{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:M7JJLD7MZF2IAUJHEDRKFTKWWG","short_pith_number":"pith:M7JJLD7M","canonical_record":{"source":{"id":"2111.14655","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-29T16:11:09Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"377f3a738be37b9a0071ea783939000c1082981a0c8a578149e9009df1c41a30","abstract_canon_sha256":"45fcff670f455edf80c6192579cab302e59f73cb14c58150a24698f4b0d02fda"},"schema_version":"1.0"},"canonical_sha256":"67d2958fecc97480512720e2a2cd56b1b05a767f3158fb62dbcc6b1c40bfdce2","source":{"kind":"arxiv","id":"2111.14655","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.14655","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"arxiv_version","alias_value":"2111.14655v2","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14655","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"pith_short_12","alias_value":"M7JJLD7MZF2I","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"pith_short_16","alias_value":"M7JJLD7MZF2IAUJH","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"pith_short_8","alias_value":"M7JJLD7M","created_at":"2026-07-05T04:26:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:M7JJLD7MZF2IAUJHEDRKFTKWWG","target":"record","payload":{"canonical_record":{"source":{"id":"2111.14655","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-29T16:11:09Z","cross_cats_sorted":["cs.AI","cs.DC"],"title_canon_sha256":"377f3a738be37b9a0071ea783939000c1082981a0c8a578149e9009df1c41a30","abstract_canon_sha256":"45fcff670f455edf80c6192579cab302e59f73cb14c58150a24698f4b0d02fda"},"schema_version":"1.0"},"canonical_sha256":"67d2958fecc97480512720e2a2cd56b1b05a767f3158fb62dbcc6b1c40bfdce2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:26:34.932357Z","signature_b64":"KPjGKDhW1IMLHZ5OUZyCh67haqYlBkfC46+ENx5cu6JoX/bdnTys53pPEh/3XUWUXLM35ZJqe1tdMIb8uT2oCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67d2958fecc97480512720e2a2cd56b1b05a767f3158fb62dbcc6b1c40bfdce2","last_reissued_at":"2026-07-05T04:26:34.931905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:26:34.931905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2111.14655","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":"2026-07-05T04:26:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NbRLyCN26WLWOYfEforTwCEulSUJHhBFusVW1oTuerR55JEcpgQ+U8JImCjgl0tjSm88mwybCFwz17uMTj8PCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:44:32.160568Z"},"content_sha256":"3860c8f1e8de2a64c76e9576c23cf56d77776e14fee10ec4c64f50efdf63077e","schema_version":"1.0","event_id":"sha256:3860c8f1e8de2a64c76e9576c23cf56d77776e14fee10ec4c64f50efdf63077e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:M7JJLD7MZF2IAUJHEDRKFTKWWG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DC"],"primary_cat":"cs.LG","authors_text":"Dezhong Yao, Hai Jin, Lichao Sun, Michael J O'Neill, Wanning Pan, Yao Wan, Yutong Dai","submitted_at":"2021-11-29T16:11:09Z","abstract_excerpt":"One underlying assumption of recent federated learning (FL) paradigms is that all local models usually share the same network architecture and size, which becomes impractical for devices with different hardware resources. A scalable federated learning framework should address the heterogeneity that clients have different computing capacities and communication capabilities. To this end, this paper proposes FedHM, a novel heterogeneous federated model compression framework, distributing the heterogeneous low-rank models to clients and then aggregating them into a full-rank model. Our solution en"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14655","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/2111.14655/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":"2026-07-05T04:26:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dqgWuvu4+uO5PzZ3XmjXum0iGDkTi7KQ5JfHpvR/TVwiYfqF1I7HuvVVKAGpYx3tHXax5d2XiytsnfRg88OtDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T16:44:32.161076Z"},"content_sha256":"8a1e9b71a6a39e78d7b4207f9daf775332b3ab9a98858fb8061b1bf9e8d0d623","schema_version":"1.0","event_id":"sha256:8a1e9b71a6a39e78d7b4207f9daf775332b3ab9a98858fb8061b1bf9e8d0d623"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M7JJLD7MZF2IAUJHEDRKFTKWWG/bundle.json","state_url":"https://pith.science/pith/M7JJLD7MZF2