{"as_of":"2026-08-10T13:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c373a00dc0e65d89efa225cc3d9e00d95ffcd048a347f257725f02501f21f572","coverage":[{"denominator":74,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":74,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T23:29:02.024766Z","state":"measured"},{"denominator":75,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":75,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T11:16:58.039873Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-05T11:16:58.067785Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"cited_work":{"arxiv_id":"2506.18150","doi":null,"metadata_source":"pith","pith_arxiv_id":"2506.18150","snapshot_observed_at":"2026-08-05T11:16:58.067785Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","venue":"cs.CR","work_id":"e08d5053-f9dd-4cc0-9f61-6b21eb2af958","year":2025},"citing_paper":{"arxiv_id":"2509.03024","last_updated":"2025-09-03T05:15:45Z","snapshot_observed_at":"2026-08-07T22:02:21.243632Z","submitted_at":"2025-09-03T05:15:45Z","title":"Efficient Privacy-Preserving Recommendation on Sparse Data using Fully Homomorphic Encryption","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T11:16:58.039873Z"},"links":{"cited_paper":"/paper/2506.18150","citing_paper":"/paper/2509.03024"},"observation_digest":"sha256:fd89a6fd77ee79c4352c5e5dd3c5dfe58d79c9367338b3127e32fbdd40991a8a","observation_id":"e67127bd-4b1c-48bd-8502-e9d5cbf83d0c","resolution":{"observed_at":"2026-08-05T11:16:58.072958Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.18150/citation-record","integrity":"/paper/2506.18150/integrity","json":"/paper/2506.18150/citation-record.json","paper":"/paper/2506.18150"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:23.106829Z","title":"Fab: An fpga- based accelerator for bootstrappable fully homomorphic encryption","venue":null,"work_id":"856510cc-5a62-4569-939e-5334e9734fd5","year":2023},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:48.876803Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:7109f0eff4184875ebfc9149e0bab6b8fd23e6a79303a3618c37bb6f6f0c3348","observation_id":"d4052248-b8b8-45a2-8a86-55ea3c315c20","resolution":{"observed_at":"2026-08-06T23:29:23.254171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2011.01805","last_updated":"2023-01-01T07:41:18Z","snapshot_observed_at":"2026-08-08T01:51:28.294746Z","submitted_at":"2020-11-03T15:54:35Z","title":"HeLayers: A Tile Tensors Framework for Large Neural Networks on Encrypted Data","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2011.01805","snapshot_observed_at":"2026-08-06T23:28:49.094747Z","title":"Helayers: A tile tensors framework for large neural networks on encrypted data.arXiv preprint arXiv:2011.01805, 2020","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:49.094747Z"},"links":{"cited_paper":"/paper/2011.01805","citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:eb824daf3261960935a7812dfbefb9d74040d84120d15b61751d1dba8423e452","observation_id":"5925ef21-83e1-42f4-8804-49f93704123a","resolution":{"observed_at":"2026-08-06T23:28:49.094747Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:22.788653Z","title":"Llama 3 model card","venue":null,"work_id":"949b82e0-25b8-46bc-95b9-8db87b243ae4","year":2024},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:49.224745Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:95a086a62962c702741598d900961610a306d9847d19c216811cba14d5f3a994","observation_id":"33e88d88-9947-4300-bc25-72260b2aaede","resolution":{"observed_at":"2026-08-06T23:29:22.934195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:22.493195Z","title":"Privft: Private and fast text classification with homomorphic encryption.IEEE Access, 8:226544–226556, 2020","venue":null,"work_id":"da59bef5-962e-44de-b1e4-cf440da1799f","year":2020},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:49.376877Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:3cc2ca7789fdfe54c0562d048d36358d89dc642abe599daa796f6a1d6bd13299","observation_id":"8f5b0dab-448e-43e2-8afd-2fee477655ab","resolution":{"observed_at":"2026-08-06T23:29:22.612384Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.03152","last_updated":"2021-04-28T04:44:18Z","snapshot_observed_at":"2026-07-06T10:57:17.838513Z","submitted_at":"2021-04-07T14:32:38Z","title":"TenSEAL: A Library for Encrypted Tensor Operations Using Homomorphic Encryption","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.03152","snapshot_observed_at":"2026-08-06T23:28:49.564750Z","title":"Tenseal: A library for encrypted tensor operations using homomorphic encryption.arXiv preprint arXiv:2104.03152, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:49.564750Z"},"links":{"cited_paper":"/paper/2104.03152","citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:1399e5564a5dd05b954eb6a1a74611b47744207c90f76d5c7f4f622f55786caa","observation_id":"5c721210-936a-4e8e-b932-5f27f3a10bb6","resolution":{"observed_at":"2026-08-06T23:28:49.564750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:22.101040Z","title":"ngraph-he2: A high- throughput framework for neural network inference on encrypted data","venue":null,"work_id":"b0487869-d783-4504-bbf8-28b99288f794","year":2019},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:49.694755Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:73a3d24c9a06bdb522196d6cce92fb5041aaf22a0fe02198f3cc19e5eb40ba47","observation_id":"1772cc59-7e5d-44cc-af92-d58141556f99","resolution":{"observed_at":"2026-08-06T23:29:22.269835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:21.832587Z","title":"ngraph-he: