{"as_of":"2026-08-12T22:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:309fb163725a9a0f4ebb2e734ce20580d3910572418a63f94207cc4822a5282d","coverage":[{"denominator":26,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":26,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T19:46:46.603903Z","state":"measured"},{"denominator":27,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":27,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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":"2026-05-07T02:12:30.086152Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-12T10:46:31.726131Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"cited_work":{"arxiv_id":"2509.09091","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2509.09091","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards confidential and efficient LLM inference with dual privacy protection","venue":null,"work_id":"28372b3f-21d9-4c48-90f1-4f6c1fd406ec","year":2025},"citing_paper":{"arxiv_id":"2605.03213","last_updated":"2026-05-07T16:46:43Z","snapshot_observed_at":"2026-08-12T21:30:34.125985Z","submitted_at":"2026-05-04T23:09:16Z","title":"When Agents Handle Secrets: A Survey of Confidential Computing for Agentic AI","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-07T02:12:30.086152Z"},"links":{"cited_paper":"/paper/2509.09091","citing_paper":"/paper/2605.03213"},"observation_digest":"sha256:2ba527f0f46439377298e417d528548e0f3c802bd98292b73292651d06b656e3","observation_id":"5508ce76-fc8c-4ed8-9438-ce6cce064dd3","resolution":{"observed_at":"2026-05-12T10:46:31.729260Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2509.09091/citation-record","integrity":"/paper/2509.09091/integrity","json":"/paper/2509.09091/citation-record.json","paper":"/paper/2509.09091"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T19:46:44.713106Z","title":"In: Proc","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:44.713106Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:11fcf33b4ecf2bf5fd2aa73b53b628ec196a75ad59b915f25655626615af947f","observation_id":"8eaaa502-d9af-46cb-8f9c-f943d0f737cc","resolution":{"observed_at":"2026-08-04T19:46:44.713106Z","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":"2026-08-04T19:46:44.771090Z","title":"In: Proc","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:44.771090Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:dc4a296a97cf47a642eb9b7bac2c4befc6f90c318134dcb78d59a3ec4d92b617","observation_id":"021a1044-240d-41c7-a903-e227c86105c6","resolution":{"observed_at":"2026-08-04T19:46:44.771090Z","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":"2026-08-04T19:46:44.828071Z","title":"In: Proc","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:44.828071Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:e6044faad73e457ee5b73d528212aef27aa69f83b1efb157b8ec0f1362653caa","observation_id":"7b423dda-c656-4bc8-aa1b-cf09d998ef07","resolution":{"observed_at":"2026-08-04T19:46:44.828071Z","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":"2026-08-04T19:46:44.852751Z","title":"In: Proc","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:44.852751Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:5818b8ef43407ce265971e9458decd74801a3f96785f9f0f5939e5591196f66d","observation_id":"6dc035b7-4891-4204-9e47-61b3f0aba054","resolution":{"observed_at":"2026-08-04T19:46:44.852751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-10T16:40:37.411115Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-04T19:46:44.925784Z","title":"arXiv preprint arXiv:2407.21783 (2024) H","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:44.925784Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:c6a1f0fad1f2e20c18b6109cf84b95b4bff6c9bbacbe391dfee9ce5e6d4a7646","observation_id":"f85471d9-8ed5-4946-9957-3d2182f44231","resolution":{"observed_at":"2026-08-04T19:46:44.925784Z","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":"2026-08-04T19:46:45.026675Z","title":"IEEE Access9, 168656– 168677 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:45.026675Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:f0cf1941437a81cc9d70203efe3a56223ed7b0a90afcb70b3de04ea10cd2af01","observation_id":"e0344e59-772d-4335-a3f1-f0f6dd700266","resolution":{"observed_at":"2026-08-04T19:46:45.026675Z","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":"2026-08-04T19:46:45.191272Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:45.191272Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:b2ff057cf4751a24e84346c89666d4fd6cd0bfccc7dcbc1f3723e63c8fba3cea","observation_id":"a5fa0fbc-0880-4826-9ad7-92e2ac023003","resolution":{"observed_at":"2026-08-04T19:46:45.191272Z","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":"2026-08-04T19:46:45.302481Z","title":"In: