{"as_of":"2026-08-10T15:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:1be7538ba7128375efdfd375a87a8a71b648a6d976c200119224fc634bb69b07","coverage":[{"denominator":38,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":38,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T23:51:22.104083Z","state":"measured"},{"denominator":38,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":38,"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/2506.16196/citation-record","integrity":"/paper/2506.16196/integrity","json":"/paper/2506.16196/citation-record.json","paper":"/paper/2506.16196"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:51:26.441281Z","title":"B., Mironov, I., Talwar, K., and Zhang, L","venue":null,"work_id":"2f5373d8-3e1c-413d-8877-a33c83574475","year":2016},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:19.116953Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:d72ec3e9fffdef99beca33e360de78dc5e8c5ebc43b707089cf5e7f3d7f0ef75","observation_id":"76228f22-a172-4a48-bcda-a7a03ed80027","resolution":{"observed_at":"2026-08-06T23:51:26.508142Z","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":"2026-08-06T23:51:26.008501Z","title":"Clark, C., Lee, K., Chang, M.-W., Kwiatkowski, T., Collins, M., and Toutanova, K","venue":null,"work_id":"a37f747c-6904-4b1b-8121-69febf84ef07","year":2023},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:19.512115Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:864d0631129e7c1a84f308382706d438affcfcc0c79f6fa10eb23e7cb8fb46f1","observation_id":"8047108a-9082-45ec-9310-f39634172f65","resolution":{"observed_at":"2026-08-06T23:51:26.128344Z","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":"2026-08-06T23:51:19.671263Z","title":"Cal- ibrating noise to sensitivity in private data analysis","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:19.671263Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:4bb4cdeef12103403d1d72ad9c9faf535f3f7efd6b24abd9534dcc7eb13f42f0","observation_id":"d80fe9a4-796f-48d3-9405-f1fc0dd9edc2","resolution":{"observed_at":"2026-08-06T23:51:19.671263Z","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":"2026-08-06T23:51:23.720544Z","title":"αce αlm αcos Learning Rate Batch Size 5.0 2.0 1.0 0.00025 5 B.2","venue":null,"work_id":"60b64796-022d-45d8-83f5-efe03ce4b992","year":2022},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.791638Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:b810ec4c3d32f7f4d5372552cc804f60cca61dba4543f4011be1e7b8b56e5093","observation_id":"797b0a7c-009d-4578-822e-cf5dedc79aa8","resolution":{"observed_at":"2026-08-06T23:51:23.789173Z","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":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-07-06T04:11:24.157003Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-06T23:51:20.050671Z","title":"Distilling the knowledge in a neural network.arXiv preprint arXiv:1503.02531, 2(7),","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:20.050671Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:493f1af214b087272387fad038022f9c417701227542e4831890006e6e7bf96d","observation_id":"b4596e6e-b17c-4474-896e-3f98ff5a7438","resolution":{"observed_at":"2026-08-06T23:51:20.050671Z","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":"6063.1341","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:51:22.561414Z","title":null,"venue":null,"work_id":"cacc141d-7cbc-477a-927a-b1fc8ce69395","year":null},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.864863Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:70d5d3d5798760f250e9af16ca7c4775e45f51a1eb70afa52b3ce7e45f06742a","observation_id":"6a9eca4c-6b78-4c6e-95fe-46492d23e2c6","resolution":{"observed_at":"2026-08-06T23:51:22.616139Z","resolver_source":"raw_fallback","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":"2104.08691","last_updated":"2021-09-02T17:34:41Z","snapshot_observed_at":"2026-08-06T15:24:34.790850Z","submitted_at":"2021-04-18T03:19:26Z","title":"The Power of Scale for Parameter-Efficient Prompt Tuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08691","snapshot_observed_at":"2026-08-06T23:51:20.287639Z","title":"Dataset posted on Hugging Face","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:20.287639Z"},"links":{"cited_paper":"/paper/2104.08691","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:1d7f5a8528bbe77ae73854135f0d57afe7aa9e9b30a44120dae6672044cb8eb5","observation_id":"ed35300b-a9a1-4ed3-bfef-242a28a64d55","resolution":{"observed_at":"2026-08-06T23:51:20.287639Z","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":"2026-08-06T23:51:25.289942Z","title":null,"venue":null,"work_id":"e103fd78-ce1c-4284-b3ec-9f8eac35bd3e","year":1950},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:20.428659Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:dc35b4df27227c631c0de6bb9c5c7c29f7d0b2ef9befaabca7573a55c7251779","observation_id":"37cdd5d4-ecd6-4e52-bd08-210b97a12923","resolution":{"observed_at":"2026-08-06T23:51:25.443809Z","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":"2026-08-06T23:51:25.053346Z","title":"A conversational movie search system based on con- ditional random fields.13th Annual Conference of the International Speech Communication Association 2012, INTERSPEECH 2012, 3, 01","venue":null,"work_id":"2f41d4dd-d080-49f4-8afc-f00a6e0a47fe","year":2012},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:20.508680Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:92882da20b03a31133bc783c9aff83e64b4c44f2c1832591de9637fb09f33b3e","observation_id":"65163342-def3-40e8-9743-2da96ab12d82","resolution":{"observed_at":"2026-08-06T23:51:25.159813Z","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":"1907.11692","last_updated":"2019-07-26T17:48:29Z","snapshot_observed_at":"2026-07-31T22:31:37.910868Z","submitted_at":"2019-07-26T17:48:29Z","title":"RoBERTa: A Robustly Optimized BERT Pretraining Approach","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1907.11692","snapshot_observed_at":"2026-08-06T23:51:20.635636Z","title":null,"venue":null,"work_id":null,"year":1907},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:20.635636Z"},"links":{"cited_paper":"/paper/1907.11692","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:7056dc193e13772e3da6d4b99140c6617045a3af1212bca9a3b07ab4e26c98f0","observation_id":"d362a222-b989-4f37-b654-6cac82bca36c","resolution":{"observed_at":"2026-08-06T23:51:20.635636Z","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":"2026-08-06T23:51:24.761344Z","title":"Bissyand ´e, T","venue":null,"work_id":"2b384a80-d37c-46b0-be4e-878abcc9ba7a","year":2024},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:20.707568Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:e7840d68e77110fe97dc6839ece514e607ca9530e35456664bc9d7822c1ffd45","observation_id":"dd3fc778-2770-4e63-af55-ea5981a0cb71","resolution":{"observed_at":"2026-08-06T23:51:24.863654Z","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":"2026-08-06T23:51:24.639548Z","title":"URL https://aclanthology.org/ 2024.moomin-1.2/","venue":null,"work_id":"4c2593c7-c738-466d-a7b8-54d43932f979","year":2024},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:20.781502Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:d13440a9ef2e38cfff933eeccba85a5cb566eacdd0d70b7cc17f9b268b00d707","observation_id":"e3594ea4-0a6c-4f55-97f8-6376b732f6ed","resolution":{"observed_at":"2026-08-06T23:51:24.689916Z","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":"2026-08-06T23:51:24.441254Z","title":null,"venue":null,"work_id":"11bd6f6d-63bb-4eaf-affa-75fb81d531ec","year":2023},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:20.870513Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:8b5eafaccdaf58e14a9842ffd81441e418f1fe577694450986f61fe10402bf98","observation_id":"d25ac3da-0e65-42d0-9ff6-6e56da1f5dbc","resolution":{"observed_at":"2026-08-06T23:51:24.538650Z","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":"2026-08-06T23:51:24.316297Z","title":"Semeval-2017 task 4: Sentiment analysis in twitter","venue":null,"work_id":"204cba15-6d64-49bc-bf7f-a25082be4712","year":2017},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:20.940534Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:a2c9648d484eb5e07f32fe2d542e7cd6b688a0b2d8717b2a540103ebd0c09f10","observation_id":"5870faa5-9aac-4653-b85b-49f3a0328f47","resolution":{"observed_at":"2026-08-06T23:51:24.355459Z","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":"1910.01108","last_updated":"2020-03-01T02:57:50Z","snapshot_observed_at":"2026-08-07T19:07:36.327251Z","submitted_at":"2019-10-02T17:56:28Z","title":"DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1910.01108","snapshot_observed_at":"2026-08-06T23