a graph compiler for deep learning on homomorphically encrypted data","venue":null,"work_id":"25c330d5-0be5-41b1-8ef7-6e816787719a","year":2019},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:49.807033Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:2e28af0a4fa99720800b139c2ba608e575e8aa50d2ca89cdb0dc2091b2307bae","observation_id":"b7f7c877-4e73-498c-a7df-1dd1c44329ad","resolution":{"observed_at":"2026-08-06T23:29:21.947723Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:21.443425Z","title":"Efficient bootstrapping for approximate homomorphic encryption with non-sparse keys","venue":null,"work_id":"310c8a4b-efb3-4ffd-baeb-d9be1b84092f","year":2021},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:50.034742Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:846ffea5f4046718130fda169ec2919c6d35ef6c8d1a2c14e8643b7f7b5fb848","observation_id":"1f87cbc5-4dec-40a6-9dba-a478caecaadf","resolution":{"observed_at":"2026-08-06T23:29:21.582166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:21.097891Z","title":"Fast homomorphic evaluation of deep discretized neural networks","venue":null,"work_id":"a99f38b4-ae3f-41a7-b066-2f796ae76bb0","year":2018},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:50.213669Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:c9a515e1c9d1443e1df8200987c13ba88bbb9a94e701e6ee8ccfdf1e1f7b0ff3","observation_id":"a712a14b-f3e3-43e7-9f1d-78b80d5e3dbc","resolution":{"observed_at":"2026-08-06T23:29:21.303098Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.00216","last_updated":"2022-06-02T01:06:12Z","snapshot_observed_at":"2026-07-06T13:16:13.214340Z","submitted_at":"2022-06-01T03:49:18Z","title":"THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.00216","snapshot_observed_at":"2026-08-06T23:28:50.462610Z","title":"The-x: Privacy-preserving transformer in- ference with homomorphic encryption.arXiv preprint arXiv:2206.00216, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:50.462610Z"},"links":{"cited_paper":"/paper/2206.00216","citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:db6db6feee2841b845178654bb6e92ec79ef88e4841361b552736a4551da7397","observation_id":"4f8878e7-047c-4ea0-9cae-529ca10f051f","resolution":{"observed_at":"2026-08-06T23:28:50.462610Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:20.729923Z","title":"Bootstrapping for approxi- mate homomorphic encryption","venue":null,"work_id":"bd8541c4-6a0f-4114-9df5-0bc30f605bdd","year":2018},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:50.644845Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:adceebfd6bc3a5da4993b5d804097b50c9c0326bd0ac972a7355d0c04f727bb5","observation_id":"2953b95d-08cf-4e22-9888-2a1a876170c5","resolution":{"observed_at":"2026-08-06T23:29:20.956308Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:20.389978Z","title":"Homomorphic encryption for arithmetic of approximate numbers","venue":null,"work_id":"c8d1e049-8a54-418f-8332-90c38c486480","year":2017},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:50.811888Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:5e612e4dd1f3addf571ead2602c9166d7c3c3cd47b702b09d25c252e3d099268","observation_id":"3519b341-0c29-40f1-99fb-c072d3252748","resolution":{"observed_at":"2026-08-06T23:29:20.560152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:20.060673Z","title":"{DaCapo}: Automatic boot- strapping management for efficient fully homomorphic encryption","venue":null,"work_id":"952406de-a6b2-4c94-9a49-96df6bca5387","year":2024},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:50.980049Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:d301f766844ac46c044686367bbfa73f2edcf97c834cb8d90cbd47297a50e1ee","observation_id":"ba4fe332-1261-46ab-82b9-d1b70727d522","resolution":{"observed_at":"2026-08-06T23:29:20.230864Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:19.682275Z","title":"Ched- dar: A swift fully homomorphic encryption library de- signed for gpu architectures","venue":null,"work_id":"bd36b448-2d42-40e6-815e-7bf5e692cbe6","year":2026},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:51.160549Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:598df4311d909c47010e95641a9abbbc361c1cebb0124c5f80fc47b1b422e79e","observation_id":"a6d6f250-98de-43ea-9054-e2b3532d7315","resolution":{"observed_at":"2026-08-06T23:29:19.862178Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:19.413905Z","title":"Por- cupine: A synthesizing compiler for vectorized homo- morphic encryption","venue":null,"work_id":"ae7917b1-a1c5-4fd1-b9b2-50016b6bada6","year":2021},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:51.355054Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:2aec19df226d6bbc0bf4b3c3ae341c6eb0e1ab63f14ea4fa7914ac4abac373b6","observation_id":"bc88a735-e159-4a59-8a06-ebe74c05846c","resolution":{"observed_at":"2026-08-06T23:29:19.544907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:19.144180Z","title":"Criteo display advertising chal- lenge dataset","venue":null,"work_id":"a6b467ec-f2f1-4490-a6f3-760ae7bfcc46","year":2014},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:51.564747Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:30566243ac122d5e97c727e00fd9d7c5183a14bbac6cede80407bd5b749c7023","observation_id":"a3c70f5c-53d7-4b31-a480-6900bae7188c","resolution":{"observed_at":"2026-08-06T23:29:19.263002Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:18.655443Z","title":"cuHE: CUDA homomorphic encryption