{"as_of":"2026-08-10T06:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e74acf71bcc4e4d7bae679534646e363d0a89c392fade7e45fdd1756390a8d30","coverage":[{"denominator":44,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":44,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T17:36:28.874435Z","state":"measured"},{"denominator":44,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":44,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2502.00847/citation-record","integrity":"/paper/2502.00847/integrity","json":"/paper/2502.00847/citation-record.json","paper":"/paper/2502.00847"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:36:29.525116Z","title":null,"venue":null,"work_id":"77fb5715-079a-43b4-82a3-bfd634abd6e9","year":2023},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.679177Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:99664c226de3b0a8634680dc34a2bd96f6bfebb2638cb9ef445e1997b94a641b","observation_id":"a4452886-140e-49a5-96a9-4edc444cf0d9","resolution":{"observed_at":"2026-08-09T17:36:29.529710Z","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":"2026-08-09T17:36:29.510329Z","title":"Bossuat, C","venue":null,"work_id":"f783a9ba-993e-4775-a0c5-214d999225cf","year":2021},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.684447Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:6bae0e7ce85958926b3edc842ce7842a1deeba3a3df2dc62e83653c8dafc268d","observation_id":"53740680-be2e-4c0f-bf12-eaa2ffd62f86","resolution":{"observed_at":"2026-08-09T17:36:29.514914Z","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":"2026-08-09T17:36:28.689105Z","title":"Brown, B","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.689105Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:78674bdb37541413f16d0de1796c811bd1f685db110551659d9899a9af223f2d","observation_id":"bdb947a7-df16-410c-802d-f40857c2d125","resolution":{"observed_at":"2026-08-09T17:36:28.689105Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-08-08T11:58:24.516369Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-09T17:36:28.693845Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.693845Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:2891c5b8b4e17263e700e7e608651261096f5ce0c3a1b7023afd1bdd4915f12e","observation_id":"99bf4785-7d9b-4aa7-a275-f9a5a418b7ce","resolution":{"observed_at":"2026-08-09T17:36:28.693845Z","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":"2026-08-09T17:36:29.486100Z","title":null,"venue":null,"work_id":"f0640a4d-9b1b-4d1b-9f89-777231db598b","year":2018},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.698969Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:04714695a948e1a826366707eb75f6453a24c4c617ad96b9590762837a663690","observation_id":"ef9ae319-ea33-4282-9dba-d2a79c6a9c8b","resolution":{"observed_at":"2026-08-09T17:36:29.490406Z","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":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-07T01:45:38.840969Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-08-09T17:36:28.703831Z","title":"Cobbe, V","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.703831Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:4a1c498df3afb67d2a2d94675072871ac060cfbfa3b48f6994bfb6750f58237f","observation_id":"1fd93c20-c814-45fc-9a17-7e04bc02bf9c","resolution":{"observed_at":"2026-08-09T17:36:28.703831Z","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":"2026-08-09T17:36:29.471890Z","title":"Dvornik, C","venue":null,"work_id":"0b7d5f4d-9dbe-4c01-a2b4-5f9907aaa004","year":2019},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.709338Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:3f61fc8f4d7d2cced4bcb2b78c190c5b6b2ee6330ef9ccb1444dceb31674f3fd","observation_id":"0883aa69-36f1-42be-b714-f3b473a7e21a","resolution":{"observed_at":"2026-08-09T17:36:29.476474Z","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":"2026-08-09T17:36:28.713675Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.713675Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:7bf307eac8ab5f757dc04b3743019493f6c3646d1e4b6b7611045fcecf76cfef","observation_id":"e732e31b-3bc2-42d2-88d8-6c25b44fea03","resolution":{"observed_at":"2026-08-09T17:36:28.713675Z","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":"2026-08-09T17:36:29.457823Z","title":null,"venue":null,"work_id":"a3603f30-32ae-41d6-ab56-71c8a6238988","year":2009},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.718261Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:e43685906778f665a5a534abe4ac105b96d7839e2d3b0f6be4d04bde74a9803d","observation_id":"f0941c3d-3415-4738-adf9-f949f50b57f1","resolution":{"observed_at":"2026-08-09T17:36:29.462373Z","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":"2026-08-09T17:36:29.443527Z","title":"Han and