{"as_of":"2026-08-09T22:44:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:408cf254875ca8e1a3e3c8de0fa8ec419cc828b4d2c4efd8c4a038bfb3bbc54d","coverage":[{"denominator":91,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":91,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T06:31:13.569014Z","state":"measured"},{"denominator":91,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":91,"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/2607.21895/citation-record","integrity":"/paper/2607.21895/integrity","json":"/paper/2607.21895/citation-record.json","paper":"/paper/2607.21895"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T06:31:05.897867Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:05.897867Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:bebdd75c372ebde1d9951623fd0ef07fcf41a500b79b759b448749bd63dfe593","observation_id":"45b961e1-59c0-4381-8424-9eecf14fefa6","resolution":{"observed_at":"2026-08-01T06:31:05.897867Z","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":"2026-08-01T06:31:05.981418Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:05.981418Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:cc166ee016f827a8861b017c2a5097c84cad6004ab267953a1ea46b6de49e4f6","observation_id":"cb9d8104-fd9f-45ac-b0f6-3db323ca4701","resolution":{"observed_at":"2026-08-01T06:31:05.981418Z","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":"2026-08-01T06:31:06.099588Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:06.099588Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:6e72d5ab7807f0c56c5b3aff38e06f59e90ce6cb59050c3c0eda36eab5336705","observation_id":"b25b0ac9-739e-43ba-a487-826df6b8b1c5","resolution":{"observed_at":"2026-08-01T06:31:06.099588Z","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":"2026-08-01T06:31:06.204749Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:06.204749Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:a431e4318376de792dcace42c78fe26877bcedfc30bd0a5ce8cb4e0b784eb319","observation_id":"e8a03ce7-fd93-4ab9-86e2-f3cc86f40d1a","resolution":{"observed_at":"2026-08-01T06:31:06.204749Z","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":"2026-08-01T06:31:06.294753Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:06.294753Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:6e64c4febcfe803e3833229eae081a591ccec08c967c25a18b1928ef25551f2d","observation_id":"94fea654-3536-497b-9d78-c2057e1159bf","resolution":{"observed_at":"2026-08-01T06:31:06.294753Z","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":"2026-08-01T06:31:06.384249Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:06.384249Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:00ec724e89059e315789587ec799042e7fe97b9fab6ee846cef500c265946f4f","observation_id":"ed7ecdf2-6cd0-480f-a12e-90c8f025be0f","resolution":{"observed_at":"2026-08-01T06:31:06.384249Z","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":"2026-08-01T06:31:06.475162Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:06.475162Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:9d648d7b8eff8ff359d6a2b6b54c638d2b90d0f94c620bc84822bf456ce2157f","observation_id":"9905f79f-e5ff-45a8-b5a1-0a9a88fbcde6","resolution":{"observed_at":"2026-08-01T06:31:06.475162Z","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":"2026-08-01T06:31:06.591442Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:06.591442Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:a923384c80407d11df42342abbea1ab03c63df47a5c402a2948a0f57770402b2","observation_id":"c905a949-06d2-4d0b-bde7-490144b0a051","resolution":{"observed_at":"2026-08-01T06:31:06.591442Z","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":"2026-08-01T06:31:06.804765Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:06.804765Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:22d01da1cd965b10aab44b8bf3c9e6acfbcbda5370e03e7b7b8ffb942f86bb48","observation_id":"e8f38673-f091-46cc-a29b-0ed5358edff7","resolution":{"observed_at":"2026-08-01T06:31:06.804765Z","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":"2026-08-01T06:31:06.894824Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:06.894824Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:786c773fab30bc2129e3eb6b73cbaf1b9202bb0d125021bec4235e08d13454fc","observation_id":"364ae701-6186-4477-a363-c328ad28aba7","resolution":{"observed_at":"2026-08-01T06:31:06.894824Z","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":"2026-08-01T06:31:07.025167Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.025167Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:e493849fbdfe8b3a41c534403b8e3d7babeda9a7198abbf42aba99bd06ed128b","observation_id":"0e57f1b0-08ea-40ed-a4fc-6b79f7267f85","resolution":{"observed_at":"2026-08-01T06:31:07.025167Z","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":"2026-08-01T06:31:07.092275Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.092275Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