library","venue":null,"work_id":"e4daa33d-b090-4011-9c70-c7dfd6e407cb","year":null},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:51.830176Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:488c35f4ef2e8d1c5732214a37a70bd448917d35536423050582c4d508b61c49","observation_id":"5be59d18-bc0d-46ef-8b9b-b763f144da1a","resolution":{"observed_at":"2026-08-06T23:29:18.972894Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:18.413707Z","title":"Eva: An encrypted vector arithmetic language and compiler for efficient homomorphic computation","venue":null,"work_id":"d41c6951-57d0-4bb1-b9de-7def183b7f46","year":2020},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:52.054754Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:3af2bfa8c37586f107fdd2110a547f772dc434cbbe8423af080bef5c917fe363","observation_id":"085eebdf-54c0-4835-bc37-e4b3456c4d6a","resolution":{"observed_at":"2026-08-06T23:29:18.503087Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:18.135090Z","title":"Chet: an optimizing compiler for fully-homomorphic neural-network inferencing","venue":null,"work_id":"452ebd75-81ba-48b5-b5cb-a45193c684bd","year":2019},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:52.233742Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:63fceff42651b09c83038ebd9296b88f1d9d1f5c3593837e4d62a4026ea65944","observation_id":"95732404-1a69-4d83-a72b-260bab81c5a1","resolution":{"observed_at":"2026-08-06T23:29:18.245208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:17.739214Z","title":"Low-precision hardware architectures meet recommendation model in- ference at scale.IEEE Micro, 41(5):93–100, 2021","venue":null,"work_id":"d8381453-2111-4a6d-a5fd-0c24a8019bf3","year":2021},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:52.439242Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:9b163ec9bd0fee9ae3d6f0f4d273507fb1be1b6fd282dec45c3b98d57eff4bf5","observation_id":"dbdfd408-8b88-481b-9ff6-5818b73e8b95","resolution":{"observed_at":"2026-08-06T23:29:17.913508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:28:52.615271Z","title":"A unified vector processing unit for fully homomorphic encryption","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:52.615271Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:47a749bb2c0650d38f73c39b8f99ed80bed3be39e4945430003f2b1f21354ff8","observation_id":"e2642eaa-84b1-4a08-949b-b5f5a842e673","resolution":{"observed_at":"2026-08-06T23:28:52.615271Z","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":"2026-08-06T23:28:52.794865Z","title":"Orion: A fully homomorphic encryption framework for deep learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:52.794865Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:031ab3917a9c9e1bd977e9788ab8ea94e3f0d1c201d3ce87d668408973dbffe3","observation_id":"6ba9a284-6aed-453f-a6fd-21d00421b034","resolution":{"observed_at":"2026-08-06T23:28:52.794865Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:17.385100Z","title":"Osiris: A systolic approach to accelerating fully homomorphic encryption","venue":null,"work_id":"e5314b96-f32f-489d-b5c5-64b01d4d40eb","year":2024},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:52.994974Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:086f58dac7aeee0797902fd751130f62983869d0c6cfaa1e654953fb909ad715","observation_id":"57b29ce2-d935-4edc-be7b-1237583b09d2","resolution":{"observed_at":"2026-08-06T23:29:17.575912Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:28:53.244858Z","title":"A pragmatic introduction to secure multi-party com- putation.Found","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:53.244858Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:8edc4f40e46ff02ed74a8731e61e87299b9d32eeebf840e76199b3a0aa34d4b1","observation_id":"686e318d-0ebe-4d45-8b48-0a057cedc5ef","resolution":{"observed_at":"2026-08-06T23:28:53.244858Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.05371","last_updated":"2021-09-25T14:41:13Z","snapshot_observed_at":"2026-08-08T11:36:22.423281Z","submitted_at":"2021-09-11T21:07:21Z","title":"F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption (Extended Version)","version":2},"cited_work":{"arxiv_id":"2109.05371","doi":null,"metadata_source":"pith","pith_arxiv_id":"2109.05371","snapshot_observed_at":"2026-08-06T23:29:05.546222Z","title":"F1: A Fast and Programmable Accelerator for Fully Homomorphic Encryption (Extended Version)","venue":"cs.CR","work_id":"7cfaf84a-322c-4a24-949d-9ac29d53a046","year":2021},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:53.466825Z"},"links":{"cited_paper":"/paper/2109.05371","citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:8e6b28b7a34fb561a64b2bfbd171cfbda5d66e65797606e474672a2561fa9d29","observation_id":"10033372-1d56-44bc-b5a5-ab1c7519ad2d","resolution":{"observed_at":"2026-08-06T23:29:05.704742Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:28:53.720924Z","title":"Fully homomorphic encryption using ideal lattices","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:53.720924Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:dd4aae4f4c69d017cd6ecfa1c83b8d717beae7d20c2d967b1055606fd25a6f87","observation_id":"09b9926e-cfb4-4a5e-9a71-52a686352fa5","resolution":{"observed_at":"2026-08-06T23:28:53.720924Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2203.15837","last_updated":"2022-03-28T06:07:30Z","snapshot_observed_at":"2026-08-02T08:12:42.765915Z","submitted_at":"2022-03-28T06:07:30Z","title":"Learning to Collide: Recommendation System Model Compression with Learned Hash Functions","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.15837","snapshot_observed_at":"2026-08-06T23:28:53.904925Z","title":"Learning to collide: Recommendation system model compres- sion with