{"as_of":"2026-08-10T01:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:963f7b50f2930529efd18952e739f0e46e45464c575479b76232fae24b34e489","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T17:39:40.298059Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"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/2607.18342/citation-record","integrity":"/paper/2607.18342/integrity","json":"/paper/2607.18342/citation-record.json","paper":"/paper/2607.18342"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T17:39:36.207814Z","title":"Homomorphic encryption for arithmetic of approximate numbers,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:36.207814Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:4a16bce98b10ccb81940334bd12a88ceb174b4e96a41b934901675db1092a59f","observation_id":"62201125-e745-44a8-b1b0-362d113fb4c5","resolution":{"observed_at":"2026-08-01T17:39:36.207814Z","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":"2026-08-01T17:39:36.330101Z","title":"Algorithms in HElib,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:36.330101Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:c5fdf2247f6eff4df560894d782a598ed76c2c0297a9fd6ac2a08a80e25925cd","observation_id":"fa644afc-1ea3-4038-801f-b0dc627129c1","resolution":{"observed_at":"2026-08-01T17:39:36.330101Z","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":"2026-08-01T17:39:36.429247Z","title":"Hunter: HE-friendly structured pruning for efficient privacy-preserving deep learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:36.429247Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:89d9a6db5aa37c3458a17df248c3b230450f7b6b1dd822db657740c5de37976d","observation_id":"82e7f689-5ea0-421e-bdba-6bc4e454cfd2","resolution":{"observed_at":"2026-08-01T17:39:36.429247Z","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":"2026-08-01T17:39:36.539580Z","title":"SpENCNN: Orchestrating encoding and sparsity for fast homomorphically encrypted neural network inference,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:36.539580Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:93e1759c84f9612592d7c05d9fb3f4b252b46808d08a23f29152ef0f6d6761b0","observation_id":"4088eaf0-7370-4242-af70-007cb3b7c773","resolution":{"observed_at":"2026-08-01T17:39:36.539580Z","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":"2026-08-01T17:39:36.656687Z","title":"MOSAIC: A prune- and-assemble approach for efficient model pruning in privacy-preserving deep learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:36.656687Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:d5a23334a96e05919a1d6d6b57bf588bd079f0a2bc226096691dd63a658b5bf4","observation_id":"4fc63899-05ba-4444-abba-e92d50af23c1","resolution":{"observed_at":"2026-08-01T17:39:36.656687Z","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":"2026-08-01T17:39:36.801429Z","title":"PrivCirNet: Efficient private inference via block circulant transformation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:36.801429Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:c6dba2312cfbdc020e43666c2518c9d73aefe15545fdaa99b8a84974a83abc84","observation_id":"1f65b7f3-782f-465d-9ffb-6d4f4feec685","resolution":{"observed_at":"2026-08-01T17:39:36.801429Z","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":"2026-08-01T17:39:36.956440Z","title":"The soft error problem: An architectural perspective,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:36.956440Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:66c4a724dc9b64a52a03cc96d2b332c2ff43e36fcdd3b5a6599fe826e6cfe405","observation_id":"af8eac3f-1a0c-4964-a8cc-73b5d6a156cd","resolution":{"observed_at":"2026-08-01T17:39:36.956440Z","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":"2026-08-01T17:39:37.039560Z","title":"Radiation-induced soft errors in advanced semiconduc- tor technologies,","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:37.039560Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:9a6a2fdb031201c4b9c71059e44f682c5dde6ec6c435cb115cc6ff2043930d9b","observation_id":"d67af2f8-e725-4033-9f33-96d7ff4c86fc","resolution":{"observed_at":"2026-08-01T17:39:37.039560Z","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":"2026-08-01T17:39:37.161906Z","title":"Ares: A framework for quantifying the resilience of deep neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:37.161906Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:e38b784747c05a4e37686c33460da06ec239ee378d67533416ae185325697854","observation_id":"44c0c5dc-f34f-41bb-8ea4-7f8593a08509","resolution":{"observed_at":"2026-08-01T17:39:37.161906Z","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":"2026-08-01T17:39:37.275107Z","title":"Understanding error propagation in deep learning neural network (DNN) accelerators and applications,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:37.275107Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:73b27541bb74f60ec778cea92fa777b4f96393b947f1d90317dd50947a9d78a2","observation_id":"b744bac5-5b1f-4c25-8f35-f0f932c7a5bc","resolution":{"observed_at":"2026-08-01T17:39:37.275107Z","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":"2026-08-01T17:39:37.453908Z","title":"Optimizing selective protection for CNN resilience,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:37.453908Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:c85654523d49f6e1367ff83a0ab63bdd08d893579a06c7f6278de5883ae16844","observation_id":"c586ae8c-929a-4d76-9760-189887ed59c1","resolution":{"observed_at":"2026-08-01T17:39:37.453908Z","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":"2026-08-01T17:39:37.599892Z","title":"BinFI: An efficient fault injector for safety-critical machine learning