{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TSTL4NTNAWQK2JIUF7SM2HLTBP","short_pith_number":"pith:TSTL4NTN","canonical_record":{"source":{"id":"2004.12088","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-25T08:52:50Z","cross_cats_sorted":[],"title_canon_sha256":"b4ac41849eea585664f78b9232e3b8a4d3750a40d79a448cbabc86ccfad4e206","abstract_canon_sha256":"991fa16e040927615c0ac0c3eaccece7921b84a9b80181a798ad512c2d05ca24"},"schema_version":"1.0"},"canonical_sha256":"9ca6be366d05a0ad25142fe4cd1d730bdaf8a28e4aba975dc2c635914ef2c5c5","source":{"kind":"arxiv","id":"2004.12088","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.12088","created_at":"2026-07-05T03:57:39Z"},{"alias_kind":"arxiv_version","alias_value":"2004.12088v5","created_at":"2026-07-05T03:57:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12088","created_at":"2026-07-05T03:57:39Z"},{"alias_kind":"pith_short_12","alias_value":"TSTL4NTNAWQK","created_at":"2026-07-05T03:57:39Z"},{"alias_kind":"pith_short_16","alias_value":"TSTL4NTNAWQK2JIU","created_at":"2026-07-05T03:57:39Z"},{"alias_kind":"pith_short_8","alias_value":"TSTL4NTN","created_at":"2026-07-05T03:57:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TSTL4NTNAWQK2JIUF7SM2HLTBP","target":"record","payload":{"canonical_record":{"source":{"id":"2004.12088","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-25T08:52:50Z","cross_cats_sorted":[],"title_canon_sha256":"b4ac41849eea585664f78b9232e3b8a4d3750a40d79a448cbabc86ccfad4e206","abstract_canon_sha256":"991fa16e040927615c0ac0c3eaccece7921b84a9b80181a798ad512c2d05ca24"},"schema_version":"1.0"},"canonical_sha256":"9ca6be366d05a0ad25142fe4cd1d730bdaf8a28e4aba975dc2c635914ef2c5c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:57:39.202985Z","signature_b64":"2gxdkMf0y6r0vZwUk8FtxMDbn8cuZmyET2muoQcaZsPoF9NNzFXQOykRs1oQiFZezmugaEv64cfqMSlXtyW+Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ca6be366d05a0ad25142fe4cd1d730bdaf8a28e4aba975dc2c635914ef2c5c5","last_reissued_at":"2026-07-05T03:57:39.202505Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:57:39.202505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.12088","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:57:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"enOv/azbR7UQpI/wB1uMH2Z4eeBgb87QyWieH97Kc9GmrowQvPgX/PwJOaBzwiDht3rLr7LXriOiSGDOioL6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:18:17.047484Z"},"content_sha256":"27b6dd7439b14daa5490797686061ae8e29b3b3eeeac996684d300aeeefa1eac","schema_version":"1.0","event_id":"sha256:27b6dd7439b14daa5490797686061ae8e29b3b3eeeac996684d300aeeefa1eac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TSTL4NTNAWQK2JIUF7SM2HLTBP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SplitFed: When Federated Learning Meets Split Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chandra Thapa, Lichao Sun, M.A.P. Chamikara, Seyit Camtepe","submitted_at":"2020-04-25T08:52:50Z","abstract_excerpt":"Federated learning (FL) and split learning (SL) are two popular distributed machine learning approaches. Both follow a model-to-data scenario; clients train and test machine learning models without sharing raw data. SL provides better model privacy than FL due to the machine learning model architecture split between clients and the server. Moreover, the split model makes SL a better option for resource-constrained environments. However, SL performs slower than FL due to the relay-based training across multiple clients. In this regard, this paper presents a novel approach, named splitfed learni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12088","kind":"arxiv","version":5},"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/2004.12088/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":"2026-07-05T03:57:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"21HkewnL15DPPpjYmBsHC0qwOZgiQ5VidcCBjnzFCB4jOm6ToltJyzKEdBk1Xbl2nIP5KBP9ejQIxKELj6QjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T03:18:17.048262Z"},"content_sha256":"47a0d00c28858cf4393154a224295a15505edbbcd362df1b65b605d4e36647dd","schema_version":"1.0","event_id":"sha256:47a0d00c28858cf4393154a224295a15505edbbcd362df1b65b605d4e36647dd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TSTL4NTNAWQK2JIUF7SM2HLTBP/bundle.json","state_url":"https://pith.science/pith/TSTL