learned hash functions.arXiv preprint arXiv:2203.15837, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:53.904925Z"},"links":{"cited_paper":"/paper/2203.15837","citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:d01cf921a258f2f28ee5f19307dfcb9a270df9a4ed3fd9cd7aed1e1ad954d947","observation_id":"16ae08c8-23b7-4d00-a9ac-702c8509ff60","resolution":{"observed_at":"2026-08-06T23:28:53.904925Z","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":"2026-08-06T23:28:54.164875Z","title":"Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:54.164875Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:e09d98d37a40a42375208d1dd60ea6e1a85c075a740eb5f3a1e42a6180ce9eef","observation_id":"35dcc6ed-0b3f-4107-947b-beb19413eba7","resolution":{"observed_at":"2026-08-06T23:28:54.164875Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.02079","last_updated":"2019-11-05T20:43:51Z","snapshot_observed_at":"2026-07-06T08:34:58.548831Z","submitted_at":"2019-11-05T20:43:51Z","title":"Post-Training 4-bit Quantization on Embedding Tables","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.02079","snapshot_observed_at":"2026-08-06T23:28:54.354254Z","title":"Post-training 4-bit quantization on embedding tables.arXiv preprint arXiv:1911.02079, 2019","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:54.354254Z"},"links":{"cited_paper":"/paper/1911.02079","citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:2a02eaf53f236c4e4a1a8c1a75b1a8bdef8698f8dcadac0e991ec3e607374eda","observation_id":"1261428b-a3dd-4b4c-ac5b-b346e9c2fda4","resolution":{"observed_at":"2026-08-06T23:28:54.354254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1906.03109","last_updated":"2020-02-15T17:58:32Z","snapshot_observed_at":"2026-08-02T16:00:42.826647Z","submitted_at":"2019-06-06T03:04:30Z","title":"The Architectural Implications of Facebook's DNN-based Personalized Recommendation","version":4},"cited_work":{"arxiv_id":"1906.03109","doi":null,"metadata_source":"pith","pith_arxiv_id":"1906.03109","snapshot_observed_at":"2026-08-06T23:29:04.977428Z","title":"The Architectural Implications of Facebook's DNN-based Personalized Recommendation","venue":"cs.DC","work_id":"4e7ad995-af57-444d-87b0-e74fb11d9405","year":2019},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:54.561970Z"},"links":{"cited_paper":"/paper/1906.03109","citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:dfbb14b77aa29ce923a78d84b85c8d29a30ea64f9da6b31e5a41db55f8437ebe","observation_id":"caf12507-7a06-47e2-8b3c-33840e02dfc3","resolution":{"observed_at":"2026-08-06T23:29:05.094748Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:17.063713Z","title":"CipherGPT: Secure two-party GPT inference","venue":null,"work_id":"a097ef85-3329-47c5-8d07-09bbcc2e2b9d","year":2023},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:54.764801Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:8c2e2212b876f435f01dca3ce17d5f1b22ca29ed8becd0fee028b96f4120d5f4","observation_id":"d4be4972-50d1-483e-a5b3-1bd8c4e4523f","resolution":{"observed_at":"2026-08-06T23:29:17.181472Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:16.700800Z","title":"Cheetah: Lean and fast secure Two-Party deep neural network inference","venue":null,"work_id":"90ddb0b7-d29f-42cc-8c41-d524fb2ed9d8","year":2022},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:54.946236Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:b1523d941f58f608337580f8f35289714592185003160940327f9cddb28a08c1","observation_id":"2cd39720-97cd-484b-9e1b-c000f16f0ca2","resolution":{"observed_at":"2026-08-06T23:29:16.806499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:16.289033Z","title":"tiktoken: A fast bpe to- keniser for use with openai’s models.https://github","venue":null,"work_id":"3a6c71d5-84c5-4a0d-87de-8114eee0f9e7","year":2022},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:55.192715Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:22575c3bbe6c17eb34950b753c7c5a52cfae57767a378c836ee6d82fb9a113f0","observation_id":"fb636029-c2e3-4480-bca4-4e2191746074","resolution":{"observed_at":"2026-08-06T23:29:16.554743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:28:55.584826Z","title":"Heart Disease","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:55.584826Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:b30f8543456c136db5a069cff77b39d7ce293c9e92d32e32bc430ad9324f6990","observation_id":"dad4e68a-c7f1-4165-ba73-b04036857259","resolution":{"observed_at":"2026-08-06T23:28:55.584826Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:15.943775Z","title":null,"venue":null,"work_id":"26c8bab6-a99a-42e7-971a-ac1e0b992ce3","year":2021},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:55.764816Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:b92390161c08eb2e2616c26768f5ef65655d9db68231544ecf21fb717984ff61","observation_id":"5aac9ef1-b106-435b-9f9c-2884a6f426aa","resolution":{"observed_at":"2026-08-06T23:29:16.070487Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:15.448616Z","title":"GAZELLE: A low latency framework for secure neural network inference","venue":null,"work_id":"440d4a24-53fa-4a82-836e-8775b9e118f7","year":2018},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:55.944962Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:442110c14c4882d85a39473abbf878b78c42f94034e53972f2a5c940109d6147","observation_id":"ea83241d-6b40-4a33-a041-ce68a848c638","resolution":{"observed_at":"2026-08-06T23:29:15.600920Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:14.985444Z","title":"Learning multi-granular quantized embeddings for large- vocab categorical