{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZZOR6IQFUZ7XSMS2REYMHJJMY4","short_pith_number":"pith:ZZOR6IQF","canonical_record":{"source":{"id":"2110.09695","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T02:26:35Z","cross_cats_sorted":[],"title_canon_sha256":"5a82b6b28d6f543f3b310eb5ecbf533bf7909c75c214525087eac8d952faa62f","abstract_canon_sha256":"afc2960691478debb11dd4377e8d4b466abb8f67798485cff6bc846a8b338369"},"schema_version":"1.0"},"canonical_sha256":"ce5d1f2205a67f79325a8930c3a52cc734ff8e502dd7a3b1eedddeff958b6ba9","source":{"kind":"arxiv","id":"2110.09695","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.09695","created_at":"2026-07-05T03:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2110.09695v1","created_at":"2026-07-05T03:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09695","created_at":"2026-07-05T03:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"ZZOR6IQFUZ7X","created_at":"2026-07-05T03:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"ZZOR6IQFUZ7XSMS2","created_at":"2026-07-05T03:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"ZZOR6IQF","created_at":"2026-07-05T03:23:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZZOR6IQFUZ7XSMS2REYMHJJMY4","target":"record","payload":{"canonical_record":{"source":{"id":"2110.09695","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T02:26:35Z","cross_cats_sorted":[],"title_canon_sha256":"5a82b6b28d6f543f3b310eb5ecbf533bf7909c75c214525087eac8d952faa62f","abstract_canon_sha256":"afc2960691478debb11dd4377e8d4b466abb8f67798485cff6bc846a8b338369"},"schema_version":"1.0"},"canonical_sha256":"ce5d1f2205a67f79325a8930c3a52cc734ff8e502dd7a3b1eedddeff958b6ba9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:23:57.991929Z","signature_b64":"2+wq/zXV9CULuPPBqjwS+DCF/Qg5kNKo/4JjS5rNWCXEdYYSHubadkq7NXwxhFuhYI18yKocH/gqySTCHGFjBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce5d1f2205a67f79325a8930c3a52cc734ff8e502dd7a3b1eedddeff958b6ba9","last_reissued_at":"2026-07-05T03:23:57.991398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:23:57.991398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.09695","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":"2026-07-05T03:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uBFtaXIYKLQnSXa5I3yqdjybiwMX9GTEzMkWn2seMvr7GgFJ+7Wk0CGtL5kNkSL7lC1lhk4wmWWC5edS5hfeAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T20:32:59.398765Z"},"content_sha256":"8f11893dd1b4b3df54f91d6d6363adcd73d9049b5c6f0207ff1a684ac6c583bc","schema_version":"1.0","event_id":"sha256:8f11893dd1b4b3df54f91d6d6363adcd73d9049b5c6f0207ff1a684ac6c583bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZZOR6IQFUZ7XSMS2REYMHJJMY4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dimitrios Dimitriadis, Kenichi Kumatani, Tae Jin Park","submitted_at":"2021-10-19T02:26:35Z","abstract_excerpt":"Federated Learning is a fast growing area of ML where the training datasets are extremely distributed, all while dynamically changing over time. Models need to be trained on clients' devices without any guarantees for either homogeneity or stationarity of the local private data. The need for continual training has also risen, due to the ever-increasing production of in-task data. However, pursuing both directions at the same time is challenging, since client data privacy is a major constraint, especially for rehearsal methods. Herein, we propose a novel algorithm to address the incremental lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09695","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/2110.09695/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":"2026-07-05T03:23:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KKr9ZCkDu+7q/9tWcZCJQI83QFGoS5qpQrswvLrX2T1fVw7OToAltAtRl6GNVWkWdR5drZtie2IV/qS2BZAIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T20:32:59.399140Z"},"content_sha256":"b6fa35919747e5268b30d099ccaa681ce5acb98a5a7e7f5920e84a25c93a3092","schema_version":"1.0","event_id":"sha256:b6fa35919747e5268b30d099ccaa681ce5acb98a5a7e7f5920e84a25c93a3092"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZZOR6IQFUZ7XSMS2REYMHJJMY4/bundle.json","state_url":"https://pith.science/pith/ZZOR6IQFUZ7XSMS2REYMHJJMY4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZZOR6IQFUZ7XSMS2REYMHJJMY4/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":"2026-07-24T20:32:59Z","links":{"resolver":"https://pith.science/pith/ZZOR6IQFUZ7XSMS2REYMHJJMY4","bundle":"https://pith.science/pith/ZZOR6IQFUZ7XSMS2REYMHJJMY4/bundle.json","state":"https://pith.science/pith/ZZOR6IQFUZ7XSMS2REYMHJJMY4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZZOR6IQFUZ7XSMS2REYMHJJMY4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZZOR6IQFUZ7XSMS2REYMHJJMY4","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":"afc2960691478debb11dd4377e8d4b466abb8f67798485cff6bc846a8b338369","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T02:26:35Z","title_canon_sha256":"5a82b6b28d6f543f3b310eb5ecbf533bf7909c75c214525087eac8d952faa62f"},"schema_version":"1.0","source":{"id":"2110.09695","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.09695","created_at":"2026-07-05T03:23:57Z"},{"alias_kind":"arxiv_version","alias_value":"2110.09695v1","created_at":"2026-07-05T03:23:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.09695","created_at":"2026-07-05T03:23:57Z"},{"alias_kind":"pith_short_12","alias_value":"ZZOR6IQFUZ7X","created_at":"2026-07-05T03:23:57Z"},{"alias_kind":"pith_short_16","alias_value":"ZZOR6IQFUZ7XSMS2","created_at":"2026-07-05T03:23:57Z"},{"alias_kind":"pith_short_8","alias_value":"ZZOR6IQF","created_at":"2026-07-05T03:23:57Z"}],"graph_snapshots":[{"event_id":"sha256:b6fa35919747e5268b30d099ccaa681ce5acb98a5a7e7f5920e84a25c93a3092","target":"graph","created_at":"2026-07-05T03:23:57Z","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/2110.09695/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated Learning is a fast growing area of ML where the training datasets are extremely distributed, all while dynamically changing over time. Models need to be trained on clients' devices without any guarantees for either homogeneity or stationarity of the local private data. The need for continual training has also risen, due to the ever-increasing production of in-task data. However, pursuing both directions at the same time is challenging, since client data privacy is a major constraint, especially for rehearsal methods. Herein, we propose a novel algorithm to address the incremental lea","authors_text":"Dimitrios Dimitriadis, Kenichi Kumatani, Tae Jin Park","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T02:26:35Z","title":"Tackling Dynamics in Federated Incremental Learning with Variational Embedding Rehearsal"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.09695","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":"sha256:8f11893dd1b4b3df54f91d6d6363adcd73d9049b5c6f0207ff1a684ac6c583bc","target":"record","created_at":"2026-07-05T03:23:57Z","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":"afc2960691478debb11dd4377e8d4b466abb8f67798485cff6bc846a8b338369","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T02:26:35Z","title_canon_sha256":"5a82b6b28d6f543f3b310eb5ecbf533bf7909c75c214525087eac8d952faa62f"},"schema_version":"1.0","source":{"id":"2110.09695","kind":"arxiv","version":1}},"canonical_sha256":"ce5d1f2205a67f79325a8930c3a52cc734ff8e502dd7a3b1eedddeff958b6ba9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce5d1f2205a67f79325a8930c3a52cc734ff8e502dd7a3b1eedddeff958b6ba9","first_computed_at":"2026-07-05T03:23:57.991398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:23:57.991398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2+wq/zXV9CULuPPBqjwS+DCF/Qg5kNKo/4JjS5rNWCXEdYYSHubadkq7NXwxhFuhYI18yKocH/gqySTCHGFjBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:23:57.991929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.09695","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8f11893dd1b4b3df54f91d6d6363adcd73d9049b5c6f0207ff1a684ac6c583bc","sha256:b6fa35919747e5268b30d099ccaa681ce5acb98a5a7e7f5920e84a25c93a3092"],"state_sha256":"3cbe60bccf378607724f23bd988bde5254c9dc6cd9f026806aa02d29c3241937"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ES+urODimVgj5yp6/zNLYStQrHBZ+W+CRmMZ8cTpEsyQK6a+m0wUqcpTLdzIOIaGlNHkhGGPuOa4TJ1SDp/OBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T20:32:59.401614Z","bundle_sha256":"d38c9c6cd3a0845e3e35418b0947850eb5f26f5ce410e14064e346a16668beba"}}