{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FBLFGSSVSCZOIA7NE5QTXDEPE2","short_pith_number":"pith:FBLFGSSV","canonical_record":{"source":{"id":"2303.04887","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-08T20:52:57Z","cross_cats_sorted":[],"title_canon_sha256":"f75f46c732cec0648f9977fcc6bd7544cd58ed6be1fad117317958a272b01172","abstract_canon_sha256":"f752ba49a7ded805ef40d2cb47911dd5f3e85b1b516805719a8d9417b412eb61"},"schema_version":"1.0"},"canonical_sha256":"2856534a5590b2e403ed27613b8c8f26bf7b8837088cab4ffee336a0da8fbf38","source":{"kind":"arxiv","id":"2303.04887","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.04887","created_at":"2026-07-05T12:02:31Z"},{"alias_kind":"arxiv_version","alias_value":"2303.04887v3","created_at":"2026-07-05T12:02:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04887","created_at":"2026-07-05T12:02:31Z"},{"alias_kind":"pith_short_12","alias_value":"FBLFGSSVSCZO","created_at":"2026-07-05T12:02:31Z"},{"alias_kind":"pith_short_16","alias_value":"FBLFGSSVSCZOIA7N","created_at":"2026-07-05T12:02:31Z"},{"alias_kind":"pith_short_8","alias_value":"FBLFGSSV","created_at":"2026-07-05T12:02:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FBLFGSSVSCZOIA7NE5QTXDEPE2","target":"record","payload":{"canonical_record":{"source":{"id":"2303.04887","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-08T20:52:57Z","cross_cats_sorted":[],"title_canon_sha256":"f75f46c732cec0648f9977fcc6bd7544cd58ed6be1fad117317958a272b01172","abstract_canon_sha256":"f752ba49a7ded805ef40d2cb47911dd5f3e85b1b516805719a8d9417b412eb61"},"schema_version":"1.0"},"canonical_sha256":"2856534a5590b2e403ed27613b8c8f26bf7b8837088cab4ffee336a0da8fbf38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:31.564361Z","signature_b64":"Lep2zdiz6S719GluwSW0xXLQYeg8lboEKwpKHqeqA7xQ28mhl6ATZcHJaQ9ybACFweMK7ATpvbBS3M7wCmGsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2856534a5590b2e403ed27613b8c8f26bf7b8837088cab4ffee336a0da8fbf38","last_reissued_at":"2026-07-05T12:02:31.563883Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:31.563883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.04887","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":"2026-07-05T12:02:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RCrPwh/swXzfF03v34pNcWXZ0Ab/43k2H0L0GOGF79upOhej6tGXBFi03kc5yCsfnlpEv0cQNt7ntB+iIYQuAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:20:23.200470Z"},"content_sha256":"258d129b613a81773f1b331de8b86f5b66fa0369eba1456ccead53d8aeb7481a","schema_version":"1.0","event_id":"sha256:258d129b613a81773f1b331de8b86f5b66fa0369eba1456ccead53d8aeb7481a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FBLFGSSVSCZOIA7NE5QTXDEPE2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Memory-adaptive Depth-wise Heterogeneous Federated Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Xing, Hongyi Wang, Kai Zhang, Lichao Sun, Xun Chen, Yutong Dai","submitted_at":"2023-03-08T20:52:57Z","abstract_excerpt":"Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data. However, the presence of heterogeneous devices in federated learning, such as mobile phones and IoT devices with varying memory capabilities, would limit the scale and hence the performance of the model could be trained. The mainstream approaches to address memory limitations focus on width-slimming techniques, where different clients train subnetworks with reduced widths locally and then the server aggregates the subnetworks. The global model produced from t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04887","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/2303.04887/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":"2026-07-05T12:02:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A+bOC4PCWaH3mF4d1azlHlZaLzARfNCmcgOSUleJDBTjsMk6WEhVYje45GUAlCJNRhP9KUxZWIM/bkn3esUtDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T05:20:23.201256Z"},"content_sha256":"0d2ce9286a8d3a34e82fc52cf43db2c27a1eb227e13fbef5730f66ce2ece39d4","schema_version":"1.0","event_id":"sha256:0d2ce9286a8d3a34e82fc52cf43db2c27a1eb227e13fbef5730f66ce2ece39d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FBLFGSSVSCZOIA7NE5QTXDEPE2/bundle.json","state_url":"https://pith.science/pith/FBLFGSSVSCZOIA7NE5QTXDEPE2