features in recommender systems","venue":null,"work_id":"95221afd-50eb-42fb-aa6b-aba11bc1217c","year":2020},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:56.154743Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:04e83fab6f3e7ddc2761e01fe2d0deaaaffdaf34cdc3c1f8fd97854fc31d21e6","observation_id":"3bdaa6a8-3144-4bdc-8fba-b3583136098b","resolution":{"observed_at":"2026-08-06T23:29:15.284770Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:14.712655Z","title":"Sharp: A short-word hierarchical accelerator for robust and prac- tical fully homomorphic encryption","venue":null,"work_id":"fd598010-7014-4d52-bbe3-9250b8207b86","year":2023},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:56.384824Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:ace6af9a05e172599a5d406f764f81affff12e9dec7fc4db3bf4470b7e535971","observation_id":"83cdf5ca-adf9-4a40-a88b-e9b3dce29b49","resolution":{"observed_at":"2026-08-06T23:29:14.802342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:28:56.574864Z","title":"ARK: Fully homomorphic encryption accelerator with runtime data generation and inter-operation key reuse","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:56.574864Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:1a0563c1b2a47af01832182d81155f44ab41896b4b13885c48d466d5d57687bb","observation_id":"09f3c397-3e82-4ccc-99a2-3c1e12f74d8f","resolution":{"observed_at":"2026-08-06T23:28:56.574864Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:14.401409Z","title":null,"venue":null,"work_id":"a2c64d0c-8c6c-4c8d-adb8-fcb5adda4b1d","year":null},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:56.924756Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:fb909518481eda3dfb6f0dfe0538bee14f809c11fe6b8ffbac0879e19737e585","observation_id":"a1bbbadd-e630-40a6-a124-ef35d5710880","resolution":{"observed_at":"2026-08-06T23:29:14.554755Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:13.842758Z","title":"Mascot: A quantization framework for efficient matrix factorization in recommender systems","venue":null,"work_id":"33aeca79-e140-4dcc-99c3-159688a50275","year":2021},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:57.164675Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:f769ee37e4ada0fadb10c7707947d552d37811318b3e6bc992026d9bd3acb32e","observation_id":"46966d2d-f194-4093-9d38-6a0e8bfa3519","resolution":{"observed_at":"2026-08-06T23:29:14.014577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:13.574948Z","title":"A tensor compiler with automatic data packing for simple and efficient fully homomorphic encryption.Proceedings of the ACM on Programming Languages, 8(PLDI):126– 150, 2024","venue":null,"work_id":"fd8c45d9-6a43-409c-ad39-7e0191f11db5","year":2024},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:57.324823Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:81902b1b73d02db13ec28951711da81c1b3f7e1df4c4d0046a1079ea0a053995","observation_id":"848f6d67-62b5-4f54-89bb-39d3cfff1b0a","resolution":{"observed_at":"2026-08-06T23:29:13.694919Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:13.264749Z","title":"Low-complexity deep convolutional neural networks on fully homomorphic encryption using multiplexed parallel convolutions","venue":null,"work_id":"a653efc5-de9c-4f37-845f-fa5b545fd145","year":2022},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:57.401196Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:48fe995c009f4cebbcf886ee153802c1e111d98da8110f30b037acde7dfd5be1","observation_id":"3a3f255a-c643-49de-a757-61aa52864fa4","resolution":{"observed_at":"2026-08-06T23:29:13.403551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.02574","last_updated":"2022-10-05T21:46:02Z","snapshot_observed_at":"2026-08-07T18:21:07.375080Z","submitted_at":"2022-10-05T21:46:02Z","title":"Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption","version":1},"cited_work":{"arxiv_id":"2210.02574","doi":null,"metadata_source":"pith","pith_arxiv_id":"2210.02574","snapshot_observed_at":"2026-08-06T23:29:04.275003Z","title":"Privacy-Preserving Text Classification on BERT Embeddings with Homomorphic Encryption","venue":"cs.CL","work_id":"9b83d97a-ca15-4bff-88bb-b665fd7a019b","year":2022},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:57.520264Z"},"links":{"cited_paper":"/paper/2210.02574","citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:ac9f1fb78c5fbb4e26e697208e6bdc5402017f68e3c4bbf477eea873863ecfb3","observation_id":"5c661e03-4ef5-4e89-ae75-7ab98f1bb3d8","resolution":{"observed_at":"2026-08-06T23:29:04.461364Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-07-30T09:12:38.100527Z","submitted_at":"2018-10-11T00:50:01Z","title":"BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.04805","snapshot_observed_at":"2026-08-06T23:28:57.664738Z","title":"Pre-training of deep bidirectional transformers for language understand- ing.arXiv preprint arXiv:1810.04805, 3(8):4171–4186, 2018","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:57.664738Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:e9d62d6beb488ff3be122af13689a10a212f2dea65590d61b44cf59113ec3420","observation_id":"d2a07826-0d96-42bd-ab0f-5137c986add5","resolution":{"observed_at":"2026-08-06T23:28:57.664738Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:12.936159Z","title":"{ELASM}:{Error- Latency-Aware} scale management for fully homomor- phic