{"as_of":"2026-08-09T11:59:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:46522972efd7f09b4632f08a08c311df590001e13767d21a5f9685075ec19955","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-13T12:53:49.802978Z","state":"measured"},{"denominator":20,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":20,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2604.03595/citation-record","integrity":"/paper/2604.03595/integrity","json":"/paper/2604.03595/citation-record.json","paper":"/paper/2604.03595"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-13T12:53:49.802978Z","title":"Blindfl: Vertical federated machine learning without peeking into your data,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:54fe679497416e14181ddcb1041233e0ac2de5f562ecf9fd23e8014b5afe328f","observation_id":"e0e64002-ba5d-45b9-abe7-c896c6271d79","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.00489","last_updated":"2021-04-14T08:05:04Z","snapshot_observed_at":"2026-08-04T19:38:41.185400Z","submitted_at":"2021-04-01T14:21:33Z","title":"PyVertical: A Vertical Federated Learning Framework for Multi-headed SplitNN","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.00489","snapshot_observed_at":"2026-07-13T12:53:49.802978Z","title":"Pyvertical: A vertical federated learning frame- work for multi-headed splitnn,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"cited_paper":"/paper/2104.00489","citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:91adda046cce629c0b20e3cd37fcbf38c698678e72ab2d6e952a3d52b20e7517","observation_id":"5ffc3413-e597-4f19-adee-3dbfc6528215","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.07427","last_updated":"2020-06-11T08:20:06Z","snapshot_observed_at":"2026-08-02T06:06:18.699148Z","submitted_at":"2020-04-16T02:53:48Z","title":"Asymmetrical Vertical Federated Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.07427","snapshot_observed_at":"2026-07-13T12:53:49.802978Z","title":"Asymmetrical vertical federated learning,","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"cited_paper":"/paper/2004.07427","citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:38cdb6ddcf2f729af9b4047a863f081a21f70f8cfc7d98755d43c7c31e4665f0","observation_id":"d408d127-732b-4485-81a0-524e6c5b87b1","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"Splitfed: When federated learning meets split learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:9035960bb5e9557c6cf7e3da3dc9ae1075a0a473d02d5d18269ce7a9cf6c4ff2","observation_id":"35f47f18-4c94-4374-b236-4c9a276b1f52","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.12115","last_updated":"2019-12-27T14:39:58Z","snapshot_observed_at":"2026-07-06T08:47:10.164127Z","submitted_at":"2019-12-27T14:39:58Z","title":"Split Learning for collaborative deep learning in healthcare","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.12115","snapshot_observed_at":"2026-07-13T12:53:49.802978Z","title":"Split learn- ing for collaborative deep learning in healthcare,","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"cited_paper":"/paper/1912.12115","citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:56abd97cad10aa8032710c06b792a1e91ac3a324362aac6e46be008caa2d5aac","observation_id":"a7585fb3-bbd4-4fa1-b359-9855aa028cf0","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00564","last_updated":"2018-12-03T05:43:20Z","snapshot_observed_at":"2026-08-04T04:23:43.839800Z","submitted_at":"2018-12-03T05:43:20Z","title":"Split learning for health: Distributed deep learning without sharing raw patient data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00564","snapshot_observed_at":"2026-07-13T12:53:49.802978Z","title":"Split learning for health: Distributed deep learning without sharing raw patient data,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"cited_paper":"/paper/1812.00564","citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:d90622f74b3bac913ff52794d1f41229b9b08a90cb8854fba32a48b2a8db1e07","observation_id":"a0dec129-483d-460a-a2c9-029cd74cd06a","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1909.09145","last_updated":"2019-09-18T21:43:33Z","snapshot_observed_at":"2026-07-06T08:23:10.708764Z","submitted_at":"2019-09-18T21:43:33Z","title":"Detailed comparison of communication efficiency of split learning and federated learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.09145","snapshot_observed_at":"2026-07-13T12:53:49.802978Z","title":"Detailed comparison of communication efficiency of split learning and federated