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FBLFGSSVSCZOIA7NE5QTXDEPE2/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":"2026-08-06T05:20:23Z","links":{"resolver":"https://pith.science/pith/FBLFGSSVSCZOIA7NE5QTXDEPE2","bundle":"https://pith.science/pith/FBLFGSSVSCZOIA7NE5QTXDEPE2/bundle.json","state":"https://pith.science/pith/FBLFGSSVSCZOIA7NE5QTXDEPE2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FBLFGSSVSCZOIA7NE5QTXDEPE2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FBLFGSSVSCZOIA7NE5QTXDEPE2","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":"f752ba49a7ded805ef40d2cb47911dd5f3e85b1b516805719a8d9417b412eb61","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-08T20:52:57Z","title_canon_sha256":"f75f46c732cec0648f9977fcc6bd7544cd58ed6be1fad117317958a272b01172"},"schema_version":"1.0","source":{"id":"2303.04887","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.04887","created_at":"2026-07-05T12:02:31Z"},{"alias_kind":"arxiv_version","alias_value":"2303.04887v3","created_at":"2026-07-05T12:02:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.04887","created_at":"2026-07-05T12:02:31Z"},{"alias_kind":"pith_short_12","alias_value":"FBLFGSSVSCZO","created_at":"2026-07-05T12:02:31Z"},{"alias_kind":"pith_short_16","alias_value":"FBLFGSSVSCZOIA7N","created_at":"2026-07-05T12:02:31Z"},{"alias_kind":"pith_short_8","alias_value":"FBLFGSSV","created_at":"2026-07-05T12:02:31Z"}],"graph_snapshots":[{"event_id":"sha256:0d2ce9286a8d3a34e82fc52cf43db2c27a1eb227e13fbef5730f66ce2ece39d4","target":"graph","created_at":"2026-07-05T12:02:31Z","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/2303.04887/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated learning is a promising paradigm that allows multiple clients to collaboratively train a model without sharing the local data. However, the presence of heterogeneous devices in federated learning, such as mobile phones and IoT devices with varying memory capabilities, would limit the scale and hence the performance of the model could be trained. The mainstream approaches to address memory limitations focus on width-slimming techniques, where different clients train subnetworks with reduced widths locally and then the server aggregates the subnetworks. The global model produced from t","authors_text":"Eric Xing, Hongyi Wang, Kai Zhang, Lichao Sun, Xun Chen, Yutong Dai","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-08T20:52:57Z","title":"Memory-adaptive Depth-wise Heterogeneous Federated Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.04887","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":"sha256:258d129b613a81773f1b331de8b86f5b66fa0369eba1456ccead53d8aeb7481a","target":"record","created_at":"2026-07-05T12:02:31Z","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":"f752ba49a7ded805ef40d2cb47911dd5f3e85b1b516805719a8d9417b412eb61","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-08T20:52:57Z","title_canon_sha256":"f75f46c732cec0648f9977fcc6bd7544cd58ed6be1fad117317958a272b01172"},"schema_version":"1.0","source":{"id":"2303.04887","kind":"arxiv","version":3}},"canonical_sha256":"2856534a5590b2e403ed27613b8c8f26bf7b8837088cab4ffee336a0da8fbf38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2856534a5590b2e403ed27613b8c8f26bf7b8837088cab4ffee336a0da8fbf38","first_computed_at":"2026-07-05T12:02:31.563883Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:31.563883Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Lep2zdiz6S719GluwSW0xXLQYeg8lboEKwpKHqeqA7xQ28mhl6ATZcHJaQ9ybACFweMK7ATpvbBS3M7wCmGsAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:31.564361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.04887","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:258d129b613a81773f1b331de8b86f5b66fa0369eba1456ccead53d8aeb7481a","sha256:0d2ce9286a8d3a34e82fc52cf43db2c27a1eb227e13fbef5730f66ce2ece39d4"],"state_sha256":"fa6ef98a496dc9f54f0e470f5ddf37ba7102733f046b062da5003b26bbe80a21"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uT3EbEtJT924rQYE/N+kkh5kxe+fW6qg0iora6Imr/2sDqmfBoIf7ar62vMeCqNwYmFC3kD/MWdBRVGTk+vuCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T05:20:23.205192Z","bundle_sha256":"8d8f2eb3e6bfca54bb5036357050e93e152de2dc30aec91b3181983fdcd4acc8"}}