{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4BMIRKHBQX2CLBTEBCI33GX7PG","short_pith_number":"pith:4BMIRKHB","canonical_record":{"source":{"id":"2412.16669","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-21T15:32:03Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"045ab69ab5bf07c1ccc32c23eb26825ba5a169e6e5ce511521ab07160d1d1dd7","abstract_canon_sha256":"a858e46fbd28cb8d0af91e48aeb2dcb43fae66e413aa8da8848e7ac3b1c211b1"},"schema_version":"1.0"},"canonical_sha256":"e05888a8e185f42586640891bd9aff79a7b338787a467acfe77d25851a59e3b8","source":{"kind":"arxiv","id":"2412.16669","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16669","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16669v1","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16669","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"pith_short_12","alias_value":"4BMIRKHBQX2C","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"pith_short_16","alias_value":"4BMIRKHBQX2CLBTE","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"pith_short_8","alias_value":"4BMIRKHB","created_at":"2026-07-05T09:53:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4BMIRKHBQX2CLBTEBCI33GX7PG","target":"record","payload":{"canonical_record":{"source":{"id":"2412.16669","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-21T15:32:03Z","cross_cats_sorted":["cs.CR"],"title_canon_sha256":"045ab69ab5bf07c1ccc32c23eb26825ba5a169e6e5ce511521ab07160d1d1dd7","abstract_canon_sha256":"a858e46fbd28cb8d0af91e48aeb2dcb43fae66e413aa8da8848e7ac3b1c211b1"},"schema_version":"1.0"},"canonical_sha256":"e05888a8e185f42586640891bd9aff79a7b338787a467acfe77d25851a59e3b8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:11.250192Z","signature_b64":"ZgzEWjvwRc0XGpid4xyOVKQCoMlXWzT/gfYQKTFDDVyR3F+H4ZfEf4Ou4vYKr4Ulp9F1RDXScbIAJbWUWXJuAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e05888a8e185f42586640891bd9aff79a7b338787a467acfe77d25851a59e3b8","last_reissued_at":"2026-07-05T09:53:11.249757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:11.249757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.16669","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:53:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EB78mzXjs5TkMOqCeObVAnK1CaCLm+6Jga0NElPvGvjj/27TdDvUvgN6z6Z5ehWHQJ3qf5L80S1Cha+fhFU/BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:05:07.470085Z"},"content_sha256":"cce327f08d597be34bb58730dd2f07095d137dce37656c933834046a699be9fe","schema_version":"1.0","event_id":"sha256:cce327f08d597be34bb58730dd2f07095d137dce37656c933834046a699be9fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4BMIRKHBQX2CLBTEBCI33GX7PG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR"],"primary_cat":"cs.LG","authors_text":"Aleksandr Beznosikov, Denis Kuznedelev, Marat Mansurov, Max Ryabinin, Philip Zmushko, Ruslan Svirschevski","submitted_at":"2024-12-21T15:32:03Z","abstract_excerpt":"As deep learning models become larger and more expensive, many practitioners turn to fine-tuning APIs. These web services allow fine-tuning a model between two parties: the client that provides the data, and the server that hosts the model. While convenient, these APIs raise a new concern: the data of the client is at risk of privacy breach during the training procedure. This challenge presents an important practical case of vertical federated learning, where the two parties perform parameter-efficient fine-tuning (PEFT) of a large model. In this study, we systematically search for a way to fi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16669","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/2412.16669/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":"2026-07-05T09:53:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2uviSeVc44qjnk0EChtIscXPk0UOFnzif6192is3VlQ8vyPiASLhi7Zn17SJCFncNS84D/JKTTc7f0C8EgsoCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T20:05:07.470637Z"},"content_sha256":"79ec2fb5574b6eaa4d3e4fbf48431c4575e5a93ddd4d64d2388eb5c1678da433","schema_version":"1.0","event_id":"sha256:79ec2fb5574b6eaa4d3e4fbf48431c4575e5a93ddd4d64d2388eb5c1678da433"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4BMIRKHBQX2CLBTEBCI33GX7PG/bundle.json","state_url":"https://pith.science/pith/4BMIRKHBQX