D","venue":null,"work_id":"314de56d-60bf-47f4-8a5f-41f4aab70620","year":2020},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.722342Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:fb4d9064072d752b2bdaeb806041c0917d5d4d6ce620492f7f15e71c6383f2b7","observation_id":"fc865d16-8c91-419b-a02a-9686c277e36e","resolution":{"observed_at":"2026-08-09T17:36:29.448123Z","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":"2026-08-09T17:36:29.429176Z","title":null,"venue":null,"work_id":"93921563-6c52-48c1-ab64-3439781995b2","year":2022},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.726588Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:7c8c9360cef3c8ca04353623d55be431812b06a77db3622daee71ed42475ff92","observation_id":"1f22e3f3-e063-404c-97fb-8976278039b7","resolution":{"observed_at":"2026-08-09T17:36:29.433854Z","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":"2026-08-09T17:36:29.415414Z","title":"Jovanovic, M","venue":null,"work_id":"dbd76786-64e5-4187-b1b2-afd49d22cfed","year":2022},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.731161Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:5035cfa9e081883920f2c1a5c171b9fe4091d4b1bd7d7158c47f179f287ee18a","observation_id":"1494ed4c-0c00-4467-ba16-7c9fedbaa64a","resolution":{"observed_at":"2026-08-09T17:36:29.419918Z","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":"2026-08-09T17:36:29.401364Z","title":"Juvekar, V","venue":null,"work_id":"c7aca7ce-aa63-4e73-85c9-9a29c2489c7d","year":2018},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.735407Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:679fbc004d01c7077fbbae0320fb5b4f00227b602240f641e7c176fe53fafc48","observation_id":"15b73145-ef8d-4065-b3b6-dd3f42753a30","resolution":{"observed_at":"2026-08-09T17:36:29.405878Z","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":"2026-08-09T17:36:29.387545Z","title":null,"venue":null,"work_id":"6c77dd5c-6798-45a1-b46c-e3eb478f793f","year":2019},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.739724Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:9ddcf3a7c7cf92e62da7d34d71a9c8f00a9c1b09e72af1257eddff98bc86a676","observation_id":"174bf2c3-0cf0-44ce-96b7-a73d9124e4f5","resolution":{"observed_at":"2026-08-09T17:36:29.391957Z","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":{"arxiv_id":"1909.11942","last_updated":"2020-02-09T03:00:18Z","snapshot_observed_at":"2026-07-06T08:24:44.631342Z","submitted_at":"2019-09-26T07:06:13Z","title":"ALBERT: A Lite BERT for Self-supervised Learning of Language Representations","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.11942","snapshot_observed_at":"2026-08-09T17:36:28.743952Z","title":null,"venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.743952Z"},"links":{"cited_paper":"/paper/1909.11942","citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:947ee53f04e428e7f7db1e42328a99bf96a433ef5735fd5f80ab81ff99ce9068","observation_id":"300c68e0-2d20-4b53-954d-674c91b57906","resolution":{"observed_at":"2026-08-09T17:36:28.743952Z","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":"2026-08-09T17:36:29.373286Z","title":"Lee, J.-W","venue":null,"work_id":"314f67c8-fd9a-4f22-9030-7b61735a6ab5","year":2022},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.748925Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:5fe43aa5a064c8efb15413ab111fe41efdc3b968dcd94f78de332651b30c6c7b","observation_id":"d6ef9009-ec94-4fa6-83eb-5e47f23e760e","resolution":{"observed_at":"2026-08-09T17:36:29.378248Z","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":"2026-08-09T17:36:28.753499Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.753499Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:a550d01a7ede51c3a9696b737af3e256f13df901e7afe55a5828a2aa5ff264a3","observation_id":"2e7942eb-c759-4bd8-9422-09e54d0b08a1","resolution":{"observed_at":"2026-08-09T17:36:28.753499Z","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":"2026-08-09T17:36:29.343244Z","title":"Li, Y .-L","venue":null,"work_id":"1a740882-a7b3-46dd-9b94-4b237e7516a9","year":2023},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.762300Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:0eda2fff7dcb5b805abd3df2ddd7fbab0c8f688180ff82e2e724889e0c855c98","observation_id":"477139aa-1db3-4502-a1ee-554fdd7afeb5","resolution":{"observed_at":"2026-08-09T17:36:29.348810Z","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":"2026-08-09T17:36:29.328337Z","title":null,"venue":null,"work_id":"a8f7a979-fb94-4caf-93ad-dab299974160","year":2023},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.767261Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:cedac3f609f04b245c38a86781e49c3ca7e79e5122b64bd5c4203b2b35be67bd","observation_id":"c34bb3e2-374b-4ca2-ab4c-fcf195a38096","resolution":{"observed_at":"2026-08-09T17:36:29.333662Z","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":"2026-08-09T17:36:29.312225Z","title":"Italy