:70e3b418220844340f9522dafcc0f729ccf02d8141fd65987a78ca4b89222b59","observation_id":"9a3b2e73-0e9d-4b34-bd1a-b792099badd9","resolution":{"observed_at":"2026-08-01T06:31:07.092275Z","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":"2026-08-01T06:31:07.136384Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.136384Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:10db9c2560ebf2b175b12341e33157c722f3a6f85fc86303302937025b842161","observation_id":"aab9a1b9-97b1-44da-a56d-f5f6e3e52ec7","resolution":{"observed_at":"2026-08-01T06:31:07.136384Z","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":"2026-08-01T06:31:07.311195Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.311195Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:db6de9bde5d62d41940605e2ae8c27a658a35e03a8c3779c385321b7d0232681","observation_id":"ddfc1140-4701-4285-934e-ada042c9043b","resolution":{"observed_at":"2026-08-01T06:31:07.311195Z","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":"2026-08-01T06:31:07.381341Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.381341Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:63209f06345dd867c857e3d1fee50676a5e4f00842138f37106a1cd14dd64726","observation_id":"43e74259-bcce-4f0e-a61c-f0686a2ad695","resolution":{"observed_at":"2026-08-01T06:31:07.381341Z","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":"2026-08-01T06:31:07.531792Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.531792Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:e63dcab268ee8e659c19e2b02e63f522e78bebbbf6e8699c37265390b9e78421","observation_id":"e8a12f4c-9aae-4c0c-a739-a7b560c56a9a","resolution":{"observed_at":"2026-08-01T06:31:07.531792Z","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":"2026-08-01T06:31:07.586082Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.586082Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:8084ec8f340ad8ca981bd6c166500fb33c73cd4e2677d94ebc338fed48c930bb","observation_id":"aabcece2-52a2-44b9-a88e-a68304825690","resolution":{"observed_at":"2026-08-01T06:31:07.586082Z","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":"2026-08-01T06:31:07.437271Z","title":"InProceedings of the 6th Workshop on Encrypted Computing & Applied Homomorphic Cryptography","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.437271Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:f94eaee7040bb5d7747c59597ae96c427d8590072908b06747ee1bd2eb7dbd70","observation_id":"9b6f64fb-21b3-4b64-9831-d4a4a298dc96","resolution":{"observed_at":"2026-08-01T06:31:07.437271Z","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":"2026-08-01T06:31:07.745466Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.745466Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:0bb25460a768d312a8075726f217888bdfd8a12584c1de1157a2d7c2c807d091","observation_id":"63c8e2c3-f4fa-4403-8d2d-56e37f6e8cc3","resolution":{"observed_at":"2026-08-01T06:31:07.745466Z","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":"2026-08-01T06:31:07.867552Z","title":null,"venue":null,"work_id":null,"year":1983},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.867552Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:efdc65de712498ab7a6f37008bac3a9f061f70153a3666bf72d240492d458a77","observation_id":"9233c6c6-f1ab-466c-b8fb-95473ae8482b","resolution":{"observed_at":"2026-08-01T06:31:07.867552Z","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":"2026-08-01T06:31:07.659755Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.659755Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:b33d11fa0c103533b5b708123124aea16498ca660fdf3fc4775136ecdd346de2","observation_id":"9b88f634-5b94-4181-a993-36bbca36a485","resolution":{"observed_at":"2026-08-01T06:31:07.659755Z","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":"2026-08-01T06:31:07.983290Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.983290Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:f745b3f3343b33341323b75762129650ef3743fda70c50cadee9d9e78de8ab2c","observation_id":"1959572c-132c-4a25-bab2-55dd1b9f0b73","resolution":{"observed_at":"2026-08-01T06:31:07.983290Z","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":"2026-08-01T06:31:08.059802Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:08.059802Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:3ebfb7cded8d57371a77436806817ca7044c6981798ec4e8ad474c6fa286aaeb","observation_id":"602c0e50-a1a8-482b-b562-346c989799d5","resolution":{"observed_at":"2026-08-01T06:31:08.059802Z","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":"2026-08-01T06:31:08.111367Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:08.111367Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:b701ebeaf6ffd2966e4d41401d8d284354e5c2766ef9a661f4e64874542ddfaa","observation_id":"86d4f24c-aefd-484f-b4fb-8d0e2843c423","resolution":{"observed_at":"2026-08-01T06:31:08.111367Z","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