{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:C23Q5PIBFLHKKJTUEI6WCYH4W3","short_pith_number":"pith:C23Q5PIB","schema_version":"1.0","canonical_sha256":"16b70ebd012acea52674223d6160fcb6d4e3436e49a28754b8137f23841d56a5","source":{"kind":"arxiv","id":"2606.25627","version":1},"attestation_state":"computed","paper":{"title":"TL++: Accuracy and Privacy Preserving Traversal Learning for Distributed Intelligent Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Erdenebileg Batbaatar, Young Yoon","submitted_at":"2026-06-24T09:34:27Z","abstract_excerpt":"Distributed intelligent systems increasingly need to train across data silos without centralizing raw data. Federated learning keeps data local but can suffer under heterogeneous partitions and requires repeated full-model exchange. Split learning reduces communication through cut-layer activations, but standard protocols generally do not recover centralized mini-batch gradient behavior and may expose activations and gradients in plaintext. We present TL++, a two-mode traversal-learning framework that constructs virtual batches across nodes to recover centralized mini-batch gradient behavior u"},"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":"2606.25627","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-24T09:34:27Z","cross_cats_sorted":["cs.AI","cs.CR","cs.DC"],"title_canon_sha256":"b466f0c31032c5faaa541b01ab159adbaadf6bbd6c07b5bfa2955d937c6d26f2","abstract_canon_sha256":"06fc8b15d7fa110af1d655d1722a0892916f1f97c171f4bcbb683e859a356e5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:10.828178Z","signature_b64":"bjjBGOl20Winx8tm9Iiru+mHtig1bWPVJgQJK7/C9R/GI1DOkz5I751Jefa69f1nvkhixH78Mbu3anXAy9NsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16b70ebd012acea52674223d6160fcb6d4e3436e49a28754b8137f23841d56a5","last_reissued_at":"2026-06-25T01:18:10.827731Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:10.827731Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TL++: Accuracy and Privacy Preserving Traversal Learning for Distributed Intelligent Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.DC"],"primary_cat":"cs.LG","authors_text":"Erdenebileg Batbaatar, Young Yoon","submitted_at":"2026-06-24T09:34:27Z","abstract_excerpt":"Distributed intelligent systems increasingly need to train across data silos without centralizing raw data. Federated learning keeps data local but can suffer under heterogeneous partitions and requires repeated full-model exchange. Split learning reduces communication through cut-layer activations, but standard protocols generally do not recover centralized mini-batch gradient behavior and may expose activations and gradients in plaintext. We present TL++, a two-mode traversal-learning framework that constructs virtual batches across nodes to recover centralized mini-batch gradient behavior u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25627","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/2606.25627/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":"2606.25627","created_at":"2026-06-25T01:18:10.827791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25627v1","created_at":"2026-06-25T01:18:10.827791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25627","created_at":"2026-06-25T01:18:10.827791+00:00"},{"alias_kind":"pith_short_12","alias_value":"C23Q5PIBFLHK","created_at":"2026-06-25T01:18:10.827791+00:00"},{"alias_kind":"pith_short_16","alias_value":"C23Q5PIBFLHKKJTU","created_at":"2026-06-25T01:18:10.827791+00:00"},{"alias_kind":"pith_short_8","alias_value":"C23Q5PIB","created_at":"2026-06-25T01:18:10.827791+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C23Q5PIBFLHKKJTUEI6WCYH4W3","json":"https://pith.science/pith/C23Q5PIBFLHKKJTUEI6WCYH4W3.json","graph_json":"https://pith.science/api/pith-number/C23Q5PIBFLHKKJTUEI6WCYH4W3/graph.json","events_json":"https://pith.science/api/pith-number/C23Q5PIBFLHKKJTUEI6WCYH4W3/events.json","paper":"https://pith.science/paper/C23Q5PIB"},"agent_actions":{"view_html":"https://pith.science/pith/C23Q5PIBFLHKKJTUEI6WCYH4W3","download_json":"https://pith.science/pith/C23Q5PIBFLHKKJTUEI6WCYH4W3.json","view_paper":"https://pith.science/paper/C23Q5PIB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25627&json=true","fetch_graph":"https://pith.science/api/pith-number/C23Q5PIBFLHKKJTUEI6WCYH4W3/graph.json","fetch_events":"https://pith.science/api/pith-number/C23Q5PIBFLHKKJTUEI6WCYH4W3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C23Q5PIBFLHKKJTUEI6WCYH4W3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C23Q5PIBFLHKKJTUEI6WCYH4W3/action/storage_attestation","attest_author":"https://pith.science/pith/C23Q5PIBFLHKKJTUEI6WCYH4W3/action/author_attestation","sign_citation":"https://pith.science/pith/C23Q5PIBFLHKKJTUEI6WCYH4W3/action/citation_signature","submit_replication":"https://pith.science/pith/C23Q5PIBFLHKKJTUEI6WCYH4W3/action/replication_record"}},"created_at":"2026-06-25T01:18:10.827791+00:00","updated_at":"2026-06-25T01:18:10.827791+00:00"}