{"as_of":"2026-08-19T05:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d7e3f55f477c8369e4b9e7750dd3081b74f01f91f1c593dcb86d00c03b0346b7","coverage":[{"denominator":51,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":51,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T10:26:42.958773Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2412.16669/citation-record","integrity":"/paper/2412.16669/integrity","json":"/paper/2412.16669/citation-record.json","paper":"/paper/2412.16669"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.879616Z","title":"Practical secure aggregation for privacy-preserving machine learning","venue":null,"work_id":"ebf4c964-4169-4b9d-a896-069c4bf42992","year":2017},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.757117Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:fd3f301ae47ea123f93d70646dc63c760e0948cac630b4108caa50943925889f","observation_id":"078f6f19-4c0d-47a4-b195-be03f7a020d3","resolution":{"observed_at":"2026-08-11T10:26:43.884987Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2209.01188","last_updated":"2023-03-02T19:33:31Z","snapshot_observed_at":"2026-08-16T16:35:03.571411Z","submitted_at":"2022-09-02T17:38:03Z","title":"Petals: Collaborative Inference and Fine-tuning of Large Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2209.01188","snapshot_observed_at":"2026-08-11T10:26:42.761185Z","title":"Petals: Collaborative inference and fine-tuning of large models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.761185Z"},"links":{"cited_paper":"/paper/2209.01188","citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:7999ac8a251f8dcc9773d18ffbec90d77211e4f1c0808b115efb120a71f2806a","observation_id":"3582bcaa-18b2-435a-bc51-fe6dea68a540","resolution":{"observed_at":"2026-08-11T10:26:42.761185Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.765052Z","title":"XGBoost : A scalable tree boosting system","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.765052Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:635142d28a0b451dc98f048d2983b37518249aa3c87d7244969f0e8e8f2d805d","observation_id":"3b4ce599-d1b3-4721-8448-53df3a3476f0","resolution":{"observed_at":"2026-08-11T10:26:42.765052Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.11416","last_updated":"2022-12-06T21:39:48Z","snapshot_observed_at":"2026-08-18T19:51:48.688199Z","submitted_at":"2022-10-20T16:58:32Z","title":"Scaling Instruction-Finetuned Language Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.11416","snapshot_observed_at":"2026-08-11T10:26:42.769085Z","title":"Chi, Jeff Dean, Jacob Devlin, Adam Roberts, Denny Zhou, Quoc V","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.769085Z"},"links":{"cited_paper":"/paper/2210.11416","citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:678e580a9a172fa740c7e94989bc5efe4b4a120806012e6589befcdbb62f6983","observation_id":"4a1e1c1f-3de2-4af6-84c8-66c32e9d4b68","resolution":{"observed_at":"2026-08-11T10:26:42.769085Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14314","last_updated":"2023-05-23T17:50:33Z","snapshot_observed_at":"2026-08-13T23:56:42.354755Z","submitted_at":"2023-05-23T17:50:33Z","title":"QLoRA: Efficient Finetuning of Quantized LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14314","snapshot_observed_at":"2026-08-11T10:26:42.772924Z","title":"Qlora: Efficient finetuning of quantized llms","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.772924Z"},"links":{"cited_paper":"/paper/2305.14314","citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:db87284c0c2c82aee3d0d8386057b4f6a1fedd4ba43981667abda7adf9ff55c3","observation_id":"76b6093c-b6b6-416e-9b47-f98d68dd7db4","resolution":{"observed_at":"2026-08-11T10:26:42.772924Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.866175Z","title":"D reambooth A P I – E asily finetune S table D iffusion and generate customised A I images --- dreamboothapi.ai","venue":null,"work_id":"5bba5a53-14df-4943-97fe-6b3b403a8b02","year":2024},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.776606Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:23007c80f2c384c005f043a5dddc0bb08058069b76cb297c8134568cbbf70f69","observation_id":"6bee8dd3-9201-412e-996e-c9a6168183b8","resolution":{"observed_at":"2026-08-11T10:26:43.870720Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.15594","last_updated":"2023-05-24T22:06:08Z","snapshot_observed_at":"2026-08-16T15:29:57.865534Z","submitted_at":"2023-05-24T22:06:08Z","title":"Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.15594","snapshot_observed_at":"2026-08-11T10:26:42.780831Z","title":"Flocks of stochastic parrots: Differentially private prompt