2CLBTEBCI33GX7PG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4BMIRKHBQX2CLBTEBCI33GX7PG/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":"2026-08-04T20:05:07Z","links":{"resolver":"https://pith.science/pith/4BMIRKHBQX2CLBTEBCI33GX7PG","bundle":"https://pith.science/pith/4BMIRKHBQX2CLBTEBCI33GX7PG/bundle.json","state":"https://pith.science/pith/4BMIRKHBQX2CLBTEBCI33GX7PG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4BMIRKHBQX2CLBTEBCI33GX7PG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4BMIRKHBQX2CLBTEBCI33GX7PG","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":"a858e46fbd28cb8d0af91e48aeb2dcb43fae66e413aa8da8848e7ac3b1c211b1","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-21T15:32:03Z","title_canon_sha256":"045ab69ab5bf07c1ccc32c23eb26825ba5a169e6e5ce511521ab07160d1d1dd7"},"schema_version":"1.0","source":{"id":"2412.16669","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.16669","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"arxiv_version","alias_value":"2412.16669v1","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.16669","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"pith_short_12","alias_value":"4BMIRKHBQX2C","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"pith_short_16","alias_value":"4BMIRKHBQX2CLBTE","created_at":"2026-07-05T09:53:11Z"},{"alias_kind":"pith_short_8","alias_value":"4BMIRKHB","created_at":"2026-07-05T09:53:11Z"}],"graph_snapshots":[{"event_id":"sha256:79ec2fb5574b6eaa4d3e4fbf48431c4575e5a93ddd4d64d2388eb5c1678da433","target":"graph","created_at":"2026-07-05T09:53:11Z","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/2412.16669/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As deep learning models become larger and more expensive, many practitioners turn to fine-tuning APIs. These web services allow fine-tuning a model between two parties: the client that provides the data, and the server that hosts the model. While convenient, these APIs raise a new concern: the data of the client is at risk of privacy breach during the training procedure. This challenge presents an important practical case of vertical federated learning, where the two parties perform parameter-efficient fine-tuning (PEFT) of a large model. In this study, we systematically search for a way to fi","authors_text":"Aleksandr Beznosikov, Denis Kuznedelev, Marat Mansurov, Max Ryabinin, Philip Zmushko, Ruslan Svirschevski","cross_cats":["cs.CR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.16669","kind":"arxiv","version":1},"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:cce327f08d597be34bb58730dd2f07095d137dce37656c933834046a699be9fe","target":"record","created_at":"2026-07-05T09:53:11Z","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":"a858e46fbd28cb8d0af91e48aeb2dcb43fae66e413aa8da8848e7ac3b1c211b1","cross_cats_sorted":["cs.CR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-21T15:32:03Z","title_canon_sha256":"045ab69ab5bf07c1ccc32c23eb26825ba5a169e6e5ce511521ab07160d1d1dd7"},"schema_version":"1.0","source":{"id":"2412.16669","kind":"arxiv","version":1}},"canonical_sha256":"e05888a8e185f42586640891bd9aff79a7b338787a467acfe77d25851a59e3b8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e05888a8e185f42586640891bd9aff79a7b338787a467acfe77d25851a59e3b8","first_computed_at":"2026-07-05T09:53:11.249757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:11.249757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZgzEWjvwRc0XGpid4xyOVKQCoMlXWzT/gfYQKTFDDVyR3F+H4ZfEf4Ou4vYKr4Ulp9F1RDXScbIAJbWUWXJuAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:11.250192Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.16669","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cce327f08d597be34bb58730dd2f07095d137dce37656c933834046a699be9fe","sha256:79ec2fb5574b6eaa4d3e4fbf48431c4575e5a93ddd4d64d2388eb5c1678da433"],"state_sha256":"76d76d53be4bde2872c3ed89b22a8d3807ad5f0517f20957cec0b15342a1b4e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6qRnWB7WZb5W0L0YiC0zTwINaeE/oWE0cgSGI791S8sPRviKNxiPbku21LwP1/EyySn/gSLcG7f9AEW8ro6VBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T20:05:07.475123Z","bundle_sha256":"09daef030ac06a354c5e81cfb1c63a6e714ee4ccfb0de2f2373a71e9f6a546d0"}}