systems,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:37.599892Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:26022f01e0b99515cbd3d35f8812b3092ef49d5447112fa2ae364a4129a6efe0","observation_id":"b6f76b57-99f7-4a84-9255-4fced215fd08","resolution":{"observed_at":"2026-08-01T17:39:37.599892Z","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":"2026-08-01T17:39:37.715293Z","title":"Reliability analysis of fully homo- morphic encryption systems under memory faults,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:37.715293Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:bb4f94633d2473be08cd6e456df8c429d8ebc7dadcf8384ae9af0ef203d1842a","observation_id":"211074f1-153a-42c9-98e1-5f1618c3b9ff","resolution":{"observed_at":"2026-08-01T17:39:37.715293Z","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":"2026-08-01T17:39:37.821487Z","title":"On the vulnerability of FHE computation to silent data corruption,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:37.821487Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:05d57a3ef0053540ba2e88b18ae9fb18a640b41384af7747a853511c48f683b4","observation_id":"0296922e-3fd8-465d-b5fd-147524e3820b","resolution":{"observed_at":"2026-08-01T17:39:37.821487Z","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":"2026-08-01T17:39:37.919894Z","title":"CryptoNets: Applying neural networks to encrypted data with high throughput and accuracy,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:37.919894Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:150c374266eb248d7d89fd7f85635d3bfb180cbddadecce4a05a0c2a5b739fa6","observation_id":"4e2df855-43cb-496d-a927-92776ef2ad86","resolution":{"observed_at":"2026-08-01T17:39:37.919894Z","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":"2026-08-01T17:39:38.087133Z","title":"GAZELLE: A low latency framework for secure neural network inference,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:38.087133Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:401a17cced2b37962b85bc932691df92a8a6cc1f22e1cc6028ed23d030644ecd","observation_id":"0d27a4a5-be91-475b-988b-3f7d406202cb","resolution":{"observed_at":"2026-08-01T17:39:38.087133Z","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":"2026-08-01T17:39:38.239462Z","title":"CryptoNAS: Private inference on a ReLU budget,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:38.239462Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:ed4cf5744993cfbc9c7ee7001a8e27ef7aa4d0ec12ceb12643ef46095d0ca069","observation_id":"8498c6d5-a3a5-456d-94b5-5906abbc53dc","resolution":{"observed_at":"2026-08-01T17:39:38.239462Z","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":"2026-08-01T17:39:38.374606Z","title":"Privacy-preserving machine learning with fully homomorphic encryption for deep neural networks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:38.374606Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:fd0d7bd166b47f14f373be4cd4c4892423b92b6ec91a7de18e4a63276d35561c","observation_id":"47bd67a4-bd03-494b-ab4e-9ed5d2963270","resolution":{"observed_at":"2026-08-01T17:39:38.374606Z","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":"2026-08-01T17:39:38.470632Z","title":"HyPHEN: A hybrid packing method and its optimizations for homomorphic encryption-based neural networks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:38.470632Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:c402f0f916ad34004ed7484711e6fa02a08e75a6664a918988fc54efa615de93","observation_id":"385a92fa-abc1-4302-838a-cd43800e74b8","resolution":{"observed_at":"2026-08-01T17:39:38.470632Z","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":"2026-08-01T17:39:38.596372Z","title":"Efficient pruning for machine learning under homomorphic encryption,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:38.596372Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:c3fbf4024272a013b4832d1d0ddfe2aa172862a25c4d323a1c9614b7b23d7ae5","observation_id":"a2d48553-426d-4ad6-886f-fbe5ff5c0a27","resolution":{"observed_at":"2026-08-01T17:39:38.596372Z","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":"2026-08-01T17:39:38.710998Z","title":"MOFHEI: Model optimizing framework for fast and efficient homomor- phically encrypted neural network inference,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:38.710998Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:93d0eda7f5ec0f008677b9a2ea2b79e54f7ccba4280c89767e7a8dfb87d63e2b","observation_id":"cee88647-2f80-44e6-a23d-bea04505995f","resolution":{"observed_at":"2026-08-01T17:39:38.710998Z","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":"2026-08-01T17:39:38.822866Z","title":"AutoFHE: Automated adaption of CNNs for efficient evaluation over FHE,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:38.822866Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:d4e582463b360086fd7fdd0c466615cef673218a70579cfc1011e7f1b1500fe8","observation_id":"2977fe1c-79ed-49b8-b824-5c53a4959fa6","resolution":{"observed_at":"2026-08-01T17:39:38.822866Z","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":"2026-08-01T17:39:38.931577Z","title":"Pruning filters for efficient convnets,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:38.931577Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:4c436b4924c36a28be096ebf7ef9e81c3dea6d684ac42175fdab5c467f6a4a74","observation_id":"31d4e0c1-5728-47eb-9f1a-8bad3857e2b6","resolution":{"observed_at":"2026-08-01T17:39:38.931577Z","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":"2026-08-01T17:39:39.047951Z","title":"Channel pruning for accelerating very deep neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:39.047951Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:e5e502cae0ea495e82e6160e39a4db06f99e0910cc4e084cbdcca37009c2b944","observation_id":"caab124c-fca5-4b94-954b-8c1491943c71","resolution":{"observed_at":"2026-08-01T17:39:39.047951Z","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":"2026-08-01T17:39:39.160804Z","title":"TFHE: Fast fully homomorphic encryption over the torus,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:39.160804Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:ce236e82098872679e9a00b9a6597af798263dbcd3bb2041c9c6750c43c9716e","observation_id":"497d4357-83ef-44a9-af18-a82b6c2939c0","resolution":{"observed_at":"2026-08-01T17:39:39.160804Z","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":"2026-08-01T17:39:39.269074Z","title":"GlitchFHE: Attacking fully homomorphic encryption using fault injection,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:39.269074Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:2620049d9569645f14932a9009af920d2d1f92df58a8b7425ea77d69d91ab6ab","observation_id":"33a7b735-7022-49b0-95dd-b71dba69f2e3","resolution":{"observed_at":"2026-08-01T17:39:39.269074Z","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":"2026-08-01T17:39:39.373493Z","title":"Self-learning activation functions to increase accuracy of privacy-preserving convolutional neural networks with homomorphic encryption,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:39.373493Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:ebec8ed24fdd87fbf5ed247375c2d48c26e775be72e9a241dfd8a59f24703e10","observation_id":"35a56f5d-d421-4451-97e8-3f9710edc99e","resolution":{"observed_at":"2026-08-01T17:39:39.373493Z","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":"2026-08-01T17:39:39.447323Z","title":"Highly accurate cnn inference using approximate activation functions over homomorphic encryption,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:39.447323Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:3e9dfe72d6ee859be180bf828116f21d0112a1bd6bee6879b5902b30ab7fc0de","observation_id":"b8f83672-35cc-45a5-b9d9-c494011e6300","resolution":{"observed_at":"2026-08-01T17:39:39.447323Z","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":"2026-08-01T17:39:39.559717Z","title":"Efficient bootstrapping for approximate homomorphic encryption with non-sparse keys,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:39.559717Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:e6082a5777da40f917219f2e9a949f095706de22843ee5230e99fb29c4d7e641","observation_id":"788dc79f-f058-4d9e-ae4c-179f6147d127","resolution":{"observed_at":"2026-08-01T17:39:39.559717Z","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":"2026-08-01T17:39:39.673822Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:39.673822Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:99985ffb0bdf564058cad6909261532349fbf57d76edad499cd7796db8a52f99","observation_id":"e6ce595d-5796-408c-a52e-9caa001f5cd1","resolution":{"observed_at":"2026-08-01T17:39:39.673822Z","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":"2026-08-01T17:39:39.820093Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:39.820093Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:5ccc4ff06d3200481741d9b1c18233a35cdf8f89e63b6ff89dbcffee0acacb28","observation_id":"290c37a0-fe3f-402e-a6f5-a80177f0a0a9","resolution":{"observed_at":"2026-08-01T17:39:39.820093Z","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":"2026-08-01T17:39:39.963171Z","title":"DeepReDuce: ReLU reduction for fast private inference,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:39.963171Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:229b6c1be25b56158a145677fa70b2f0853a8a575b56cfa63f9b19daed6ffd09","observation_id":"b9072b68-fa52-4fcf-abde-654d5d7db0bd","resolution":{"observed_at":"2026-08-01T17:39:39.963171Z","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":"2026-08-01T17:39:40.062981Z","title":"OpenFHE: Open-source fully homomorphic encryption library,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:40.062981Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:8e981784e4f5be7890642e029a0fe819a4e37687c7bcc2b2fa965eced5a74933","observation_id":"9ac69b9c-29ac-4288-810a-9f24384023bc","resolution":{"observed_at":"2026-08-01T17:39:40.062981Z","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":"2026-08-01T17:39:40.194664Z","title":"Statistical fault injection: Quantified error and confidence,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:40.194664Z"},"links":{"citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:1b9a9e93db9f79157735b55bc080173236e1d2482ec9379e556861f7e121f09d","observation_id":"05742c53-1731-43f5-8876-0d103aefed89","resolution":{"observed_at":"2026-08-01T17:39:40.194664Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.06699","last_updated":"2022-02-18T05:10:15Z","snapshot_observed_at":"2026-08-03T21:42:54.808569Z","submitted_at":"2022-01-18T02:02:02Z","title":"AESPA: Accuracy Preserving Low-degree Polynomial Activation for Fast Private Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.06699","snapshot_observed_at":"2026-08-01T17:39:40.298059Z","title":"AESPA: Accuracy preserving low-degree polynomial activation for fast private inference,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T17:39:40.298059Z"},"links":{"cited_paper":"/paper/2201.06699","citing_paper":"/paper/2607.18342"},"observation_digest":"sha256:78384cfa6fe922893645a513020a804ccb0095fbf0fd97a150d5b417b7de939d","observation_id":"f741a7cc-450d-4305-93aa-e5d47dd86d25","resolution":{"observed_at":"2026-08-01T17:39:40.298059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.18342","last_updated":"2026-07-20T05:47:06Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-07T23:01:58.047269Z","submitted_at":"2026-07-20T05:47:06Z","title":"PRISM: Sensitivity-Aware PolynoMial PRuning for EffIcient Neural Network Encryption"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":35,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":35},"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 10 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2607.18342."}