learning for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.780831Z"},"links":{"cited_paper":"/paper/2305.15594","citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:f9f9192dad8deb55b75b2ed59e174d9d8e13e6eaa551a8b301e1a2f9b9962437","observation_id":"8f681012-46c6-43b4-be22-5d07bb092aa5","resolution":{"observed_at":"2026-08-11T10:26:42.780831Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.784524Z","title":"Differential privacy","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.784524Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:e4b96f35492c28bda2af3ecb7838132010fd7411363d7b660d535b1f73e35195","observation_id":"6022b683-7d75-4326-b46b-db67e28b3c14","resolution":{"observed_at":"2026-08-11T10:26:42.784524Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.843531Z","title":"Unsupervised domain adaptation by backpropagation","venue":null,"work_id":"3a37d1e4-70a3-4c86-a28d-2829b0a1fdc4","year":2015},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.788044Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:33b2d048f99350afdf4f93ed1673ff14b258c2d6837c2e4736ccee40867a645e","observation_id":"fdc8151d-0e29-4b7a-9992-07b05d7eedfd","resolution":{"observed_at":"2026-08-11T10:26:43.848553Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.791335Z","title":"Distributed learning of deep neural network over multiple agents","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.791335Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:baf57628b48fbe8edc2ce38c4eb03dc82542fdb727b6997c92f11dbf5b1812e0","observation_id":"966c983a-4222-4108-8318-957ebe19e6e8","resolution":{"observed_at":"2026-08-11T10:26:42.791335Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.794821Z","title":"WARP : W ord-level A dversarial R e P rogramming","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.794821Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:5583b25abca76a3f2481e7b094db1e5ee63fa88f196fc7552f548c3b046051ee","observation_id":"28606261-f6fc-4031-a2d4-86d8b74d6685","resolution":{"observed_at":"2026-08-11T10:26:42.794821Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.827896Z","title":"Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption, 2017","venue":null,"work_id":"655afd83-f672-460c-845a-767d3aaf73de","year":2017},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.799073Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:368abc96aafe5d078e819fd65a8949514d32e93233552b041702d39e34005fe6","observation_id":"a9d227a4-9aca-4115-8c2c-abf7ceb540f9","resolution":{"observed_at":"2026-08-11T10:26:43.832580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.803059Z","title":"Deberta: Decoding-enhanced bert with disentangled attention","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.803059Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:d03fc8a11f054872cc2696c1786caba7a72dd0c38647a13a11b8d8f42262e53e","observation_id":"275e4c23-3461-44eb-9523-d736574b10e5","resolution":{"observed_at":"2026-08-11T10:26:42.803059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.806981Z","title":"Parameter-efficient transfer learning for NLP","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.806981Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:092417cc289da953c570ee0b5335b9d6d8cc31aed414f09d1e503ad01e85381d","observation_id":"e57e1296-344d-4e5d-8137-5e0ec1ed8a96","resolution":{"observed_at":"2026-08-11T10:26:42.806981Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.810928Z","title":"Lo RA : Low-rank adaptation of large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.810928Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:01e9cf60f814bb57b025c1d25ebad19f445b04a05d23249a56f957eae7effde1","observation_id":"fd15cdb1-4d56-4809-95ad-c124dc6105a4","resolution":{"observed_at":"2026-08-11T10:26:42.810928Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.781006Z","title":"A uto T rain --- huggingface.co","venue":null,"work_id":"79be9276-7e56-4283-8302-ddff11f1c7b3","year":2024},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.814771Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:bf5f5170df779d62b995dc71e0ce302e9225382307ad8b96e26449de1dfe12ad","observation_id":"b465f6ec-9bbf-43e2-8b78-75145359228d","resolution":{"observed_at":"2026-08-11T10:26:43.785502Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-17T19:26:44.032537Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-11T10:26:42.818621Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.818621Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:393aff2ba9ee162c0736a12429edb448ae0dd4dbe8b50d07072f3398896abe3c","observation_id":"dc3698c8-8b68-48f8-8b80-a5051292eb37","resolution":{"observed_at":"2026-08-11T10:26:42.818621Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.766889Z","title":"Label