":"2026-08-01T06:31:07.923042Z","title":null,"venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.923042Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:9af5d30071f2c0e748fc86861e200c84e738d7b10f4cef25b5e95eedfe9e6a80","observation_id":"fda91163-d2be-4253-9c6a-2bbbee1983ba","resolution":{"observed_at":"2026-08-01T06:31:07.923042Z","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":"2026-08-01T06:31:08.272709Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:08.272709Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:57e1392c19a361c9b7ed5be65882cb5a17e07416a304f6188e19b622f43ae837","observation_id":"0e74933c-2772-4167-8bd8-bd71e509bcc0","resolution":{"observed_at":"2026-08-01T06:31:08.272709Z","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":"2026-08-01T06:31:08.353560Z","title":null,"venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:08.353560Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:187810db43a35a0e413197b5b7c9a65537f4418030eda4718868337ed336007f","observation_id":"ace4c3ae-a4ba-4efd-b6d6-dfeaa1625984","resolution":{"observed_at":"2026-08-01T06:31:08.353560Z","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":"2026-08-01T06:31:08.448614Z","title":"2009.Foundations of cryptography: volume 2, basic applications","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:08.448614Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:82fd25f2760103bff912e19431e35161ac9b93705049a3a3ee089c84c0817f12","observation_id":"b837c7ea-809a-4ed0-b7ec-d4b65500ba7d","resolution":{"observed_at":"2026-08-01T06:31:08.448614Z","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":"2026-08-01T06:31:08.218353Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:08.218353Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:3f563bf0b3856c07759a0bde15e4b0e02223f2f5d8aca4e6d05ab0a907aa9274","observation_id":"e0b701b5-f2f2-4570-8f63-4a3e5a810774","resolution":{"observed_at":"2026-08-01T06:31:08.218353Z","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":"2026-08-01T06:31:08.601674Z","title":null,"venue":null,"work_id":null,"year":1995},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:08.601674Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:3ce38382c1c9748d54e7de7996913e196872790544b70f5a2258a8402d96e873","observation_id":"ade8abda-21f3-4174-abed-f7978c67f5ef","resolution":{"observed_at":"2026-08-01T06:31:08.601674Z","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":"2026-08-01T06:31:08.674751Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:08.674751Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:7e90be347f12cada9b9379d16a7d0b0291cf531e800df1b7e73c8611f547f93d","observation_id":"e4086d74-8101-4be9-84af-517be21a082d","resolution":{"observed_at":"2026-08-01T06:31:08.674751Z","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":"2026-08-01T06:31:08.767602Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:08.767602Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:41ae71ada8ba96dfbe280c017dd4ad5e87e618fcd337c7083069e760993fb1d8","observation_id":"8af018ab-0a5b-4830-baf5-f94da8809c4b","resolution":{"observed_at":"2026-08-01T06:31:08.767602Z","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":"2026-08-01T06:31:08.534748Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:08.534748Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:1da4dd858e36c63cff36bd14190ebdeaa597a2f490e93a5df49e7881c8f88bf8","observation_id":"a8409bc2-9b35-4289-98cd-4d9c2c127d5e","resolution":{"observed_at":"2026-08-01T06:31:08.534748Z","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":"2026-08-01T06:31:08.919220Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:08.919220Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:bedec688fe95e8695bae42be3c9109a723b5f9ac23269032a39b15d74c510809","observation_id":"475d7c83-6e97-41d1-a5b5-ef9e8b5bb860","resolution":{"observed_at":"2026-08-01T06:31:08.919220Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2303.00566","last_updated":"2023-11-30T15:39:30Z","snapshot_observed_at":"2026-08-06T09:31:44.328315Z","submitted_at":"2023-03-01T15:12:55Z","title":"Structured Pruning for Deep Convolutional Neural Networks: A survey","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.00566","snapshot_observed_at":"2026-08-01T06:31:08.970517Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:08.970517Z"},"links":{"cited_paper":"/paper/2303.00566","citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:f1dbff15e9df7fcedf3230c6574062e5a768db5e92ba24d269fe7056968070d6","observation_id":"0202f4fc-a606-4750-9a99-9426289e667f","resolution":{"observed_at":"2026-08-01T06:31:08.970517Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05189","last_updated":"2017-11-14T16:53:39Z","snapshot_observed_at":"2026-07-06T06:09:25.471912Z","submitted_at":"2017-11-14T16:53:39Z","title":"CryptoDL: Deep Neural Networks over