encryption","venue":null,"work_id":"8442cff1-e825-4373-a206-b67512d24a69","year":2023},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:57.794746Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:05800a15451cf6fa5a0a17402c3fdb47ca5f895dc4f1659e8b0fab73f11c739f","observation_id":"e76b3105-7666-436a-8053-57508db4a93d","resolution":{"observed_at":"2026-08-06T23:29:13.084989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:12.701204Z","title":"Hecate: Performance-aware scale optimization for homomorphic encryption compiler","venue":null,"work_id":"e39ff6fa-0187-4dcb-8f74-be09982695b6","year":2022},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:58.054754Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:676b1dbe34fe0d2d2ac39fe631d802a5f7850d4af147ec7359a3cbe4d977c355","observation_id":"1ed798e9-367f-4b75-9cf7-a58d5f346881","resolution":{"observed_at":"2026-08-06T23:29:12.814780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:12.443931Z","title":"Fastquery: Communication- efficient embedding table query for private llm inference,","venue":null,"work_id":"a76e6916-a62d-423d-bef6-1909f260ec05","year":null},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:58.174943Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:b2d6ad45268798f59c2d4c690e108bd871d5b816ee50a2fb05c3fc32afe9c86e","observation_id":"a4557f4b-09fa-40b5-861b-36adcae95400","resolution":{"observed_at":"2026-08-06T23:29:12.524749Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:12.180990Z","title":"Oblivious neural network predictions via minionn trans- formations","venue":null,"work_id":"0e1605b6-cc48-4457-8a20-8e1aa0fb6e94","year":2017},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:58.429855Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:aa642e6fa8ee7546dd7d8528f2fe0b16c4d7c603dc520e13602fcad618b85d82","observation_id":"613450b1-3035-40c8-becc-e2e21ab9a8ed","resolution":{"observed_at":"2026-08-06T23:29:12.331112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:11.714747Z","title":"Cafe+: Towards compact, adaptive, and fast embedding for large-scale online recommendation models.ACM Transactions on Information Systems, 2025","venue":null,"work_id":"2a33b426-b563-4a94-982d-3185186778da","year":2025},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:58.542936Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:c08715fb09cc9f85bab2dcd22691c275862b075635c3f35050f399bee71dd771","observation_id":"730d8d2a-ee84-418a-ac79-55aa995ce5c6","resolution":{"observed_at":"2026-08-06T23:29:11.904765Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:11.244752Z","title":"Coy- ote: A compiler for vectorizing encrypted arithmetic circuits","venue":null,"work_id":"5540e438-7b59-4c78-b41d-259d00590d10","year":2023},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:58.664351Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:48bc538d53b157bd0f519a6eb8c3b72fd4bb1b385ae31e907cca289444886738","observation_id":"bbb8fd83-14fc-4428-8a63-9b5206c33f2b","resolution":{"observed_at":"2026-08-06T23:29:11.495104Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:10.963649Z","title":"Thor: Secure transformer inference with homo- morphic encryption","venue":null,"work_id":"87690d6c-ca62-4171-8576-a7ec65180d4c","year":2025},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:58.834820Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:00d028ec41ea60af05fde4aef2b00ec70aae8d1194c02d2eb0c4007d2d844ce8","observation_id":"77e81082-97e9-4f4c-83bb-88422f3a026c","resolution":{"observed_at":"2026-08-06T23:29:11.017967Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1906.00091","last_updated":"2019-05-31T21:51:16Z","snapshot_observed_at":"2026-08-02T13:53:54.252223Z","submitted_at":"2019-05-31T21:51:16Z","title":"Deep Learning Recommendation Model for Personalization and Recommendation Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1906.00091","snapshot_observed_at":"2026-08-06T23:28:58.999330Z","title":"Deep learning recommen- dation model for personalization and recommendation systems.arXiv preprint arXiv:1906.00091, 2019","venue":null,"work_id":null,"year":1906},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:58.999330Z"},"links":{"cited_paper":"/paper/1906.00091","citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:a0827fedf923efeaddf4db240f9ce5cbbc570e72a0ff46afbba4faa2cd5e2bba","observation_id":"c4722516-ccee-4d85-9aad-a6c14b36983a","resolution":{"observed_at":"2026-08-06T23:28:58.999330Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:10.764755Z","title":"Language models are un- supervised multitask learners","venue":null,"work_id":"db39977a-801f-4d1a-befc-78f6c9ecfcf3","year":2019},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:59.137305Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:cc68613534ed10a15794091d0eba9520e3a0df537437c0826cb0f0d46fb153d0","observation_id":"9b2a2aa5-9676-4517-a4e8-bbac1b4d3d17","resolution":{"observed_at":"2026-08-06T23:29:10.884223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:10.515120Z","title":"Cheetah: Optimizing and accelerating homo- morphic encryption for private inference","venue":null,"work_id":"139325bb-edb4-4187-9d9c-32d0258b3e98","year":2021},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:59.314750Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:6c48dacf07a933c803e4070ce0456f3edb150f0a630ae66f56ea1522b9c4f521","observation_id":"d4463b2c-f724-4711-bc58-539fbc32ee6b","resolution":{"observed_at":"2026-08-06T23:29:10.597494Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:28:59.472454Z","title":"Sadegh Riazi, Kim Laine, Blake Pelton, and Wei