learning,","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"cited_paper":"/paper/1909.09145","citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:447d6b93e7b81dd35d34bfe1f5c90dd9048a73c621df6f412855f9d31ba65319","observation_id":"61f42bfa-1cd0-48cc-820e-13deb8e2227c","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:715c4d6893988b71f1f26c4d74163ce6f1eac2e3caca4d05f1f2bc9119acbe36","observation_id":"40b3b043-b22a-4da6-8bfc-2a98cd0c06df","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"Split learning for distributed collaborative training of deep learning models in health informatics,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:51739f9e3763db1e4d78a2b086b4448203dc6cd642efded08899adb4feb39b88","observation_id":"c0e7640e-bcfb-452b-975f-d115090d26fd","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"Split learning optimized for the medical field: Reducing communication overhead,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:bdc9ac38823e10669285d76b52eb3c4c63b5ae928624ca39e0ec35d738fda32d","observation_id":"4b8c21d3-a5d4-4d89-bab5-12ce2ae4cbbf","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"Villain: Backdoor attacks against vertical split learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:56aea42364bdae4b6a27769fe0e3c302bc668628ac1235aaaad1d88e62d95efc","observation_id":"849f3399-8fe8-46a3-807c-551138cf17ac","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"Backdoor attack against split neural network-based vertical federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:89d4bcc1989bd2f3d6424405b1275548b1c455a7761f982344156e7d81ef9e03","observation_id":"4ed21750-19b5-41f3-9735-cc7de1d2caf4","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"Badvfl: Backdoor attacks in vertical federated learning,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:9f5c61f7daf07580747a90250f06e15d38e40eb6d0cb9ab68a29e1c71f204498","observation_id":"cff2cfc2-7848-4ea3-9a97-d34f2c7961f6","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"Securesplit: Mitigating backdoor attacks in split learning,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:3017ea9abac6d2439d8edd273fb3af553b75442da3e93395b136e975a23630dd","observation_id":"dc53764c-81d4-467a-9560-2e73eaf33213","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"Vflip: A backdoor defense for vertical federated learning via identification and purification,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:a825b9d2a7e3d01714c3c9ab4fd10cb39bd9a8209d5f1c2976da347945893832","observation_id":"70e2a79b-c448-4376-b46a-73798f84ce81","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"A data-driven approach to predict the success of bank telemarketing,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:22e2e7f6af7a198a227ad11a88bb87cf8171df2669f2d160484e3d99515161a5","observation_id":"b5bdabc3-0510-4600-b10e-3ac38d39fa80","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"Deep learning with differential privacy,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:38de13c0a4f9b899d54bef6de97d5c48af0df567d8a43fbaaf5e41187bc8a2ef","observation_id":"d72d2277-a0d0-4871-add7-f3ae0e216525","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"Fine-pruning: Defending against backdooring attacks on deep neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:cc2aaa713d8e42c322aabeddd5f1306a36e8055d50afb1430eea1c0d31ca22f4","observation_id":"40e95068-54ee-4306-9321-77da44f63b6b","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"Adversarial neuron pruning purifies backdoored deep models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:26c1407fec8de7e7922abb265ab45e4e48ef941360e226273091d8281027f5fb","observation_id":"99066e57-d9c9-4415-8171-7c67e48bb38d","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","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":"2026-07-13T12:53:49.802978Z","title":"Safesplit: A novel defense against client-side backdoor attacks in split learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-07-13T12:53:49.802978Z"},"links":{"citing_paper":"/paper/2604.03595"},"observation_digest":"sha256:80e3cc4bb5f54d3c6cf1a1737cd2f882417627f2638492a8cea48a67c9c96a92","observation_id":"7588d942-2a11-4aa2-9a58-cca8a9b617a5","resolution":{"observed_at":"2026-07-13T12:53:49.802978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2604.03595","last_updated":"2026-04-04T05:24:09Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-06T15:57:36.599250Z","submitted_at":"2026-04-04T05:24:09Z","title":"ProtoGuard-SL: Prototype Consistency Based Backdoor Defense for Vertical Split Learning"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":20,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":20},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 0 inbound Pith citation observations for arXiv:2604.03595."}