Encrypted Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05189","snapshot_observed_at":"2026-08-01T06:31:09.147766Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:09.147766Z"},"links":{"cited_paper":"/paper/1711.05189","citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:8aa3408f380cabefad8c4f15556768f8bf58761d4fefadc51d106b74b7c54d6e","observation_id":"6cc6cb52-99a0-4f2b-9f87-210e0a91b58b","resolution":{"observed_at":"2026-08-01T06:31:09.147766Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1808.06866","last_updated":"2018-08-21T12:22:38Z","snapshot_observed_at":"2026-07-06T06:56:39.566826Z","submitted_at":"2018-08-21T12:22:38Z","title":"Soft Filter Pruning for Accelerating Deep Convolutional Neural Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1808.06866","snapshot_observed_at":"2026-08-01T06:31:08.856358Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:08.856358Z"},"links":{"cited_paper":"/paper/1808.06866","citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:4bf9e9e6e12c0efcb751b3b4182e96430807ef643125cc6704fa0de3b3af8746","observation_id":"7cfad0e5-2342-4c00-b82d-ca068bac789f","resolution":{"observed_at":"2026-08-01T06:31:08.856358Z","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":"2026-08-01T06:31:09.421716Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:09.421716Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:43d41693447313a464c73a08aa61b1a50434d0881b9be36d95d66733153c1347","observation_id":"a0cb409d-f5c9-4e32-b4c0-faf3ce5e95d7","resolution":{"observed_at":"2026-08-01T06:31:09.421716Z","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":"2026-08-01T06:31:09.564219Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:09.564219Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:a4bea9d093cf211fe2aebc393e9d059c0dc2f6cfad0bd242e24489ad70e8099b","observation_id":"9fa5e0fa-0465-42f1-b6d8-47c62131b262","resolution":{"observed_at":"2026-08-01T06:31:09.564219Z","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":"2026-08-01T06:31:09.683427Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:09.683427Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:6de3814e32b02dbb2757f98fa8a9fbaefcf28568ed4f2d5ffc10536aa980d0b0","observation_id":"d48dc005-d5ea-4f2a-8a40-ba8c046599a8","resolution":{"observed_at":"2026-08-01T06:31:09.683427Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.03487","last_updated":"2020-01-31T17:12:52Z","snapshot_observed_at":"2026-08-08T14:54:18.420295Z","submitted_at":"2018-10-08T14:21:46Z","title":"Security Analysis of Deep Neural Networks Operating in the Presence of Cache Side-Channel Attacks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.03487","snapshot_observed_at":"2026-08-01T06:31:09.310951Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:09.310951Z"},"links":{"cited_paper":"/paper/1810.03487","citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:94b5eb8eb2793176db96a6327beae5a43304179e72ffa5e89e117047dd855d7c","observation_id":"1a5f3978-9307-42b2-9250-20c5fc02c30c","resolution":{"observed_at":"2026-08-01T06:31:09.310951Z","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":"2026-08-01T06:31:09.944303Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:09.944303Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:3ce1ef0d834c932ebd3b945a6012d599209902da4326a38f43380baee59a5b0e","observation_id":"e9c0686b-ad9c-4ea8-b3f8-ad381e9f589a","resolution":{"observed_at":"2026-08-01T06:31:09.944303Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.00319","last_updated":"2021-01-30T21:47:23Z","snapshot_observed_at":"2026-08-06T10:03:59.091329Z","submitted_at":"2021-01-30T21:47:23Z","title":"Efficient CNN Building Blocks for Encrypted Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.00319","snapshot_observed_at":"2026-08-01T06:31:10.013543Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.013543Z"},"links":{"cited_paper":"/paper/2102.00319","citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:0be3a5662cbb28ec895c29642a8b6997f1fe36580f4ed70cfdc3f4a1d40f15af","observation_id":"1094850d-421c-489f-b2aa-66d23c93c1be","resolution":{"observed_at":"2026-08-01T06:31:10.013543Z","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":"2026-08-01T06:31:10.078163Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.078163Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:9075e2afacadaeb05bbe988f2c289c6180bb97e257367427d26c1210c9d1c5ce","observation_id":"4ec754f3-b517-4317-adb3-fde1e532236d","resolution":{"observed_at":"2026-08-01T06:31:10.078163Z","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":"2026-08-01T06:31:09.834549Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:09.834549Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:aed723815f88f884f3657da9649a03ab15742e16651384018f7c5fb0503dc636","observation_id":"d81243b6-a5c2-4ab6-980c-d99cc1aeaee0","resolution":{"observed_at":"2026-08-01T06:31:09.834549Z","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":"2026-08-01T06:31:10.209739Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.209739Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:02c8f585c74e1fe602fbf2ef957ab167d082e42d3a24a95245941b58fb1049ae","observation_id":"3434b949-db32-4c96-bdfb-8be3213e5747","resolution":{"observed_at":"2026-08-01T06:31:10.209739Z","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":"2026-08-01T06:31:10.298361Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.298361Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:9274181469fcd4a9cc93ad181512acb01e2643db1d6ccbcdd7d645cf0a7caa10","observation_id":"f75749cb-993d-41f9-aadd-0b9279abd6a0","resolution":{"observed_at":"2026-08-01T06:31:10.298361Z","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":"2026-08-01T06:31:10.363029Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.363029Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:1b01c1aded6a5b69cf69e72646e4250411d4cdeee3f9fb8945993629d6b30203","observation_id":"8ef0b515-a0d1-42d6-a74e-e72102319474","resolution":{"observed_at":"2026-08-01T06:31:10.363029Z","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":"2026-08-01T06:31:10.148356Z","title":null,"venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.148356Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:9e7026aea2ab875fae55e4f9b2c4d95ce48b30fd3e729c244c3385677d9c0898","observation_id":"0d22ffc6-0eb1-4b2c-8923-005af505fa41","resolution":{"observed_at":"2026-08-01T06:31:10.148356Z","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":"2026-08-01T06:31:10.526696Z","title":null,"venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.526696Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:43783f4be6a77e9be0c64428670df3203994f3b0033513b20ff316026a92d362","observation_id":"0e16c952-cb48-494f-bf9d-f029697f58b9","resolution":{"observed_at":"2026-08-01T06:31:10.526696Z","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":"2026-08-01T06:31:10.633375Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.633375Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:00abe407f0ab59745217455020468fb818ae92da831ea1b7bca962645565a83d","observation_id":"5d3587dc-d6d2-4636-9676-af8167d39235","resolution":{"observed_at":"2026-08-01T06:31:10.633375Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1608.08710","last_updated":"2017-03-10T17:57:56Z","snapshot_observed_at":"2026-08-09T05:37:48.140401Z","submitted_at":"2016-08-31T02:29:59Z","title":"Pruning Filters for Efficient ConvNets","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.08710","snapshot_observed_at":"2026-08-01T06:31:10.696232Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.696232Z"},"links":{"cited_paper":"/paper/1608.08710","citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:e8b8fbcc40700c5c5c0499323783fdad67c9fb2ba885ad08a14fea12b033c415","observation_id":"f9a8276c-b79c-4d63-a18c-38338b27341e","resolution":{"observed_at":"2026-08-01T06:31:10.696232Z","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":"2026-08-01T06:31:10.455672Z","title":null,"venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.455672Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:608988369e02331147ea5d12493f7520dd0214deab8216c77710b28bde64a050","observation_id":"cdd939b3-5e6d-4129-a3d3-dfa849305256","resolution":{"observed_at":"2026-08-01T06:31:10.455672Z","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":"2026-08-01T06:31:10.837693Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.837693Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:12b8f326e016eb85d77ef5a729e7dd80660fec1cbdcb7510bcf6be59ff17ee7c","observation_id":"bcd82583-5606-4ae3-8331-3cf72f8e2a68","resolution":{"observed_at":"2026-08-01T06:31:10.837693Z","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":"2026-08-01T06:31:10.907028Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.907028Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:2db0c651efda5f867c40612675f4edec6af2d020a03cc9164cf5998981829c74","observation_id":"0914e09f-f9ee-49e7-8923-e2b452e50334","resolution":{"observed_at":"2026-08-01T06:31:10.907028Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.05270","last_updated":"2019-03-05T05:58:11Z","snapshot_observed_at":"2026-07-06T07:07:34.689643Z","submitted_at":"2018-10-11T22:15:28Z","title":"Rethinking the Value of Network