orders chatgpt blocked citing data protection concerns","venue":null,"work_id":"3c964d44-0385-47c1-a9d1-ee5f764e4d07","year":2023},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.771815Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:0cdeef6aa9662b9d732542944fa68b0055e84f69179abf387529c36008632df9","observation_id":"216889bd-4398-4e9a-988e-84b30f00a325","resolution":{"observed_at":"2026-08-09T17:36:29.318069Z","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":"2026-08-09T17:36:29.281996Z","title":null,"venue":null,"work_id":"b289417c-e6a3-4442-9a87-7c1b586cc72a","year":2024},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.781116Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:7dba3990f4db7b07d540317bc7b2cde3ea3c2328dc939f8d56bd1e6e76e36fc7","observation_id":"2134366a-3f52-41cc-b65c-00ff1bf8df72","resolution":{"observed_at":"2026-08-09T17:36:29.286480Z","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":"2026-08-09T17:36:29.266771Z","title":"Radford, J","venue":null,"work_id":"3f940c43-a38d-45b1-bd07-43473bd32ddf","year":2021},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.785546Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:12fa32d97e73f4970b379578d1730c0ea41a078a94ae47545345b8881cb5c401","observation_id":"1ee6af84-b594-4a27-8410-7875afbff194","resolution":{"observed_at":"2026-08-09T17:36:29.271415Z","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":"2026-08-09T17:36:29.251915Z","title":"Raffel, N","venue":null,"work_id":"5df676d1-2d9c-4d36-9dd9-209e503b99c8","year":2020},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.789926Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:72ca56659911dfd73cb62f9a9872362ab790e156567d9e653b295aafd6e19263","observation_id":"77b83b83-55e9-44ff-a7c8-16cbfc747ad2","resolution":{"observed_at":"2026-08-09T17:36:29.256477Z","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":"1608.01413","last_updated":"2016-08-20T11:50:41Z","snapshot_observed_at":"2026-08-09T10:12:36.401845Z","submitted_at":"2016-08-04T01:47:23Z","title":"Solving General Arithmetic Word Problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1608.01413","snapshot_observed_at":"2026-08-09T17:36:28.794174Z","title":"Roy and D","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.794174Z"},"links":{"cited_paper":"/paper/1608.01413","citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:b76ec0b2ba1f40a660862da6ec0f7ff2c8e8422066e554a709c5b90392ee9916","observation_id":"c667471e-484f-4281-8746-d3a47b83bdfb","resolution":{"observed_at":"2026-08-09T17:36:28.794174Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.07676","last_updated":"2021-01-25T10:56:45Z","snapshot_observed_at":"2026-08-07T14:12:26.620672Z","submitted_at":"2020-01-21T17:57:33Z","title":"Exploiting Cloze Questions for Few Shot Text Classification and Natural Language Inference","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.07676","snapshot_observed_at":"2026-08-09T17:36:28.798773Z","title":"Schick and H","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.798773Z"},"links":{"cited_paper":"/paper/2001.07676","citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:42c555f725d254bbbaf155b26f9eaeb9b0a1a262e4ab935902dca42c71b5732b","observation_id":"40badd00-1970-47d0-bb95-e0b4e39d7084","resolution":{"observed_at":"2026-08-09T17:36:28.798773Z","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":"2026-08-09T17:36:28.803691Z","title":"Schick and H","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.803691Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:b5d231b9074f944b975ebbdcdaa48ad575637b84e8566d0156f4072d396d99cb","observation_id":"f77d6aec-58b9-4a3e-b4fd-03ca24506a16","resolution":{"observed_at":"2026-08-09T17:36:28.803691Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.13641","last_updated":"2020-10-26T14:56:22Z","snapshot_observed_at":"2026-07-06T10:08:36.623926Z","submitted_at":"2020-10-26T14:56:22Z","title":"Automatically Identifying Words That Can Serve as Labels for Few-Shot Text Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.13641","snapshot_observed_at":"2026-08-09T17:36:28.808125Z","title":"Schick, H","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.808125Z"},"links":{"cited_paper":"/paper/2010.13641","citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:c07b7bae12c3740446406cc92e9388a66c2a9cc22ca6d364e022d8bc3dd55301","observation_id":"46a0f98e-6ca6-4e0a-b595-d6ec4acad69e","resolution":{"observed_at":"2026-08-09T17:36:28.808125Z","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":"2026-08-09T17:36:29.236314Z","title":null,"venue":null,"work_id":"c592517f-573a-412c-b471-10fa56e4ec99","year":2007},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.812861Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:a8e7ba15e23588352