:51:21.021456Z","title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter.ArXiv, abs/1910.01108,","venue":null,"work_id":null,"year":1910},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.021456Z"},"links":{"cited_paper":"/paper/1910.01108","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:ab1f34281521424c382aee9b70e7e490268f1a8a3065963c65de223b53fab816","observation_id":"99db9a13-2fee-4f4e-9daf-28672702bcf0","resolution":{"observed_at":"2026-08-06T23:51:21.021456Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2012.11926","last_updated":"2021-10-04T14:52:03Z","snapshot_observed_at":"2026-07-06T10:26:51.748161Z","submitted_at":"2020-12-22T10:53:07Z","title":"Few-Shot Text Generation with Pattern-Exploiting Training","version":2},"cited_work":{"arxiv_id":"2012.11926","doi":null,"metadata_source":"pith","pith_arxiv_id":"2012.11926","snapshot_observed_at":"2026-08-06T23:51:22.890691Z","title":"Few-Shot Text Generation with Pattern-Exploiting Training","venue":"cs.CL","work_id":"21fbfcfc-19fb-42fb-8476-315c025ba2d8","year":2020},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.108437Z"},"links":{"cited_paper":"/paper/2012.11926","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:dfc795686b8c092398f97aa1113817ae9e0c166ef4c7c744029818a3f40e602d","observation_id":"5119602e-b12a-4956-8969-5e331bcd3e6a","resolution":{"observed_at":"2026-08-06T23:51:22.925163Z","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":"2026-08-06T23:51:24.003297Z","title":"L., Wallace, E., and Singh, S","venue":null,"work_id":"c4020441-aaa5-45b3-a7af-29fc6d7cacb9","year":2020},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.271251Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:2c16a6f94e1b370f0fc499984a7fb6b8f753f62ab5f5f90cb4f183606b975fd1","observation_id":"048e2eda-9b1a-4bc5-81c1-531fd964d778","resolution":{"observed_at":"2026-08-06T23:51:24.067247Z","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":"2408.11796","last_updated":"2024-12-09T18:31:01Z","snapshot_observed_at":"2026-08-07T10:56:20.468878Z","submitted_at":"2024-08-21T17:38:48Z","title":"LLM Pruning and Distillation in Practice: The Minitron Approach","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.11796","snapshot_observed_at":"2026-08-06T23:51:21.346388Z","title":"Su, Y ., Wang, X., Qin, Y ., Chan, C.-M., Lin, Y ., Wang, H., Wen, K., Liu, Z., Li, P., Li, J., et al","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.346388Z"},"links":{"cited_paper":"/paper/2408.11796","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:b3a51d15fad2204c6b5033feb6c528a9ee14eed005a8edb1b321faf8a2e3c822","observation_id":"cff09b21-b52d-4ed2-81e9-948ee10bea16","resolution":{"observed_at":"2026-08-06T23:51:21.346388Z","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":"2026-08-06T23:51:21.432610Z","title":"Touvron, H., Martin, L., Stone, K","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.432610Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:35a48e96e85c2b50985013919d569dbcd426741e6adcd5bc6eea6eba751fd076","observation_id":"5b7ce82a-9e8d-4e0d-9b42-4dd652414769","resolution":{"observed_at":"2026-08-06T23:51:21.432610Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.18955","last_updated":"2024-03-03T13:49:49Z","snapshot_observed_at":"2026-07-06T17:52:13.812196Z","submitted_at":"2024-03-03T13:49:49Z","title":"Structurally Prune Anything: Any Architecture, Any Framework, Any Time","version":1},"cited_work":{"arxiv_id":"2403.18955","doi":null,"metadata_source":"pith","pith_arxiv_id":"2403.18955","snapshot_observed_at":"2026-08-06T23:51:22.725696Z","title":"Structurally Prune Anything: Any Architecture, Any Framework, Any Time","venue":"cs.LG","work_id":"c0d8fe42-b75c-4e54-a966-4f1912f8c776","year":2024},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.522905Z"},"links":{"cited_paper":"/paper/2403.18955","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:8e08ddd2e997f4aff03885f33efa7a12a71d4d8bd556d644d63b844778f60d23","observation_id":"419ae4c0-cba7-4205-be56-549852550208","resolution":{"observed_at":"2026-08-06T23:51:22.777115Z","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":{"arxiv_id":"2302.04870","last_updated":"2023-02-09T18:59:55Z","snapshot_observed_at":"2026-07-06T14:50:11.149218Z","submitted_at":"2023-02-09T18:59:55Z","title":"Offsite-Tuning: Transfer Learning without Full