Proc","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:45.302481Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:89e4d1c71faceb3a450088a415259b723a35c7dfe5ec25dc586a4a46c3e9d09c","observation_id":"1768843b-c2e7-4bd6-996b-8c69f697366a","resolution":{"observed_at":"2026-08-04T19:46:45.302481Z","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":"2026-08-04T19:46:45.426100Z","title":"In: Proc","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:45.426100Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:dd6138a4e9af066352dbdbee7488c61454dd520cc7da27133cebf40d328c195d","observation_id":"6fda5830-3eac-4565-b19f-6e2158611243","resolution":{"observed_at":"2026-08-04T19:46:45.426100Z","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":"2026-08-04T19:46:45.578640Z","title":"In: Proc","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:45.578640Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:407a35adbb80222fa9a1e61c6308ca879644c021dc4f68d04cbf71d0020533eb","observation_id":"556a5b27-cd14-4423-9690-f27f490b4c6f","resolution":{"observed_at":"2026-08-04T19:46:45.578640Z","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":"2026-08-04T19:46:45.694672Z","title":"In: Proc","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:45.694672Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:377b4b47ac2ce820c2f6b0384c45d6cf47c6aa947ff7a17cdc63db2d505d6af1","observation_id":"d840fb56-3372-48dc-b867-9af52fb1806b","resolution":{"observed_at":"2026-08-04T19:46:45.694672Z","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":"2026-08-04T19:46:45.814458Z","title":"In: Proc","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:45.814458Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:fc18b21cec7df5f71de4456c8173224d5ad8848b4afa1cf1b0667b2273b22bd5","observation_id":"2861bc2e-6d57-47c9-9e7f-5d36ca28a1a0","resolution":{"observed_at":"2026-08-04T19:46:45.814458Z","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":"2026-08-04T19:46:45.910618Z","title":"In: Proc","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:45.910618Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:4d646089b1f7d44f54a5d87203ffa0b9bdcd24ddabef2290b1b9671942011cc2","observation_id":"7d4eed8b-0b14-4c6c-b78f-a7aa2eabae61","resolution":{"observed_at":"2026-08-04T19:46:45.910618Z","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":"2026-08-04T19:46:45.991489Z","title":"In: Proc","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:45.991489Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:e9d0e6cb5936efe8f5ad91fabd720228f19f741ff4d9a557961f6b71c9f65621","observation_id":"b03e8f5e-fd68-4e71-9ee9-858062d565e3","resolution":{"observed_at":"2026-08-04T19:46:45.991489Z","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":"2026-08-04T19:46:46.057789Z","title":"In: Proc","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:46.057789Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:b0a3cbd09f1d414148560b048e44ff5614b168c05044f2a56cc81a527b046ead","observation_id":"dcd38fd5-6130-4607-9613-c019382828b9","resolution":{"observed_at":"2026-08-04T19:46:46.057789Z","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":"2026-08-04T19:46:46.118259Z","title":"In: Proc","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:46.118259Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:ade6604695728296e5227c553d8eb22acb1ea0cfc3298b8729b105c712c37c3d","observation_id":"590a1712-518f-44ec-b2b1-6b6e29ff1954","resolution":{"observed_at":"2026-08-04T19:46:46.118259Z","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":"2026-08-04T19:46:46.192785Z","title":"Nature medicine (8), 1930–1940 (2023)","venue":null,"work_id":null,"year":1930},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:46.192785Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:5cc83ef37e92c2610f6b24f9fbbee7c56b70e3efd1a96a4b5a6c3b77c1dbe3e7","observation_id":"c7842db2-9ae3-465f-83aa-d49f4e1acbd5","resolution":{"observed_at":"2026-08-04T19:46:46.192785Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-04T19:46:46.244674Z","title":"arXiv preprint arXiv:2307.09288 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:46.244674Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:f9dd2b99b1db4c2722d1f48be7232b23902e4bdcb6d6cc2ecd1b8f963517112d","observation_id":"c2798727-9b4c-4805-a803-84465f86a7e8","resolution":{"observed_at":"2026-08-04T19:46:46.244674Z","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":"2026-08-04T19:46:46.294240Z","title":"In: Proc","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:46.294240Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:70467b9199a1cb16ad457f41415802e95b7dbef0ebe71fb91d2f83fced983bc9","observation_id":"4ffdfed4-d6e3-4858-8377-ea834e9d1fed","resolution":{"observed_at":"2026-08-04T19:46:46.294240Z","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":"2026-08-04T19:46:46.358564Z","title":"In: Proc","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:46.358564Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:1208e866aee503f20c299562e3784547a12a2edf67245a450951c5442f9f281c","observation_id":"4b7edada-45dd-49b4-8688-5ad9dbdbc1a7","resolution":{"observed_at":"2026-08-04T19:46:46.358564Z","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":"2026-08-04T19:46:46.384248Z","title":"In: Proc","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:46.384248Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:06160bdc52d21bd2601e96bdcba12fdd592158f091b35ba05fed3405bb4cfb55","observation_id":"48ba394e-5dcb-4a8b-9fd2-f4d3197fde9e","resolution":{"observed_at":"2026-08-04T19:46:46.384248Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.11531","last_updated":"2024-01-21T15:57:04Z","snapshot_observed_at":"2026-08-10T11:27:41.406523Z","submitted_at":"2024-01-21T15:57:04Z","title":"Tempo: Confidentiality Preservation in Cloud-Based Neural Network Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.11531","snapshot_observed_at":"2026-08-04T19:46:46.435329Z","title":"arXiv preprint arXiv:2401.11531 (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:46.435329Z"},"links":{"cited_paper":"/paper/2401.11531","citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:4a916477d868f47381aff68a4c7d9decd68c16bd974705cb9e186479fa2d762b","observation_id":"9f1625d1-e926-400b-8ab3-a9bee3407804","resolution":{"observed_at":"2026-08-04T19:46:46.435329Z","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":"2026-08-04T19:46:46.488391Z","title":"In: Proc","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:46.488391Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:af14bec9afdb43aba4d632b6334b744d1a4ba1f160f998bee55df3d803f226f3","observation_id":"0c685fb3-82e5-4b95-bafe-d1671203b985","resolution":{"observed_at":"2026-08-04T19:46:46.488391Z","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":"2026-08-04T19:46:46.510358Z","title":"In: Proc","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:46.510358Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:394639b69d563bbc6558d723271d7d12b43b8f8b3b00e416531e95d07d2c6eae","observation_id":"756317b9-0ae3-440a-b6d4-3b23dde077e9","resolution":{"observed_at":"2026-08-04T19:46:46.510358Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2311.07911","last_updated":"2023-11-14T05:13:55Z","snapshot_observed_at":"2026-07-06T16:47:08.877195Z","submitted_at":"2023-11-14T05:13:55Z","title":"Instruction-Following Evaluation for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.07911","snapshot_observed_at":"2026-08-04T19:46:46.554488Z","title":"arXiv preprint arXiv:2311.07911 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:46.554488Z"},"links":{"cited_paper":"/paper/2311.07911","citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:4171b183b2b42f8765f3c9c9deb11cf2f22818a633ae8b78e4fb0ef94711335f","observation_id":"c75b3ec7-7f83-45d9-b843-233543ef9ade","resolution":{"observed_at":"2026-08-04T19:46:46.554488Z","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":"2026-08-04T19:46:46.603903Z","title":"In: Proc","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T19:46:46.603903Z"},"links":{"citing_paper":"/paper/2509.09091"},"observation_digest":"sha256:bdbf5fa52c313e25c3f09976fbba0bb0be27c108d5ab4d8f9d16dd7e53cb47ac","observation_id":"b5387db9-04cf-49ee-be3b-b78bb24d6e62","resolution":{"observed_at":"2026-08-04T19:46:46.603903Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2509.09091","last_updated":"2025-09-11T01:54:13Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-04T19:46:44.170070Z","submitted_at":"2025-09-11T01:54:13Z","title":"Towards Confidential and Efficient LLM Inference with Dual Privacy Protection"},"reference_resolution":{"displayed":26,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":26,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":26},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 26 of 26 outbound references and 1 inbound Pith citation observation for arXiv:2509.09091."}