Dai","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:59.472454Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:45ebfb15d3cc2d110bbae05c47a82b7114347e2525b679e7ecaab95a3eafb942","observation_id":"53517a1a-b478-4910-a692-0682852d9615","resolution":{"observed_at":"2026-08-06T23:28:59.472454Z","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":"2026-08-06T23:28:59.569249Z","title":"Craterlake: A hardware accelerator for efficient un- bounded computation on encrypted data","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:59.569249Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:e6ed1a9ae9b0806e7b69be6559776b1e38376500897f887425379176249458d8","observation_id":"ab4b096b-b09f-4b58-b242-6a8b44319bf9","resolution":{"observed_at":"2026-08-06T23:28:59.569249Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:10.222197Z","title":"Compositional embeddings using complementary partitions for memory-efficient recom- mendation systems","venue":null,"work_id":"b0f2fcd7-a167-46ca-a11d-d3a02b861cb6","year":2020},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:59.774777Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:2dacbffd625fe9106d18d712e62ed64db69136dee872b1dccc2c7ce8c2fa8111","observation_id":"fe5fae30-f61a-4613-9417-84eacdf8cff3","resolution":{"observed_at":"2026-08-06T23:29:10.334557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:09.859954Z","title":"Compressing word embeddings via deep compositional code learn- ing","venue":null,"work_id":"a371655e-4627-4f41-a09e-ac6e04900e71","year":2018},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:59.954650Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:949ad28107577034492a8bb9a74016249eaef401e7ef47a20aeed31270cb0d27","observation_id":"858040b9-453a-4d35-b89e-98a19ecc8152","resolution":{"observed_at":"2026-08-06T23:29:09.999906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:09.546351Z","title":"Delphi: A cryptographic inference service for neural networks","venue":null,"work_id":"42b4886d-85fa-49d8-b914-91134d40f79a","year":2019},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:00.229514Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:5a0e1365e7116c3174c267f1e5d18553e0a71a39e4ded897b3bdcdf944671f4f","observation_id":"26d041c1-6bbf-4a5c-a755-a061acfcd27a","resolution":{"observed_at":"2026-08-06T23:29:09.677324Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:09.204753Z","title":"Clustering the sketch: dynamic compression for embedding tables.Advances in Neural Information Processing Systems, 36:72155– 72180, 2023","venue":null,"work_id":"74ab2c28-7d48-41f9-b198-c2c634e0169c","year":2023},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:00.424827Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:2d961047a77fe362e8b4eda18f30640e006a14263bcbed1a20a339e5bcc5baf5","observation_id":"137b20f9-6550-4829-8a9d-6312b233edc4","resolution":{"observed_at":"2026-08-06T23:29:09.374755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1904.12840","last_updated":"2019-04-29T17:42:25Z","snapshot_observed_at":"2026-07-06T07:49:17.886466Z","submitted_at":"2019-04-29T17:42:25Z","title":"SEALion: a Framework for Neural Network Inference on Encrypted Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.12840","snapshot_observed_at":"2026-08-06T23:29:00.678622Z","title":"Sealion: A framework for neural network inference on encrypted data.arXiv preprint arXiv:1904.12840, 2019","venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:00.678622Z"},"links":{"cited_paper":"/paper/1904.12840","citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:815b41153f5c79d7b83668a469ad83e552d62a56ca4acce93adaf9ee2174f157","observation_id":"b43fd4ec-474a-4613-a17a-3d58b23473e3","resolution":{"observed_at":"2026-08-06T23:29:00.678622Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:08.952599Z","title":"Heco: fully homomorphic encryption com- piler","venue":null,"work_id":"b3d7100c-d6ea-4a11-8080-a47cef2a6555","year":2023},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:00.814751Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:aaf47dbb1a2b6fccc9c13826212ca27f3a28349f0381175008738a17cb370772","observation_id":"7dfd9da6-cff3-4545-9aa9-ea9ac27be986","resolution":{"observed_at":"2026-08-06T23:29:09.065078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:08.645770Z","title":"Feature hashing for large scale multitask learning","venue":null,"work_id":"507789d5-a2d0-416d-88ef-aa42b2b5afcd","year":2009},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:00.974627Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:0a2549075a88280421c84f8ccb24e7dbdbd8694fbb60368771c4f340ace62213","observation_id":"f71bf60a-dc75-41e7-8f57-e8e48b4723f3","resolution":{"observed_at":"2026-08-06T23:29:08.835858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:08.325881Z","title":"Arion: Attention- optimized transformer inference on encrypted data","venue":null,"work_id":"8a6edc55-d30a-450e-942e-e1b2a9115298","year":2025},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:01.135797Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:50cc7200b511d51a4474f6dd38d374c9e3001838b176c112e635f6a2c083d50d","observation_id":"f4f484c8-48db-425a-ba0b-0fdc7e445315","resolution":{"observed_at":"2026-08-06T23:29:08.512160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:01.254425Z","title":"Poseidon: Prac- tical homomorphic encryption accelerator","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:01.254425Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:88ac3579956b806f692ef1f2ef9acd82afd0d37e901fa7c47dea52e7863113d7","observation_id":"a6fc6916-2b44-468a-a384-dcc7d6ab0efb","resolution":{"observed_at":"2026-08-06T23:29:01.254425Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:07.726023Z","title":"Tt-rec: Tensor train