Pruning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.05270","snapshot_observed_at":"2026-08-01T06:31:10.954853Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.954853Z"},"links":{"cited_paper":"/paper/1810.05270","citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:f1f8fbfa68f1bfa72871093bb9719eaf65e29ae4621e29353fca326dd8eee6c2","observation_id":"600374c0-9106-48b6-b14a-616676b7ca1e","resolution":{"observed_at":"2026-08-01T06:31:10.954853Z","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":"2026-08-01T06:31:10.768066Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:10.768066Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:22e9a44683594f0cfbbc99065746945aa948078294c317d484947e3e780a4702","observation_id":"c2f31bfa-2d85-48fd-bc03-8aa087139a84","resolution":{"observed_at":"2026-08-01T06:31:10.768066Z","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":"2026-08-01T06:31:11.211959Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:11.211959Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:44d033a2e27ee94bd9ddc080cc4fe5176d4d083641008590626ace9f8c875ace","observation_id":"041de178-bd13-4bf2-9984-e800aa764f01","resolution":{"observed_at":"2026-08-01T06:31:11.211959Z","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":"2026-08-01T06:31:11.252970Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:11.252970Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:d7d898747451cdfc26bc3bd299d005eca31895715e5c2688c73bd8528e6c4928","observation_id":"4b7b0662-a37d-4dd7-8872-e52d7f3781b3","resolution":{"observed_at":"2026-08-01T06:31:11.252970Z","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":"2026-08-01T06:31:11.340553Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:11.340553Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:c625a40fab83165e18de0be2bc60cfc076e01c4aa32027038f83b236a67b1c68","observation_id":"390d699b-728a-4566-8d97-69dbf6b564a0","resolution":{"observed_at":"2026-08-01T06:31:11.340553Z","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":"2026-08-01T06:31:11.097782Z","title":null,"venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:11.097782Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:72d6465d30a228b9e500874877d684222a4a1f7c3eab66cdab72bbc3b3184b3c","observation_id":"0f00e17c-3ac2-4e3b-8b28-a1801a741349","resolution":{"observed_at":"2026-08-01T06:31:11.097782Z","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":"2026-08-01T06:31:11.581783Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:11.581783Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:82f4c42d04dd41898e6a74c939e5d0d8a4ce45eda043ad2a81bc4e50e1cf29dd","observation_id":"1c89b1f0-e22e-4a55-bced-40422d93f60c","resolution":{"observed_at":"2026-08-01T06:31:11.581783Z","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":"2026-08-01T06:31:11.644669Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:11.644669Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:61399302817a9c37417003ee3867cfef4e3e1fd529efd8058507c561c4b57da2","observation_id":"b0ec78e4-732a-4e9d-964c-ce37ed906a97","resolution":{"observed_at":"2026-08-01T06:31:11.644669Z","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":"2026-08-01T06:31:11.715137Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:11.715137Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:d5f2fb2826ce74d2734f0a02d778d663f94a672ec6bb77b93310ed98c3e0df80","observation_id":"f7de8a44-3dc7-439a-a00d-55b6b93b8e3c","resolution":{"observed_at":"2026-08-01T06:31:11.715137Z","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":"2026-08-01T06:31:11.779767Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:11.779767Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:bd2f0ab06daec89e38692bfa9c54d2326d58e269a975c4985a2f141cf79e0e27","observation_id":"c3647e0f-0b28-4cc4-83b2-8f974ee14b3d","resolution":{"observed_at":"2026-08-01T06:31:11.779767Z","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":"2026-08-01T06:31:11.494047Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:11.494047Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:4d077f5a983105df20b459c20af6fc574c3d84ff1e523fe3d9d40252e175694b","observation_id":"156affc7-5bd4-48bd-9760-81a624fcbd5e","resolution":{"observed_at":"2026-08-01T06:31:11.494047Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1710.05941","last_updated":"2017-10-27T17:45:21Z","snapshot_observed_at":"2026-08-08T18:23:31.977872Z","submitted_at":"2017-10-16T18:05:45Z","title":"Searching for Activation Functions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.05941","snapshot_observed_at":"2026-08-01T06:31:11.897478Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:11.897478Z"},"links":{"cited_paper":"/paper/1710.05941","citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:f70c32a4369df97e66cd72fd3c11f3d720a94df54190cb08ddc85d353c43f625","observation_id":"3989ca4c-5b9c-4530-a7bf-6f203cb13ca5","resolution":{"observed_at":"2026-08-01T06:31:11.897478Z","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":"2026-08-01T06:31:11.949174Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:11.949174Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:3312fdf3cf2384e0eee06495a8b0da53660558eaeb14b276b5a5cfc5640f4e98","observation_id":"c176d36b-0ee9-497c-858d-7830e324370e","resolution":{"observed_at":"2026-08-01T06:31:11.949174Z","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":"2026-08-01T06:31:12.014721Z","title":null,"venue":null,"work_id":null,"year":1978},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:12.014721Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:f28182871dee8be91e4541a384da019395d6432df182c28336b45ca112e36c35","observation_id":"bf733f98-8f0b-44c6-b2bc-7c6c56df3c9b","resolution":{"observed_at":"2026-08-01T06:31:12.014721Z","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":"2026-08-01T06:31:12.074087Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:12.074087Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:7dd9a310fdad62f5d67addd025decf35361d024b7fde9401aee08fbbf10415e4","observation_id":"94534a1e-451e-4b6a-ae20-37207b084b13","resolution":{"observed_at":"2026-08-01T06:31:12.074087Z","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":"2026-08-01T06:31:11.836193Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:11.836193Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:5a7dcab367a3ac133fcdd839e3e0110b3fca1752518e0c142420df585cdc4f4e","observation_id":"74d44454-c287-4753-ac67-5d28eb1bb92d","resolution":{"observed_at":"2026-08-01T06:31:11.836193Z","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":"2026-08-01T06:31:12.304919Z","title":"Microsoft SEAL (release 4.0)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:12.304919Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:cef72f2906886f2403707edde7fa59208e2c1fd437cfb3bd93d232013f871b6f","observation_id":"85c17a8f-daa8-4796-adf1-7478efdf0a56","resolution":{"observed_at":"2026-08-01T06:31:12.304919Z","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":"2026-08-01T06:31:12.413502Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:12.413502Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:8ac82ea87bcf3229ab7a069abd6d34431e3cb1be84b706e58cf87cf89763fa56","observation_id":"5cfbfcfc-55d5-44d6-b606-727c45c85cfa","resolution":{"observed_at":"2026-08-01T06:31:12.413502Z","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":"2026-08-01T06:31:12.529704Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:12.529704Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:3b57fa04338951d0082c376bbbcea1742e0b615740dc6557c6147896b3c9bb39","observation_id":"1290af96-1e9e-4160-99b4-b74784524c6a","resolution":{"observed_at":"2026-08-01T06:31:12.529704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-07-06T03:53:32.549552Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-01T06:31:12.630148Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:12.630148Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:945b9e4692787a092f95e34807a401210986c1611a8b97bc868366d8b9c95d21","observation_id":"d782cb6d-4c7f-4b5a-a7c7-3710f1c07f0f","resolution":{"observed_at":"2026-08-01T06:31:12.630148Z","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":"2026-08-01T06:31:12.167915Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:12.167915Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:ad3d31ea20d70391f460dadd2cb6290839dfb1abc030a2604d850466df678df7","observation_id":"61db2a21-3205-4a04-b946-e066fdda58fa","resolution":{"observed_at":"2026-08-01T06:31:12.167915Z","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":"2026-08-01T06:31:12.824689Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:12.824689Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:335890bf626578f75c1760e1ebf0c85770e28a465f84ce60a7a822cfa12a816d","observation_id":"f2f09925-8e9a-4151-a561-7a2397fc4774","resolution":{"observed_at":"2026-08-01T06:31:12.824689Z","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":"2026-08-01T06:31:12.940415Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:12.940415Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:3bbe5a5be54176e61028c05183ff0c1a4d9d32864b890421e3f8d73ad7b84a39","observation_id":"a0dd9c1e-f491-4eae-8113-8cd955b73414","resolution":{"observed_at":"2026-08-01T06:31:12.940415Z","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":"2026-08-01T06:31:13.032157Z","title":null,"venue":null,"work_id":null,"year":1982},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:13.032157Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:468bffeabafe255225844c907af2ec25cdc8709d957923447283bb98e18e30d5","observation_id":"e7768717-bc3b-41b7-83e6-a395b8c9193c","resolution":{"observed_at":"2026-08-01T06:31:13.032157Z","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":"2026-08-01T06:31:13.121723Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:13.121723Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:f57795f35def0ecaa321044eefa59ba23fe041be918f69e3e042c87ba10f66f6","observation_id":"df9a4438-73ed-42bd-bf13-73221b2920c6","resolution":{"observed_at":"2026-08-01T06:31:13.121723Z","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":"2026-08-01T06:31:12.717326Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:12.717326Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:ae5f5f89d92936329a6018fca079466d5066727525c0f041000cbf6047dd7700","observation_id":"14744be4-40de-4dda-a488-84fa00d65473","resolution":{"observed_at":"2026-08-01T06:31:12.717326Z","