{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:XB4FQPT6LL5RJHWQMEG3B3VDKL","short_pith_number":"pith:XB4FQPT6","canonical_record":{"source":{"id":"2007.09236","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-17T21:11:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2d548b4eccaae61a3001a69d0e0a1974f50aff7e26c26e7a5eb08d938aaacba2","abstract_canon_sha256":"8566df0c7a90ab4f169a6916c7cd563536c09c0e4e46de98d57ed10e4e4094e0"},"schema_version":"1.0"},"canonical_sha256":"b878583e7e5afb149ed0610db0eea352c3b51741d8e76d0f9a2f30635c45a594","source":{"kind":"arxiv","id":"2007.09236","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.09236","created_at":"2026-07-05T02:59:53Z"},{"alias_kind":"arxiv_version","alias_value":"2007.09236v3","created_at":"2026-07-05T02:59:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.09236","created_at":"2026-07-05T02:59:53Z"},{"alias_kind":"pith_short_12","alias_value":"XB4FQPT6LL5R","created_at":"2026-07-05T02:59:53Z"},{"alias_kind":"pith_short_16","alias_value":"XB4FQPT6LL5RJHWQ","created_at":"2026-07-05T02:59:53Z"},{"alias_kind":"pith_short_8","alias_value":"XB4FQPT6","created_at":"2026-07-05T02:59:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:XB4FQPT6LL5RJHWQMEG3B3VDKL","target":"record","payload":{"canonical_record":{"source":{"id":"2007.09236","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-17T21:11:01Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"2d548b4eccaae61a3001a69d0e0a1974f50aff7e26c26e7a5eb08d938aaacba2","abstract_canon_sha256":"8566df0c7a90ab4f169a6916c7cd563536c09c0e4e46de98d57ed10e4e4094e0"},"schema_version":"1.0"},"canonical_sha256":"b878583e7e5afb149ed0610db0eea352c3b51741d8e76d0f9a2f30635c45a594","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:53.498721Z","signature_b64":"H5+h9ZSShqntvyAGWRjJJRu8fX4JLeDXBUTucC5rGkw9H19F+umzT9juYQGh/m+IZTy4bGM783lQqyQpDBaAAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b878583e7e5afb149ed0610db0eea352c3b51741d8e76d0f9a2f30635c45a594","last_reissued_at":"2026-07-05T02:59:53.498230Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:53.498230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2007.09236","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:59:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9CBf9D3aAL8rk2R7YhCovglEDiA22tky+NBbaUNkkKOFs9i8HQrnW1ltAxhIflOkwPDDFcpJMODuBx0BzriNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:40:53.940130Z"},"content_sha256":"dde0881f42410c47727ac3d32eb52bd1eb274530344cb356e62546c55301c8dd","schema_version":"1.0","event_id":"sha256:dde0881f42410c47727ac3d32eb52bd1eb274530344cb356e62546c55301c8dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:XB4FQPT6LL5RJHWQMEG3B3VDKL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge Computing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Geyong Min, Jed Mills, Jia Hu","submitted_at":"2020-07-17T21:11:01Z","abstract_excerpt":"Federated Learning (FL) is an emerging approach for collaboratively training Deep Neural Networks (DNNs) on mobile devices, without private user data leaving the devices. Previous works have shown that non-Independent and Identically Distributed (non-IID) user data harms the convergence speed of the FL algorithms. Furthermore, most existing work on FL measures global-model accuracy, but in many cases, such as user content-recommendation, improving individual User model Accuracy (UA) is the real objective. To address these issues, we propose a Multi-Task FL (MTFL) algorithm that introduces non-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.09236","kind":"arxiv","version":3},"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/2007.09236/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":"2026-07-05T02:59:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F/hy1w2bkOkXOyWu1wWob1fZN+TG+Un/aA2tml6dw26SJcPzgIQpSREcQ/aJ06WwwBLlSWdoVwzZhwcvOe6VBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:40:53.940661Z"},"content_sha256":"4ffc6f8c582162d880ca724b587c4142f23ee1a719cb388bbb8e94c9325ec298","schema_version":"1.0","event_id":"sha256:4ffc6f8c582162d880ca724b587c4142f23ee1a719cb388bbb8e94c9325ec298"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XB4FQPT6LL5RJHWQMEG3B3VDKL/bundle.json","state_url":"https://pith.science/pith/XB4FQPT6LL5RJHWQMEG3B3VDKL