IAUJHEDRKFTKWWG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M7JJLD7MZF2IAUJHEDRKFTKWWG/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":"2026-07-31T16:44:32Z","links":{"resolver":"https://pith.science/pith/M7JJLD7MZF2IAUJHEDRKFTKWWG","bundle":"https://pith.science/pith/M7JJLD7MZF2IAUJHEDRKFTKWWG/bundle.json","state":"https://pith.science/pith/M7JJLD7MZF2IAUJHEDRKFTKWWG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M7JJLD7MZF2IAUJHEDRKFTKWWG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:M7JJLD7MZF2IAUJHEDRKFTKWWG","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":"45fcff670f455edf80c6192579cab302e59f73cb14c58150a24698f4b0d02fda","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-29T16:11:09Z","title_canon_sha256":"377f3a738be37b9a0071ea783939000c1082981a0c8a578149e9009df1c41a30"},"schema_version":"1.0","source":{"id":"2111.14655","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.14655","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"arxiv_version","alias_value":"2111.14655v2","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.14655","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"pith_short_12","alias_value":"M7JJLD7MZF2I","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"pith_short_16","alias_value":"M7JJLD7MZF2IAUJH","created_at":"2026-07-05T04:26:34Z"},{"alias_kind":"pith_short_8","alias_value":"M7JJLD7M","created_at":"2026-07-05T04:26:34Z"}],"graph_snapshots":[{"event_id":"sha256:8a1e9b71a6a39e78d7b4207f9daf775332b3ab9a98858fb8061b1bf9e8d0d623","target":"graph","created_at":"2026-07-05T04:26:34Z","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/2111.14655/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One underlying assumption of recent federated learning (FL) paradigms is that all local models usually share the same network architecture and size, which becomes impractical for devices with different hardware resources. A scalable federated learning framework should address the heterogeneity that clients have different computing capacities and communication capabilities. To this end, this paper proposes FedHM, a novel heterogeneous federated model compression framework, distributing the heterogeneous low-rank models to clients and then aggregating them into a full-rank model. Our solution en","authors_text":"Dezhong Yao, Hai Jin, Lichao Sun, Michael J O'Neill, Wanning Pan, Yao Wan, Yutong Dai","cross_cats":["cs.AI","cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-29T16:11:09Z","title":"FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.14655","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":"sha256:3860c8f1e8de2a64c76e9576c23cf56d77776e14fee10ec4c64f50efdf63077e","target":"record","created_at":"2026-07-05T04:26:34Z","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":"45fcff670f455edf80c6192579cab302e59f73cb14c58150a24698f4b0d02fda","cross_cats_sorted":["cs.AI","cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-11-29T16:11:09Z","title_canon_sha256":"377f3a738be37b9a0071ea783939000c1082981a0c8a578149e9009df1c41a30"},"schema_version":"1.0","source":{"id":"2111.14655","kind":"arxiv","version":2}},"canonical_sha256":"67d2958fecc97480512720e2a2cd56b1b05a767f3158fb62dbcc6b1c40bfdce2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67d2958fecc97480512720e2a2cd56b1b05a767f3158fb62dbcc6b1c40bfdce2","first_computed_at":"2026-07-05T04:26:34.931905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:26:34.931905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KPjGKDhW1IMLHZ5OUZyCh67haqYlBkfC46+ENx5cu6JoX/bdnTys53pPEh/3XUWUXLM35ZJqe1tdMIb8uT2oCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:26:34.932357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.14655","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3860c8f1e8de2a64c76e9576c23cf56d77776e14fee10ec4c64f50efdf63077e","sha256:8a1e9b71a6a39e78d7b4207f9daf775332b3ab9a98858fb8061b1bf9e8d0d623"],"state_sha256":"78f5184e2d0125fbf8cc99e15479980dccbe5ed6e85ebb6393c18b76e85b1bef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EjBTCMxN/q7nSDmtJAFxQdAyIAQN4S0+BHwMB1vdDiWHXTb25lmjsk1gOveYgCwkCdH33U7ESWVcsrbspBqWAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T16:44:32.165438Z","bundle_sha256":"1df381705075d2f290c61d4e9aef5e27c7c58f5e57d127d8b0defec0f8bfa3d9"}}