Model","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.04870","snapshot_observed_at":"2026-08-06T23:51:21.660873Z","title":"Offsite-tuning: Transfer learn- ing without full model.arXiv preprint arXiv:2302.04870,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.660873Z"},"links":{"cited_paper":"/paper/2302.04870","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:cba8b508d0b024c2f7a41d66ea76c23ac217203350282448a86d62ae463d6887","observation_id":"7261a1c6-85f6-413d-b75e-b6e44e88514d","resolution":{"observed_at":"2026-08-06T23:51:21.660873Z","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":"2026-08-06T23:51:23.885389Z","title":"Factual probing is [mask]: Learning vs","venue":null,"work_id":"7428989f-51c9-48bf-b4a2-047d40f0d0ca","year":2021},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.715226Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:231fc07c56598071246e2a4827c9293791f8c459683ba2fd65f5484c354d0ccd","observation_id":"f712776f-e0d3-4799-b1ff-7d4e8cad9fc8","resolution":{"observed_at":"2026-08-06T23:51:23.969374Z","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":"2026-08-06T23:51:23.526634Z","title":"The results show that using the same dataset for both private and public sets consistently achieves the best performance","venue":null,"work_id":"1318dbb8-e2a5-4a9a-8a1c-f78cf490c0a0","year":2016},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.928244Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:32bebf46eb7320162428b0f00f7cc83874e58a5d0bb6f9455326b7e516f0ff89","observation_id":"a4ef57da-cba5-4692-ac83-305d21726c2e","resolution":{"observed_at":"2026-08-06T23:51:23.625664Z","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":"2026-08-06T23:51:23.349426Z","title":null,"venue":null,"work_id":"2a7377d0-5c5a-4760-8281-c149a31cc615","year":2015},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.999257Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:d55cd59f6122d6c6a9379edc11e16cee84797b49bae7c7879fb2a3834cd6de2d","observation_id":"90bdd5dc-8b91-41b0-8d07-e3fff49bdb9b","resolution":{"observed_at":"2026-08-06T23:51:23.435668Z","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":"2786.6783","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T23:51:22.355660Z","title":"Knowledge Distillation Setup.We also investigated the best way of performing KD to improve prompt transferability","venue":null,"work_id":"1e44567b-942e-4a6c-beae-ef48e42ff314","year":null},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:22.040979Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:9ab0f69ef49e3072304b2ecfec07aedbce096f8bded47f009c305624a975a915","observation_id":"070c9392-c974-4068-ab63-2b254027bbe1","resolution":{"observed_at":"2026-08-06T23:51:22.424294Z","resolver_source":"raw_fallback","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":"2026-08-06T23:51:23.236993Z","title":"Both too few or too many tokens in the soft prompt lead to sub-optimal performance","venue":null,"work_id":"34e33c24-7a63-4ffd-a754-b84781b34e09","year":2023},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:22.104083Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:ef7ebcab74a2a1a38b419907cff57cc5289f433da8444904537a6ec2cfedf641","observation_id":"f9884a3c-e3fe-4736-af3c-b05612f32a16","resolution":{"observed_at":"2026-08-06T23:51:23.273197Z","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":"2026-08-06T23:51:26.218641Z","title":"Membership inference attacks from first principles","venue":null,"work_id":"77d7b44e-cb72-47ff-8169-ba8aeed1cea8","year":1914},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":2006,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:19.323002Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:095cb05b61aa6d7397af46617002559e49c6ec04324207db2f621f01c3c6eb1c","observation_id":"94b7ddcc-24fc-4c06-bfca-fa87003e2793","resolution":{"observed_at":"2026-08-06T23:51:26.325647Z","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":"2312.03724","last_updated":"2024-03-17T23:16:41Z","snapshot_observed_at":"2026-07-06T16:57:55.137830Z","submitted_at":"2023-11-27T02:01:10Z","title":"DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.03724","snapshot_observed_at":"2026-08-06T23:51:20.136653Z","title":"T., Zhang, C., Li, Z., Li, B., and