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":"2026-08-01T06:31:13.458873Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:13.458873Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:fac029d58a88f7c4a79eef5fc93c42498b62ba8d97a7e7eb6c080f0b20bbfe11","observation_id":"46acf29a-2708-426c-a7fc-049796a6b078","resolution":{"observed_at":"2026-08-01T06:31:13.458873Z","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":"2026-08-01T06:31:13.523900Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:13.523900Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:a35ed0bc020370744c2a99c229c795a720e164a8b81f43ad12405b2f916b4a5c","observation_id":"ef5cf795-6169-4dfc-9151-7d21cfee9c2d","resolution":{"observed_at":"2026-08-01T06:31:13.523900Z","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":"2026-08-01T06:31:13.227572Z","title":"InInternational Conference on Machine Learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:13.227572Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:bbfb4e1628c03838e0cf48b498b2372f32f20ef386619c139cada5d0a1fe497a","observation_id":"bd1fd820-845b-4a9c-90ea-38d08b94b5cb","resolution":{"observed_at":"2026-08-01T06:31:13.227572Z","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":"2026-08-01T06:31:13.322489Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:13.322489Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:d3ab6b12bab240f7a7b6089f2e329dd7ad8a4323de33c49beac9d02e0a3fc766","observation_id":"5419ef46-cab4-47c4-8bc1-aad4a0e89019","resolution":{"observed_at":"2026-08-01T06:31:13.322489Z","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":"2026-08-01T06:31:13.389032Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:13.389032Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:5fbe96e8a3c109a1586bd432418867bb85199054327ceb2fed8328d582a1078e","observation_id":"baba57f0-1bfa-4b2c-b9b2-b06fd9e7df20","resolution":{"observed_at":"2026-08-01T06:31:13.389032Z","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":"2026-08-01T06:31:13.569014Z","title":"• CIFAR10","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:13.569014Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:f1a88a557939f524d3ab6f5d07b50b1e6b202d798dcc02713d71601e51cdbd9d","observation_id":"f620c2b0-0c57-42dd-bd12-673f9a4825bf","resolution":{"observed_at":"2026-08-01T06:31:13.569014Z","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":"2026-08-01T06:31:07.805548Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.805548Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:538cef3f28616e2ee6f87550077855cdda48ea8a7977d76bf3c9916f12d0bb3d","observation_id":"d7eab8bd-c098-4eaf-9a19-19b1f1b923ea","resolution":{"observed_at":"2026-08-01T06:31:07.805548Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1811.09953","last_updated":"2018-11-25T05:56:18Z","snapshot_observed_at":"2026-08-01T16:50:05.340137Z","submitted_at":"2018-11-25T05:56:18Z","title":"Faster CryptoNets: Leveraging Sparsity for Real-World Encrypted Inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.09953","snapshot_observed_at":"2026-08-01T06:31:07.234828Z","title":"arXiv preprint arXiv:1811.09953(2018)","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:07.234828Z"},"links":{"cited_paper":"/paper/1811.09953","citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:841bd8cfe573552c2dd057762d3e884186dc2132c52a4ffbd2082d6cde85d151","observation_id":"a68a4db1-f59a-4960-a14d-a5bddc747f70","resolution":{"observed_at":"2026-08-01T06:31:07.234828Z","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":"2026-08-01T06:31:11.431853Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:11.431853Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:5277743fa5f81c6f833a1c3892dcf98b556cbf9e8081399432bc42c32f1815ba","observation_id":"e21a852e-8900-4b58-8baa-80bb51b8f0ea","resolution":{"observed_at":"2026-08-01T06:31:11.431853Z","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":"2026-08-01T06:31:06.684775Z","title":"InAAAI, Vol","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-01T06:31:06.684775Z"},"links":{"citing_paper":"/paper/2607.21895"},"observation_digest":"sha256:2676c89a340a8bdd956ba762de8b81a5ab6982e29f8b1ab92e3eddd4146c3823","observation_id":"a9a3767a-b379-49d8-84c8-bdbe5de2b597","resolution":{"observed_at":"2026-08-01T06:31:06.684775Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.21895","last_updated":"2026-07-24T01:52:18Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-07T11:05:22.470736Z","submitted_at":"2026-07-24T01:52:18Z","title":"PrivDNN: A Secure Multi-Party Computation Framework for Deep Learning using Partial DNN Encryption"},"reference_resolution":{"displayed":91,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":91,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":91},"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 91 of 91 outbound references and 0 inbound Pith citation observations for arXiv:2607.21895."}