f4301f30bc9d1461b92b474d81943f38205075cfd2c03e9","observation_id":"993939fb-9bb6-4b16-b1cb-7da8d7aaad94","resolution":{"observed_at":"2026-08-09T17:36:29.241155Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:36:28.816969Z","title":"Shokri, M","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.816969Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:28dc3e11b07f9fc2614985be95e4df09991911dfcc482386bad07c01ec7d9a06","observation_id":"c252a12d-c5ca-4621-bd13-2ba792030476","resolution":{"observed_at":"2026-08-09T17:36:28.816969Z","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":"2026-08-09T17:36:29.210529Z","title":null,"venue":null,"work_id":"b1902d43-2fd3-445f-8804-d66643d359a0","year":2019},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.821309Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:e81e101051f5ca3cdd9c7285b9d42c23f4fac88adeb733fba45666db28aef1f2","observation_id":"0412b3e5-fb4b-42b8-979c-3a519907478d","resolution":{"observed_at":"2026-08-09T17:36:29.215182Z","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":"2026-08-09T17:36:29.195152Z","title":"Viand, P","venue":null,"work_id":"0f768b6d-77e1-4f57-b31d-130cdcb08cd7","year":2023},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.825639Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:e6efe3d290018fd05209de0b3688dded866e93aba8d3e33bc09c7d9915419de5","observation_id":"fffdd6b6-3665-41e4-a344-e838c0b7ffab","resolution":{"observed_at":"2026-08-09T17:36:29.200170Z","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":"2111.02840","last_updated":"2022-01-10T06:05:16Z","snapshot_observed_at":"2026-07-06T12:05:25.336577Z","submitted_at":"2021-11-04T12:59:55Z","title":"Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.02840","snapshot_observed_at":"2026-08-09T17:36:28.830087Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.830087Z"},"links":{"cited_paper":"/paper/2111.02840","citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:247684856c1b9dcfbd36d36eb6a341c5ed000441c6daabcadc07d768cf68bc2a","observation_id":"02a5b6f4-3520-42f2-b258-e7a0263ce9b5","resolution":{"observed_at":"2026-08-09T17:36:28.830087Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.17644","last_updated":"2025-05-26T16:16:43Z","snapshot_observed_at":"2026-08-06T05:24:39.144385Z","submitted_at":"2024-01-31T07:52:48Z","title":"BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.17644","snapshot_observed_at":"2026-08-09T17:36:28.834585Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.834585Z"},"links":{"cited_paper":"/paper/2401.17644","citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:3e9d0e615ab2c37d01ef799c3fc71fb72f03da2691b653a9b7f3a565cc7566c3","observation_id":"71049746-53cc-4c9a-9454-e5f0143eed05","resolution":{"observed_at":"2026-08-09T17:36:28.834585Z","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":"2026-08-09T17:36:29.180565Z","title":null,"venue":null,"work_id":"3140aad4-ab5b-4ced-805c-42754f38cf34","year":2023},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.839489Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:3483022843b3f4e11e920c77547520f5305c0dee67aade6383bf632182660f57","observation_id":"fe8758a1-0736-4869-97e1-9bc02b59bedd","resolution":{"observed_at":"2026-08-09T17:36:29.185070Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:36:28.843538Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.843538Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:22c6b5af6445bcc2e0644c88278ceb124513400d9d95e55bef39ecacb31dd351","observation_id":"b36e1340-48cf-43e5-8c2d-fd43ea13c026","resolution":{"observed_at":"2026-08-09T17:36:28.843538Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.02232","last_updated":"2019-05-04T02:44:35Z","snapshot_observed_at":"2026-07-06T07:43:43.696691Z","submitted_at":"2019-04-03T20:29:10Z","title":"BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.02232","snapshot_observed_at":"2026-08-09T17:36:28.847529Z","title":null,"venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.847529Z"},"links":{"cited_paper":"/paper/1904.02232","citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:5b8dd265ec60a30619f1d7ff9d0f96a5fd8580b10dfcc4ab56f7a420a071a7f5","observation_id":"f368d523-b78a-4755-8edb-57f57b8d2c2e","resolution":{"observed_at":"2026-08-09T17:36:28.847529Z","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":"2026-08-09T17:36:29.153582Z","title":null,"venue":null,"work_id":"a177252e-e828-42f2-a570-919e8c3f6c54","year":2022},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.851932Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:4783961fe9a619495410994f0c86d69a61e321ef43422e19b3069f5f79a06c09","observation_id":"0de5a819-4a27-4135-a2f6-9a4eede85269","resolution":{"observed_at":"2026-08-09T17:36:29.158447Z","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":{"arxiv_id":"1902.01718","last_updated":"2019-09-18T01:31:39Z","snapshot_observed_at":"2026-08-07T23:11:30.567142Z","submitted_at":"2019-02-05T14:50:48Z","title":"End-to-End