compression for deep learn- ing recommendation models.Proceedings of Machine Learning and Systems, 3:448–462, 2021","venue":null,"work_id":"55794e0e-467e-4778-8afc-4d7da8fffa4b","year":2021},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:01.322007Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:a202fda5703356fcd06b78e9507b7cd8d128662cc52a1c6f9506461d460ddb04","observation_id":"789ae3a4-ce1e-4262-8666-3e0f02f51c41","resolution":{"observed_at":"2026-08-06T23:29:07.954762Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:07.435467Z","title":"Privacy-preserving embedding via look-up ta- ble evaluation with fully homomorphic encryption","venue":null,"work_id":"a003cc1d-2c3b-4f4c-8a03-8fcb55a0e583","year":2024},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:01.414308Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:eb6921151ffd81dafc06a2fd091033e38415fba4d4f2d9274d04e42acdf7fb37","observation_id":"9fa2ae19-a887-4155-9938-0e232a388974","resolution":{"observed_at":"2026-08-06T23:29:07.558345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:07.119575Z","title":"Concrete ML: a privacy-preserving machine learning library using fully homomorphic encryption for data scientists, 2022","venue":null,"work_id":"e517b1d3-2b1f-4b30-8fd8-0e85961ecf8f","year":2022},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:01.494806Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:7e478214bf9d39605324c4aa6f315388c373d1681abcaf649c0707e59abe0127","observation_id":"25936485-6426-455b-aad5-0858e6ace40c","resolution":{"observed_at":"2026-08-06T23:29:07.224751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:06.794750Z","title":"Secure transformer infer- ence made non-interactive.Cryptology ePrint Archive, 2024","venue":null,"work_id":"d5fc1821-12b6-47d1-bc50-1dc8b519b2e5","year":2024},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:01.614757Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:46b2425481935aaf2e6077008d5948cda584cb81b9ff79ec85756c74f821b50e","observation_id":"b86f9229-43ca-4d37-8cb3-b034dd05088a","resolution":{"observed_at":"2026-08-06T23:29:06.893086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:29:06.414838Z","title":"MOAI: Module-optimizing architec- ture for non-interactive secure transformer inference","venue":null,"work_id":"000ee1de-a7b0-4844-98f4-b4042359918d","year":2026},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:01.778892Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:4ee503ebf1059df98ccbbeff4b3198f5883dcef88746d71cc05d7271de16f1f1","observation_id":"d5eec759-c3f0-4318-8987-95a2d425a161","resolution":{"observed_at":"2026-08-06T23:29:06.594918Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2410.20046","last_updated":"2024-10-26T02:33:52Z","snapshot_observed_at":"2026-08-10T08:33:27.225125Z","submitted_at":"2024-10-26T02:33:52Z","title":"DQRM: Deep Quantized Recommendation Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.20046","snapshot_observed_at":"2026-08-06T23:29:02.024766Z","title":"Dqrm: Deep quantized recommendation models.arXiv preprint arXiv:2410.20046, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-06T23:29:02.024766Z"},"links":{"cited_paper":"/paper/2410.20046","citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:ca3df4e6b8b8026f11908b67d1911489267e1f22863b95b862f4441ce2eb8bfa","observation_id":"66d67b77-085a-4970-976d-03dcc033847c","resolution":{"observed_at":"2026-08-06T23:29:02.024766Z","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":"2026-08-06T23:28:57.069195Z","title":"3527415,doi:10.1145/3470496.3527415","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:57.069195Z"},"links":{"citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:cf279f0fbcb34363acb922f4a099820dc720b35d4d4a6564b444ffd0e6f14c21","observation_id":"a5cb7f4a-5432-4da9-955e-d4518d9fed1d","resolution":{"observed_at":"2026-08-06T23:28:57.069195Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.16241","last_updated":"2024-05-25T13:58:45Z","snapshot_observed_at":"2026-08-07T23:09:59.886683Z","submitted_at":"2024-05-25T13:58:45Z","title":"FastQuery: Communication-efficient Embedding Table Query for Private LLM Inference","version":1},"cited_work":{"arxiv_id":"2405.16241","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.16241","snapshot_observed_at":"2026-08-06T23:29:03.594800Z","title":"FastQuery: Communication-efficient Embedding Table Query for Private LLM Inference","venue":"cs.CR","work_id":"70953b09-1f55-461f-8961-9ae46e33947e","year":2024},"citing_paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption","version":4},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T23:28:58.282382Z"},"links":{"cited_paper":"/paper/2405.16241","citing_paper":"/paper/2506.18150"},"observation_digest":"sha256:e5b460352cb80e5089954bc7165094150ed3e9dd7145fdeadc26f79a3369084d","observation_id":"2c72c154-679e-4306-a808-b1467e99f57c","resolution":{"observed_at":"2026-08-06T23:29:03.834822Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.18150","last_updated":"2026-07-18T20:18:57Z","latest_version":4,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-10T04:04:57.521177Z","submitted_at":"2025-06-22T19:40:04Z","title":"HE-LRM: Encrypted Deep Learning Recommendation Models using Fully Homomorphic Encryption"},"reference_resolution":{"displayed":74,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":22,"verified_exact":3,"verified_fuzzy":48},"total_outbound_references":74},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 74 of 74 outbound references and 1 inbound Pith citation observation for arXiv:2506.18150."}