sha256":"b78c47c894a324fc31023929b7b125887dcf479b63e8df3f16d7e99ff945890c"},"schema_version":"1.0"},"canonical_sha256":"3b3084fe91aa7e3f4265c925e111c442cd2de29732bc9ae9f36fa28481d7bd3d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:12:39.415302Z","signature_b64":"zft/Gt6+pqJK+hukQSbIxP9GVM2V9IXLCGDviDmTyC/NiONT7tS2tTP26lampk7lSyff6WdGtxX65xE9aBZIAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b3084fe91aa7e3f4265c925e111c442cd2de29732bc9ae9f36fa28481d7bd3d","last_reissued_at":"2026-07-05T02:12:39.414894Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:12:39.414894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.06268","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":"2026-07-05T02:12:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1N86xjV9dT2qZPicgmdF4yfnz7kYxwM5qZz2ZG1LnE3HtXmL0I0cqSZnS+uhK4gqov+MmuLlo+VAHqaKjhtlAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:51:47.819622Z"},"content_sha256":"c8fefaf2158eb043743d8d609a5cfac8894c36bb3e7bf0c9ea066c4a9f8e9c43","schema_version":"1.0","event_id":"sha256:c8fefaf2158eb043743d8d609a5cfac8894c36bb3e7bf0c9ea066c4a9f8e9c43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:HMYIJ7URVJ7D6QTFZES6CEOEIL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Variational Federated Multi-Task Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Ami Beuret, Joachim M. Buhmann, Luca Corinzia","submitted_at":"2019-06-14T16:09:56Z","abstract_excerpt":"In federated learning, a central server coordinates the training of a single model on a massively distributed network of devices. This setting can be naturally extended to a multi-task learning framework, to handle real-world federated datasets that typically show strong statistical heterogeneity among devices. Despite federated multi-task learning being shown to be an effective paradigm for real-world datasets, it has been applied only on convex models. In this work, we introduce VIRTUAL, an algorithm for federated multi-task learning for general non-convex models. In VIRTUAL the federated ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06268","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/1906.06268/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":"2026-07-05T02:12:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KPnhp3Kwp6w2OB9oEVbCyMzw/9IDmA8B4PbUTaKFV6YZokBYmkjDiQLInChCejRZSaeT+3pbyeglN5gOcrlxAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T12:51:47.820135Z"},"content_sha256":"5af5bc74f3b560c9dee14b64c574e0f444f9b12a320a62b0cc3bd9114f2b9091","schema_version":"1.0","event_id":"sha256:5af5bc74f3b560c9dee14b64c574e0f444f9b12a320a62b0cc3bd9114f2b9091"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HMYIJ7URVJ7D6QTFZES6CEOEIL/bundle.json","state_url":"https://pith.science/pith/HMYIJ7URVJ7D6QTFZES6CEOEIL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HMYIJ7URVJ7D6QTFZES6CEOEIL/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":"2026-08-12T12:51:47Z","links":{"resolver":"https://pith.science/pith/HMYIJ7URVJ7D6QTFZES6CEOEIL","bundle":"https://pith.science/pith/HMYIJ7URVJ7D6QTFZES6CEOEIL/bundle.json","state":"https://pith.science/pith/HMYIJ7URVJ7D6QTFZES6CEOEIL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HMYIJ7URVJ7D6QTFZES6CEOEIL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:HMYIJ7URVJ7D6QTFZES6CEOEIL","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":"b78c47c894a324fc31023929b7b125887dcf479b63e8df3f16d7e99ff945890c","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T16:09:56Z","title_canon_sha256":"9c1e3139ba19713c8ef7ad67c3d3feeb2b23233ec479791ae9af13dd3990bd33"},"schema_version":"1.0","source":{"id":"1906.06268","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.06268","created_at":"2026-07-05T02:12:39Z"},{"alias_kind":"arxiv_version","alias_value":"1906.06268v2","created_at":"2026-07-05T02:12:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.06268","created_at":"2026-07-05T02:12:39Z"},{"alias_kind":"pith_short_12","alias_value":"HMYIJ7URVJ7D","created_at":"2026-07-05T02:12:39Z"},{"alias_kind":"pith_short_16","alias_value":"HMYIJ7URVJ7D6QTF","created_at":"2026-07-05T02:12:39Z"},{"alias_kind":"pith_short_8","alias_value":"HMYIJ7UR","created_at":"2026-07-05T02:12:39Z"}],"graph_snapshots":[{"event_id":"sha256:5af5bc74f3b560c9dee14b64c574e0f444f9b12a320a62b0cc3bd9114f2b9091","target":"graph","created_at":"2026-07-05T02:12:39Z","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/1906.06268/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In federated learning, a central server coordinates the training of a single model on a massively distributed network of devices. This setting can be naturally extended to a multi-task learning framework, to handle real-world federated datasets that typically show strong statistical heterogeneity among devices. Despite federated multi-task learning being shown to be an effective paradigm for real-world datasets, it has been applied only on convex models. In this work, we introduce VIRTUAL, an algorithm for federated multi-task learning for general non-convex models. In VIRTUAL the federated ne","authors_text":"Ami Beuret, Joachim M. Buhmann, Luca Corinzia","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T16:09:56Z","title":"Variational Federated Multi-Task Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.06268","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:c8fefaf2158eb043743d8d609a5cfac8894c36bb3e7bf0c9ea066c4a9f8e9c43","target":"record","created_at":"2026-07-05T02:12:39Z","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":"b78c47c894a324fc31023929b7b125887dcf479b63e8df3f16d7e99ff945890c","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2019-06-14T16:09:56Z","title_canon_sha256":"9c1e3139ba19713c8ef7ad67c3d3feeb2b23233ec479791ae9af13dd3990bd33"},"schema_version":"1.0","source":{"id":"1906.06268","kind":"arxiv","version":2}},"canonical_sha256":"3b3084fe91aa7e3f4265c925e111c442cd2de29732bc9ae9f36fa28481d7bd3d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3b3084fe91aa7e3f4265c925e111c442cd2de29732bc9ae9f36fa28481d7bd3d","first_computed_at":"2026-07-05T02:12:39.414894Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:12:39.414894Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zft/Gt6+pqJK+hukQSbIxP9GVM2V9IXLCGDviDmTyC/NiONT7tS2tTP26lampk7lSyff6WdGtxX65xE9aBZIAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:12:39.415302Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.06268","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8fefaf2158eb043743d8d609a5cfac8894c36bb3e7bf0c9ea066c4a9f8e9c43","sha256:5af5bc74f3b560c9dee14b64c574e0f444f9b12a320a62b0cc3bd9114f2b9091"],"state_sha256":"be7660a5cd90e9d76b6cf422649869720b8c29af4a62ec5a1f0d9a0d23c82210"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CzJaLT9N31B1OSltTPSGd4ng1AQah+P1ORtESlJ9OaaAJKxQqkXGQNlZ/chjV4a2fuLegV5NTZHJyLa4YusOBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T12:51:47.825118Z","bundle_sha256":"1e45e464c1cfe047dc502089379be7efee7ebfbd30734c86d29783be9f7660d1"}}