Open-Domain Question Answering with BERTserini","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1902.01718","snapshot_observed_at":"2026-08-09T17:36:28.856204Z","title":null,"venue":null,"work_id":null,"year":1902},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.856204Z"},"links":{"cited_paper":"/paper/1902.01718","citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:41f0785d90352eb54e1984896335be8e5da87ff119e50ec7e48eeac53fce043c","observation_id":"a3d7da0b-86ae-4976-b4f6-b369a51bca17","resolution":{"observed_at":"2026-08-09T17:36:28.856204Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1903.10972","last_updated":"2019-03-26T15:58:33Z","snapshot_observed_at":"2026-07-06T07:41:46.709954Z","submitted_at":"2019-03-26T15:58:33Z","title":"Simple Applications of BERT for Ad Hoc Document Retrieval","version":1},"cited_work":{"arxiv_id":"1903.10972","doi":null,"metadata_source":"pith","pith_arxiv_id":"1903.10972","snapshot_observed_at":"2026-08-09T17:36:28.941095Z","title":"Simple Applications of BERT for Ad Hoc Document Retrieval","venue":"cs.IR","work_id":"59706d4c-b14c-41e8-9355-16c1d89f1838","year":2019},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.860882Z"},"links":{"cited_paper":"/paper/1903.10972","citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:6e3f835a7a582167225c3f730e5e316379f5534d96394a81ddcea2bec04b3ac2","observation_id":"829d82d7-6cbd-47cf-831b-473c89a3e7df","resolution":{"observed_at":"2026-08-09T17:36:28.948426Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T17:36:29.137957Z","title":null,"venue":null,"work_id":"91f46567-5492-46e4-96a9-5d37614130bf","year":2022},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.865489Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:261dd91c492c7e46222776b341edcb359fad2685c0b8aa8cea0dc706e24fea58","observation_id":"594ac47e-23ee-49d1-a6d5-6961709eccc8","resolution":{"observed_at":"2026-08-09T17:36:29.142899Z","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":"2026-08-09T17:36:29.122332Z","title":null,"venue":null,"work_id":"eaca56f6-fca5-4369-9f36-77a7e0181512","year":2023},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.869723Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:28fe41a3b9ad67c4d539e517c13e15971b9a2812b540bcf9d9c4add2ae980d92","observation_id":"90107148-14de-4c56-9282-86151d0fbead","resolution":{"observed_at":"2026-08-09T17:36:29.127370Z","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":"2026-08-09T17:36:29.107506Z","title":"Zhang, X","venue":null,"work_id":"7ede9649-46d4-48ef-aded-254a0f17d9ce","year":2024},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.874435Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:e39f1b6956a88c6ba423e3631bc938280ded266b4a641a670457cc938d26f3d0","observation_id":"67dc4d1d-27ce-4c64-a9e5-976fb4388b6f","resolution":{"observed_at":"2026-08-09T17:36:29.112216Z","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":"2026-08-09T17:36:29.358766Z","title":null,"venue":null,"work_id":"604fefc7-0a0c-4ad0-b5a8-7dcd168a3c13","year":2023},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":291,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.758126Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:6ebd0e74ea2edae7c6cbaca4c3a1cf06fc70e3965a1a7c7be49440badc75ab1e","observation_id":"a081b288-7812-42a2-b245-4e8b9cafa822","resolution":{"observed_at":"2026-08-09T17:36:29.363305Z","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":"2026-08-09T17:36:29.296281Z","title":null,"venue":null,"work_id":"bc6fb91f-b22d-46d9-9c19-82bc52ac1e9e","year":2023},"citing_paper":{"arxiv_id":"2502.00847","last_updated":"2025-02-02T16:40:21Z","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-09T17:36:28.776568Z"},"links":{"citing_paper":"/paper/2502.00847"},"observation_digest":"sha256:41791826143fb15b4cb28c650c1de0e440bc015d29d48842cb78c3c36dd7a01a","observation_id":"7d82e359-b365-4e5b-89a2-730d65bafe19","resolution":{"observed_at":"2026-08-09T17:36:29.300835Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"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":"2502.00847","last_updated":"2025-02-02T16:40:21Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-09T17:27:59.046601Z","submitted_at":"2025-02-02T16:40:21Z","title":"SecPE: Secure Prompt Ensembling for Private and Robust Large Language Models"},"reference_resolution":{"displayed":44,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":1,"unresolved":30,"verified_exact":1,"verified_fuzzy":12},"total_outbound_references":44},"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 44 of 44 outbound references and 0 inbound Pith citation observations for arXiv:2502.00847."}