leakage and protection in two-party split learning","venue":null,"work_id":"474d19a4-e2e3-4f21-b83f-dd4fc2e8f832","year":2022},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.822811Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:46b0e32d7ffe538d7d4d5661851272ec331a7ed6dafa09c87ffce6dcbc459e3d","observation_id":"2cd7ae6f-7aec-402b-ad39-ec36f9682379","resolution":{"observed_at":"2026-08-11T10:26:43.771561Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.750915Z","title":"A survey on federated learning systems: Vision, hype and reality for data privacy and protection","venue":null,"work_id":"02a243e4-0c59-4334-a9e9-acf4c656e7fd","year":2021},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.826672Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:91c0fb3de8490b76cb3fb7ea6f1cb4cbd3580a3e879388af96aa6ab6cbcbf3f7","observation_id":"c35edeac-9102-4af6-8bd4-1070b2fe9e86","resolution":{"observed_at":"2026-08-11T10:26:43.756166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.734198Z","title":"PyTorch RPC: Distributed Deep Learning Built on Tensor-Optimized Remote Procedure Calls","venue":null,"work_id":"796ff4e2-f6d6-46f6-9298-fb684bda0968","year":2023},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.830671Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:fd1ce96a9a2dd38bad00d2c00915d817376e5e6fb1644e7305c0d7eef183b297","observation_id":"8e968b4b-906a-49a7-9232-64b1605d0836","resolution":{"observed_at":"2026-08-11T10:26:43.739879Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.834502Z","title":"Prefix-tuning: Optimizing continuous prompts for generation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.834502Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:94991e252abfe2bb5b5df9a4d40e58adc1b0ca0e4abe1727a0161b0e05fdc0f2","observation_id":"1adb9842-7a1b-4389-842e-e8cc32ddee70","resolution":{"observed_at":"2026-08-11T10:26:42.834502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.838486Z","title":"Privacy-preserving prompt tuning for large language model services","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.838486Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:b4ae8519bc775f60fdf81371fc588607bfc989862434c8dcdb878157c3bebbf8","observation_id":"d7d2f0cd-6175-4699-9889-25a16381054d","resolution":{"observed_at":"2026-08-11T10:26:42.838486Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.17493","last_updated":"2024-06-02T06:31:21Z","snapshot_observed_at":"2026-08-16T14:30:58.721319Z","submitted_at":"2023-12-29T06:50:38Z","title":"Differentially Private Low-Rank Adaptation of Large Language Model Using Federated Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.17493","snapshot_observed_at":"2026-08-11T10:26:42.842299Z","title":"Differentially private low-rank adaptation of large language model using federated learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.842299Z"},"links":{"cited_paper":"/paper/2312.17493","citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:ca2b03f4100889720591945f44623822aa334d0f825d10f481380483a98a74e5","observation_id":"f918c9f1-b289-42ec-8c16-49e4fc5fa13c","resolution":{"observed_at":"2026-08-11T10:26:42.842299Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.847172Z","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.847172Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:bcd4f4dfa92852109871ea560680e9ddaa6d4ee9d6bac7dfdc99e32c87e86dbc","observation_id":"8c33e2cf-7d43-4f12-bc24-6af45cd03da9","resolution":{"observed_at":"2026-08-11T10:26:42.847172Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.705612Z","title":"N vidia confidential computing","venue":null,"work_id":"ce963174-fde3-4942-811c-de3b8c2a0ada","year":2024},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.851119Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:c0031a7b257d1975cf164e969edb168191c30852ad1939834e00e8de6dd96257","observation_id":"65ccb2ac-4b4a-4e5b-b39a-1dfb9f98a779","resolution":{"observed_at":"2026-08-11T10:26:43.710840Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.688397Z","title":"F ine-tuning S table D iffusion --- docs.octoai.cloud","venue":null,"work_id":"a924005f-014d-4512-982e-bbfe92852d6b","year":2024},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.854984Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:801479e406a7ade7b9de26485cc2944ad0d200589d0604c64cd74d07e4504dee","observation_id":"e99c351d-9f3d-40ad-a3b5-e3456017b38e","resolution":{"observed_at":"2026-08-11T10:26:43.693001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.674697Z","title":"O