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XB4FQPT6LL5RJHWQMEG3B3VDKL/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":"2026-08-05T07:40:53Z","links":{"resolver":"https://pith.science/pith/XB4FQPT6LL5RJHWQMEG3B3VDKL","bundle":"https://pith.science/pith/XB4FQPT6LL5RJHWQMEG3B3VDKL/bundle.json","state":"https://pith.science/pith/XB4FQPT6LL5RJHWQMEG3B3VDKL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XB4FQPT6LL5RJHWQMEG3B3VDKL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XB4FQPT6LL5RJHWQMEG3B3VDKL","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":"8566df0c7a90ab4f169a6916c7cd563536c09c0e4e46de98d57ed10e4e4094e0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-17T21:11:01Z","title_canon_sha256":"2d548b4eccaae61a3001a69d0e0a1974f50aff7e26c26e7a5eb08d938aaacba2"},"schema_version":"1.0","source":{"id":"2007.09236","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2007.09236","created_at":"2026-07-05T02:59:53Z"},{"alias_kind":"arxiv_version","alias_value":"2007.09236v3","created_at":"2026-07-05T02:59:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2007.09236","created_at":"2026-07-05T02:59:53Z"},{"alias_kind":"pith_short_12","alias_value":"XB4FQPT6LL5R","created_at":"2026-07-05T02:59:53Z"},{"alias_kind":"pith_short_16","alias_value":"XB4FQPT6LL5RJHWQ","created_at":"2026-07-05T02:59:53Z"},{"alias_kind":"pith_short_8","alias_value":"XB4FQPT6","created_at":"2026-07-05T02:59:53Z"}],"graph_snapshots":[{"event_id":"sha256:4ffc6f8c582162d880ca724b587c4142f23ee1a719cb388bbb8e94c9325ec298","target":"graph","created_at":"2026-07-05T02:59:53Z","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/2007.09236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Learning (FL) is an emerging approach for collaboratively training Deep Neural Networks (DNNs) on mobile devices, without private user data leaving the devices. Previous works have shown that non-Independent and Identically Distributed (non-IID) user data harms the convergence speed of the FL algorithms. Furthermore, most existing work on FL measures global-model accuracy, but in many cases, such as user content-recommendation, improving individual User model Accuracy (UA) is the real objective. To address these issues, we propose a Multi-Task FL (MTFL) algorithm that introduces non-","authors_text":"Geyong Min, Jed Mills, Jia Hu","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-17T21:11:01Z","title":"Multi-Task Federated Learning for Personalised Deep Neural Networks in Edge Computing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2007.09236","kind":"arxiv","version":3},"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:dde0881f42410c47727ac3d32eb52bd1eb274530344cb356e62546c55301c8dd","target":"record","created_at":"2026-07-05T02:59:53Z","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":"8566df0c7a90ab4f169a6916c7cd563536c09c0e4e46de98d57ed10e4e4094e0","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-07-17T21:11:01Z","title_canon_sha256":"2d548b4eccaae61a3001a69d0e0a1974f50aff7e26c26e7a5eb08d938aaacba2"},"schema_version":"1.0","source":{"id":"2007.09236","kind":"arxiv","version":3}},"canonical_sha256":"b878583e7e5afb149ed0610db0eea352c3b51741d8e76d0f9a2f30635c45a594","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b878583e7e5afb149ed0610db0eea352c3b51741d8e76d0f9a2f30635c45a594","first_computed_at":"2026-07-05T02:59:53.498230Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:59:53.498230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H5+h9ZSShqntvyAGWRjJJRu8fX4JLeDXBUTucC5rGkw9H19F+umzT9juYQGh/m+IZTy4bGM783lQqyQpDBaAAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:59:53.498721Z","signed_message":"canonical_sha256_bytes"},"source_id":"2007.09236","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dde0881f42410c47727ac3d32eb52bd1eb274530344cb356e62546c55301c8dd","sha256:4ffc6f8c582162d880ca724b587c4142f23ee1a719cb388bbb8e94c9325ec298"],"state_sha256":"c84d60321b1d377ecff64b97d920b7b4a14a1ced66e2652917458b9159d20b01"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c5yOnPZG9R6jM4NWHU+8JZmmUbad7XGPUlLN1SWLbfbAmHBWJpRQQX1iPPYCyPX4W66hklugaPtSpNfAU2WRBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:40:53.943910Z","bundle_sha256":"7c49ffa4fca35741ff919268785877a5c0ce1b5308a1ead3d7db9fa7724faeb5"}}