4NTNAWQK2JIUF7SM2HLTBP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TSTL4NTNAWQK2JIUF7SM2HLTBP/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":"2026-08-10T03:18:17Z","links":{"resolver":"https://pith.science/pith/TSTL4NTNAWQK2JIUF7SM2HLTBP","bundle":"https://pith.science/pith/TSTL4NTNAWQK2JIUF7SM2HLTBP/bundle.json","state":"https://pith.science/pith/TSTL4NTNAWQK2JIUF7SM2HLTBP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TSTL4NTNAWQK2JIUF7SM2HLTBP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TSTL4NTNAWQK2JIUF7SM2HLTBP","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":"991fa16e040927615c0ac0c3eaccece7921b84a9b80181a798ad512c2d05ca24","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-25T08:52:50Z","title_canon_sha256":"b4ac41849eea585664f78b9232e3b8a4d3750a40d79a448cbabc86ccfad4e206"},"schema_version":"1.0","source":{"id":"2004.12088","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.12088","created_at":"2026-07-05T03:57:39Z"},{"alias_kind":"arxiv_version","alias_value":"2004.12088v5","created_at":"2026-07-05T03:57:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.12088","created_at":"2026-07-05T03:57:39Z"},{"alias_kind":"pith_short_12","alias_value":"TSTL4NTNAWQK","created_at":"2026-07-05T03:57:39Z"},{"alias_kind":"pith_short_16","alias_value":"TSTL4NTNAWQK2JIU","created_at":"2026-07-05T03:57:39Z"},{"alias_kind":"pith_short_8","alias_value":"TSTL4NTN","created_at":"2026-07-05T03:57:39Z"}],"graph_snapshots":[{"event_id":"sha256:47a0d00c28858cf4393154a224295a15505edbbcd362df1b65b605d4e36647dd","target":"graph","created_at":"2026-07-05T03:57:39Z","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/2004.12088/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Federated learning (FL) and split learning (SL) are two popular distributed machine learning approaches. Both follow a model-to-data scenario; clients train and test machine learning models without sharing raw data. SL provides better model privacy than FL due to the machine learning model architecture split between clients and the server. Moreover, the split model makes SL a better option for resource-constrained environments. However, SL performs slower than FL due to the relay-based training across multiple clients. In this regard, this paper presents a novel approach, named splitfed learni","authors_text":"Chandra Thapa, Lichao Sun, M.A.P. Chamikara, Seyit Camtepe","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-25T08:52:50Z","title":"SplitFed: When Federated Learning Meets Split Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.12088","kind":"arxiv","version":5},"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":"sha256:27b6dd7439b14daa5490797686061ae8e29b3b3eeeac996684d300aeeefa1eac","target":"record","created_at":"2026-07-05T03:57:39Z","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":"991fa16e040927615c0ac0c3eaccece7921b84a9b80181a798ad512c2d05ca24","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-04-25T08:52:50Z","title_canon_sha256":"b4ac41849eea585664f78b9232e3b8a4d3750a40d79a448cbabc86ccfad4e206"},"schema_version":"1.0","source":{"id":"2004.12088","kind":"arxiv","version":5}},"canonical_sha256":"9ca6be366d05a0ad25142fe4cd1d730bdaf8a28e4aba975dc2c635914ef2c5c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9ca6be366d05a0ad25142fe4cd1d730bdaf8a28e4aba975dc2c635914ef2c5c5","first_computed_at":"2026-07-05T03:57:39.202505Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:57:39.202505Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2gxdkMf0y6r0vZwUk8FtxMDbn8cuZmyET2muoQcaZsPoF9NNzFXQOykRs1oQiFZezmugaEv64cfqMSlXtyW+Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:57:39.202985Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.12088","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27b6dd7439b14daa5490797686061ae8e29b3b3eeeac996684d300aeeefa1eac","sha256:47a0d00c28858cf4393154a224295a15505edbbcd362df1b65b605d4e36647dd"],"state_sha256":"0ee9b9a654f4fd98a9989fec789acb23affd28578c2b097492a6f05977fc9722"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nJjGpQKJ2c/O0M1XAX6BUdiVCj61OHZ2nuoUF3eZQDJQ3XkuAEmRR8dsCSEdcJrQlqvyZE5P7EIzX0vMx9dOCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T03:18:17.054833Z","bundle_sha256":"70fa4b858b120a5ade8e824014783a2817d65dcc68503eb4f62824b79419c3d3"}}