pen A I P latform --- platform.openai.com","venue":null,"work_id":"5f065e88-01ee-4213-80f7-03927bf044b8","year":2024},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.859484Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:a016ec4f37692e4e0ab77b873d0627f53af7eeda4d7bb9349e731500890a25a0","observation_id":"917da093-c772-4862-bd23-6a648876008e","resolution":{"observed_at":"2026-08-11T10:26:43.679247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.865386Z","title":"Unleashing the tiger: Inference attacks on split learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.865386Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:fbbffa9a37de2bf00d11199f2b513839e1e8ad90e271b07aaeb9432a8d6d049a","observation_id":"4bc32ee8-2ff8-4196-a240-caa08d1d944e","resolution":{"observed_at":"2026-08-11T10:26:42.865386Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.870990Z","title":"Adapterfusion: Non-destructive task composition for transfer learning, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.870990Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:1b69c571c5be7f79231d37e6674385b50530274bc79bd96dc2d7d06bedf8caab","observation_id":"4f8583ff-ef51-4b70-bf86-75af8c6eba9e","resolution":{"observed_at":"2026-08-11T10:26:42.870990Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.649988Z","title":"Bittensor: A peer-to-peer intelligence market, 2021","venue":null,"work_id":"64187ec5-4a4e-41a2-9374-826c2c6802c0","year":2021},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.875792Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:f40614ba217c4b0a686718cf8bf5a45e703f59f7bcd2c70095e76372b04dd6f5","observation_id":"ff748d11-4299-45a9-a1ae-79da8063d600","resolution":{"observed_at":"2026-08-11T10:26:43.655761Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2204.07667","last_updated":"2022-10-27T16:18:52Z","snapshot_observed_at":"2026-08-16T17:06:38.291266Z","submitted_at":"2022-04-15T22:36:55Z","title":"Just Fine-tune Twice: Selective Differential Privacy for Large Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.07667","snapshot_observed_at":"2026-08-11T10:26:42.879429Z","title":"Just fine-tune twice: Selective differential privacy for large language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.879429Z"},"links":{"cited_paper":"/paper/2204.07667","citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:313b7b5b54bc07cb4f4a0dfd1d1b1aa9eada39bcc3ed958d2434fa6a219d5cdb","observation_id":"1e029f4c-89d7-4ebe-bb9d-d8c5d4a0b58e","resolution":{"observed_at":"2026-08-11T10:26:42.879429Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.883666Z","title":"Manning, Andrew Ng, and Christopher Potts","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.883666Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:fa6baf1bd433f0a05ca53ebaea5a952b7ab7622f9b9fe4ec00f56e145f47280d","observation_id":"6cf986de-01a8-46ab-ab67-99892a9762d3","resolution":{"observed_at":"2026-08-11T10:26:42.883666Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.01451","last_updated":"2022-05-25T00:33:07Z","snapshot_observed_at":"2026-08-16T17:17:21.689654Z","submitted_at":"2022-03-02T22:54:54Z","title":"Label Leakage and Protection from Forward Embedding in Vertical Federated Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.01451","snapshot_observed_at":"2026-08-11T10:26:42.887015Z","title":"Label leakage and protection from forward embedding in vertical federated learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.887015Z"},"links":{"cited_paper":"/paper/2203.01451","citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:f780b6374adca43ba7534670f008684a06dc6118e31220c70a5e14d3d4c75ea3","observation_id":"7e129fdf-cfcc-4b8b-a88b-36f6cb3aee0f","resolution":{"observed_at":"2026-08-11T10:26:42.887015Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.623492Z","title":"A survey on deep transfer learning","venue":null,"work_id":"853ea637-2eaf-4a80-bdc1-0af6c086377e","year":2018},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.890970Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:44ffe4c516ce954ee4b8a9b7a7fa1df45331fa08775342acd8390fe0fc089aa7","observation_id":"ccf6f5ae-af72-4846-882a-ffb6569b20cd","resolution":{"observed_at":"2026-08-11T10:26:43.628658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-11T10:26:42.894590Z","title":"Llama 2: Open foundation and fine-tuned chat models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.894590Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:883bc301b02575474dc3724f6ccc66d44de27aca8cdab5ba7824cd95d2463afd","observation_id":"64dee3b8-0963-4d1f-9adf-83ac2027e22a","resolution":{"observed_at":"2026-08-11T10:26:42.894590Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.609595Z","title":"Split