{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:SDTUT3PA7JTLBGHFBHBRSBAKE3","short_pith_number":"pith:SDTUT3PA","schema_version":"1.0","canonical_sha256":"90e749ede0fa66b098e509c319040a26dd3cfdfcf5f593ca6e96f04aaecc3cd3","source":{"kind":"arxiv","id":"2008.04137","version":1},"attestation_state":"computed","paper":{"title":"SplitNN-driven Vertical Partitioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Singh, Alberto Roman, Eduardo Mugica, Iker Ceballos, Praneeth Vepakomma, Ramesh Raskar, Vivek Sharma","submitted_at":"2020-08-07T17:41:42Z","abstract_excerpt":"In this work, we introduce SplitNN-driven Vertical Partitioning, a configuration of a distributed deep learning method called SplitNN to facilitate learning from vertically distributed features. SplitNN does not share raw data or model details with collaborating institutions. The proposed configuration allows training among institutions holding diverse sources of data without the need of complex encryption algorithms or secure computation protocols. We evaluate several configurations to merge the outputs of the split models, and compare performance and resource efficiency. The method is flexib"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2008.04137","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-08-07T17:41:42Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"850180e261a8f68408e929c37bd695241330c0073bc58c6f5258d175a7f1d700","abstract_canon_sha256":"80a6aeaba8cb2b2863e18dc70b1420100aa8bea69b997d91dd684a6bdc4db3b3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:00.184028Z","signature_b64":"PyfheOcghC40e+mG2/UKdWsE6aDA4mKeQymhLfjfggfyNGBtXIDnGJ8Cfi2welEyThsTHV4AJjnmxemfKIZaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90e749ede0fa66b098e509c319040a26dd3cfdfcf5f593ca6e96f04aaecc3cd3","last_reissued_at":"2026-07-05T01:26:00.183482Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:00.183482Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SplitNN-driven Vertical Partitioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Abhishek Singh, Alberto Roman, Eduardo Mugica, Iker Ceballos, Praneeth Vepakomma, Ramesh Raskar, Vivek Sharma","submitted_at":"2020-08-07T17:41:42Z","abstract_excerpt":"In this work, we introduce SplitNN-driven Vertical Partitioning, a configuration of a distributed deep learning method called SplitNN to facilitate learning from vertically distributed features. SplitNN does not share raw data or model details with collaborating institutions. The proposed configuration allows training among institutions holding diverse sources of data without the need of complex encryption algorithms or secure computation protocols. We evaluate several configurations to merge the outputs of the split models, and compare performance and resource efficiency. The method is flexib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.04137","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/2008.04137/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2008.04137","created_at":"2026-07-05T01:26:00.183542+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.04137v1","created_at":"2026-07-05T01:26:00.183542+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.04137","created_at":"2026-07-05T01:26:00.183542+00:00"},{"alias_kind":"pith_short_12","alias_value":"SDTUT3PA7JTL","created_at":"2026-07-05T01:26:00.183542+00:00"},{"alias_kind":"pith_short_16","alias_value":"SDTUT3PA7JTLBGHF","created_at":"2026-07-05T01:26:00.183542+00:00"},{"alias_kind":"pith_short_8","alias_value":"SDTUT3PA","created_at":"2026-07-05T01:26:00.183542+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.12708","citing_title":"Mixture of Predefined Experts: Maximizing Data Usage on Vertical Federated Learning","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SDTUT3PA7JTLBGHFBHBRSBAKE3","json":"https://pith.science/pith/SDTUT3PA7JTLBGHFBHBRSBAKE3.json","graph_json":"https://pith.science/api/pith-number/SDTUT3PA7JTLBGHFBHBRSBAKE3/graph.json","events_json":"https://pith.science/api/pith-number/SDTUT3PA7JTLBGHFBHBRSBAKE3/events.json","paper":"https://pith.science/paper/SDTUT3PA"},"agent_actions":{"view_html":"https://pith.science/pith/SDTUT3PA7JTLBGHFBHBRSBAKE3","download_json":"https://pith.science/pith/SDTUT3PA7JTLBGHFBHBRSBAKE3.json","view_paper":"https://pith.science/paper/SDTUT3PA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.04137&json=true","fetch_graph":"https://pith.science/api/pith-number/SDTUT3PA7JTLBGHFBHBRSBAKE3/graph.json","fetch_events":"https://pith.science/api/pith-number/SDTUT3PA7JTLBGHFBHBRSBAKE3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SDTUT3PA7JTLBGHFBHBRSBAKE3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SDTUT3PA7JTLBGHFBHBRSBAKE3/action/storage_attestation","attest_author":"https://pith.science/pith/SDTUT3PA7JTLBGHFBHBRSBAKE3/action/author_attestation","sign_citation":"https://pith.science/pith/SDTUT3PA7JTLBGHFBHBRSBAKE3/action/citation_signature","submit_replication":"https://pith.science/pith/SDTUT3PA7JTLBGHFBHBRSBAKE3/action/replication_record"}},"created_at":"2026-07-05T01:26:00.183542+00:00","updated_at":"2026-07-05T01:26:00.183542+00:00"}