learning for health: Distributed deep learning without sharing raw patient data, 2018","venue":null,"work_id":"6d4f0afd-994a-4fcc-9efa-02640a6d2e17","year":2018},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.898357Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:67ac2a8eac0db81dc4c46c68d7bad94440e536799c8bca09abeee6b53cba2467","observation_id":"56e1f5d5-b9b5-44eb-b763-fed891478eb5","resolution":{"observed_at":"2026-08-11T10:26:43.614268Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.593730Z","title":"Reducing leakage in distributed deep learning for sensitive health data","venue":null,"work_id":"c98946e8-16dd-432f-9632-91bdf5569895","year":2019},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.901491Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:f0b4ce79ff43e57ecc0ab118f57c987b13b38b20babeff8a827da9d7c389f921","observation_id":"e703753d-4e69-49c6-9236-6b70a3ea0c86","resolution":{"observed_at":"2026-08-11T10:26:43.598840Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.579724Z","title":"Pslf: Defending against label leakage in split learning","venue":null,"work_id":"c3e1dc7e-3113-4dd6-80f2-88376691c3d0","year":2023},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.905074Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:94f99d77faa3a4882a9bc2d76fe84ecac9c07610a2046ff63ae4c8a35f60e422","observation_id":"e5e32f37-f9f0-4569-865b-234f9aa2d219","resolution":{"observed_at":"2026-08-11T10:26:43.583558Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.07461","last_updated":"2019-02-22T23:53:34Z","snapshot_observed_at":"2026-08-16T09:50:11.319379Z","submitted_at":"2018-04-20T06:35:04Z","title":"GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.07461","snapshot_observed_at":"2026-08-11T10:26:42.909029Z","title":"Glue: A multi-task benchmark and analysis platform for natural language understanding","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.909029Z"},"links":{"cited_paper":"/paper/1804.07461","citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:5efc139c3cdf9d0fdba1328f2eeb744ff055d8dc3cf5b542ddd4f4f0db9d47bf","observation_id":"8c9525aa-bbce-4319-a1af-2531b1c579a7","resolution":{"observed_at":"2026-08-11T10:26:42.909029Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.14030","last_updated":"2023-11-23T14:36:30Z","snapshot_observed_at":"2026-08-17T21:48:47.111569Z","submitted_at":"2023-11-23T14:36:30Z","title":"PrivateLoRA For Efficient Privacy Preserving LLM","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.14030","snapshot_observed_at":"2026-08-11T10:26:42.912661Z","title":"Privatelora for efficient privacy preserving llm","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.912661Z"},"links":{"cited_paper":"/paper/2311.14030","citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:1c9f1a346adaf6fd097df67469c4bf2b4502b4f4c03a22d66bfa61cf3d942505","observation_id":"cb908729-ac0e-4e2e-bc06-0fb687dafcdf","resolution":{"observed_at":"2026-08-11T10:26:42.912661Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.567546Z","title":"Randomized response: A survey technique for eliminating evasive answer bias","venue":null,"work_id":"5d4fb898-0a03-4bf0-a38e-4d42e4403e48","year":1965},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.916382Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:92b308dbf0eaa3549d70a596a62d5006f43c83937f7008fedc35aa6da986ef52","observation_id":"2d0ac9c7-a549-41a7-a227-cc0a7a8fcdf4","resolution":{"observed_at":"2026-08-11T10:26:43.571545Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1704.05426","last_updated":"2018-02-19T19:19:51Z","snapshot_observed_at":"2026-08-18T10:01:09.572933Z","submitted_at":"2017-04-18T17:10:13Z","title":"A Broad-Coverage Challenge Corpus for Sentence Understanding through Inference","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1704.05426","snapshot_observed_at":"2026-08-11T10:26:42.919720Z","title":"A broad-coverage challenge corpus for sentence understanding through inference","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.919720Z"},"links":{"cited_paper":"/paper/1704.05426","citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:0a6220663a2bc9cf951dd874a551e8d1284ad50b1810dcdc7c0a89595c5a7442","observation_id":"6b86f629-c9b1-4394-aedf-db8eb80533a3","resolution":{"observed_at":"2026-08-11T10:26:42.919720Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.04870","last_updated":"2023-02-09T18:59:55Z","snapshot_observed_at":"2026-08-18T14:30:42.666081Z","submitted_at":"2023-02-09T18:59:55Z","title":"Offsite-Tuning: Transfer Learning without Full Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.04870","snapshot_observed_at":"2026-08-11T10:26:42.923827Z","title":"Offsite-tuning: Transfer learning without full model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.923827Z"},"links":{"cited_paper":"/paper/2302.04870","citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:a2de2680b207ced7770736d570ab700b14181dc234a701f709d74e002fad0407","observation_id":"d81ac49d-6ff7-4a18-99dc-8d6e17a81b53","resolution":{"observed_at":"2026-08-11T10:26:42.923827Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.928261Z","title":"Federated machine learning: Concept and applications","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.928261Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:76af06160e25f566e464464d036cea1e2d983e5d8e6bc0c3d118cad039f91445","observation_id":"f6bae7e1-2438-4625-818f-b9b147b3a586","resolution":{"observed_at":"2026-08-11T10:26:42.928261Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.932208Z","title":"Differentially private fine-tuning of language models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.932208Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:f9a289261ea0441df4606cb29a0b0fc2487f62eef675ebb333e7a50b17814881","observation_id":"0158a6a9-2b2c-4e38-973f-5b223204ddd3","resolution":{"observed_at":"2026-08-11T10:26:42.932208Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.18653/v1/2023.findings-acl.632","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.993667Z","title":"F ed PET uning: When federated learning meets the parameter-efficient tuning methods of pre-trained language models","venue":null,"work_id":"ff777d4d-9d39-40ba-9232-d729c7400340","year":2023},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.936908Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:334935a30d88c2b3955d54d0a9b5fa85e34f2e9bde1aaa33703213825e498107","observation_id":"a6f13ae2-74c8-473f-9cd2-c7c6bee40617","resolution":{"observed_at":"2026-08-11T10:26:43.000387Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:43.546049Z","title":"Fedprompt: Communication-efficient and privacy preserving prompt tuning in federated learning, 2023","venue":null,"work_id":"7d3400f3-4ff6-4763-b85e-777f9c58c093","year":2023},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.941167Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:dceb47369faa6c8fbd465c2d709c35227b27cc17b3ad53dd4afde6e5053751f8","observation_id":"f93cb331-d791-4d9b-92d1-344d8c2fddbb","resolution":{"observed_at":"2026-08-11T10:26:43.550432Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.945093Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.945093Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:5052c15f7851d6262e01f6af0c9492f2749bc9144b43ab093dd39319ff744667","observation_id":"da532418-9195-4628-8c3b-b32c076ba48f","resolution":{"observed_at":"2026-08-11T10:26:42.945093Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.949836Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.949836Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:ff58aed12f4cf298e0601efe116070ad2e80bbae75063c9bb8d935bf764498c3","observation_id":"b4f04011-4cb0-4c38-bd92-8a3d597c5ab7","resolution":{"observed_at":"2026-08-11T10:26:42.949836Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.954556Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.954556Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:0aac822162e7fa0ef246fb1f6ad398a7983553ac3b0d1cb2adf439814dfdc3b3","observation_id":"1e2e9b99-6e63-42d3-983d-871194a36972","resolution":{"observed_at":"2026-08-11T10:26:42.954556Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T10:26:42.958773Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-11T10:26:42.958773Z"},"links":{"citing_paper":"/paper/2412.16669"},"observation_digest":"sha256:e0f832c6daa8445b7239251455cea4696082e160bc7aa60b35f3a879d99253ee","observation_id":"4232eb65-237c-4e53-ab07-cc2ff7b752c5","resolution":{"observed_at":"2026-08-11T10:26:42.958773Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2412.16669","last_updated":"2024-12-21T15:32:03Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T00:35:24.712671Z","submitted_at":"2024-12-21T15:32:03Z","title":"Label Privacy in Split Learning for Large Models with Parameter-Efficient Training"},"reference_resolution":{"displayed":51,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":32,"verified_exact":1,"verified_fuzzy":18},"total_outbound_references":51},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 51 of 51 outbound references and 0 inbound Pith citation observations for arXiv:2412.16669."}