Wang, Z","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:20.136653Z"},"links":{"cited_paper":"/paper/2312.03724","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:a83a89583166557b9968a98770016f2994974a20c95362391f335886b229ec09","observation_id":"a1c1a4b2-a234-4d46-a4c5-d8cceae247e9","resolution":{"observed_at":"2026-08-06T23:51:20.136653Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1510.00149","last_updated":"2016-02-15T06:25:40Z","snapshot_observed_at":"2026-08-04T16:59:47.843960Z","submitted_at":"2015-10-01T09:03:44Z","title":"Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1510.00149","snapshot_observed_at":"2026-08-06T23:51:19.949589Z","title":"Han, X., Zhao, W., Ding, N., Liu, Z., and Sun, M","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:19.949589Z"},"links":{"cited_paper":"/paper/1510.00149","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:a5748ff674eeadf86468a91c7478f2cf67af963bdf6f30807859fcc5d48e39ea","observation_id":"2da8cb45-101c-47f5-9b7f-de67a87f7f38","resolution":{"observed_at":"2026-08-06T23:51:19.949589Z","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":"2026-08-06T23:51:25.534645Z","title":null,"venue":null,"work_id":"24efa92c-2246-41e2-9e31-73a665b38079","year":2002},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:20.366245Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:190b9759e1c6b25c09245dcacbdbb17f0ac4e9bffc407205f02d646440ec7980","observation_id":"bd9aa433-6047-4d8c-8979-32fdc8741619","resolution":{"observed_at":"2026-08-06T23:51:25.647634Z","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":"1712.05877","last_updated":"2017-12-15T23:56:52Z","snapshot_observed_at":"2026-07-06T06:14:38.280461Z","submitted_at":"2017-12-15T23:56:52Z","title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1712.05877","snapshot_observed_at":"2026-08-06T23:51:20.222981Z","title":"Kudari, V","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:20.222981Z"},"links":{"cited_paper":"/paper/1712.05877","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:20b4e151767e8da2d99e96001ba39a78f44a9155c8886b6727fed598858a0143","observation_id":"423c16e3-a107-4dbf-b123-0926c6c87fe3","resolution":{"observed_at":"2026-08-06T23:51:20.222981Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-06T23:51:19.593363Z","title":"Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:19.593363Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:616f4628aa59757d45db88f01c78fdf1b8ca84299a35d4b1f1b417c56b128ab8","observation_id":"8a789b62-2649-4c29-9b6e-a1c007fd3242","resolution":{"observed_at":"2026-08-06T23:51:19.593363Z","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":"2026-08-06T23:51:24.143372Z","title":"and Sch¨utze, H","venue":null,"work_id":"34225957-afca-48c3-be40-7f9253633927","year":2021},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.195059Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:441e10203580322f844d2c287baa9a78e83a8a3932260381b0ea745ebf71e43c","observation_id":"0b211430-49fb-42c2-a747-476ffd90ded6","resolution":{"observed_at":"2026-08-06T23:51:24.216230Z","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":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-06T23:51:19.739874Z","title":"M., Hauth, A., et al","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:19.739874Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:f51b32d7477a490be7cde0816f0fcfcafa6b3ad8bfe83cdf7101790c65338f17","observation_id":"4a4d1bfe-a61c-4afb-b5bb-f399c6a81271","resolution":{"observed_at":"2026-08-06T23:51:19.739874Z","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":"2026-08-06T23:51:19.397146Z","title":"Chiang, W.-L., Li, Z., Lin, Z., Sheng, Y ., Wu, Z., Zhang, H., Zheng, L., Zhuang, S., Zhuang, Y ., Gonzalez, J","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:19.397146Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:49e87bdf150418baa2dacec99cb94d665cef672a2bd289fac216c071934acb8b","observation_id":"696aacdb-eef5-4de3-97b7-26b3362e05a1","resolution":{"observed_at":"2026-08-06T23:51:19.397146Z","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":"2026-08-06T23:51:19.213684Z","title":"D., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:19.213684Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:79e289f98a9fa720f97a99d338ab7cad7c6193eeb8011d8144b58f42f3d5f297","observation_id":"b0748cc4-9869-4bdf-bc2a-c106256673d2","resolution":{"observed_at":"2026-08-06T23:51:19.213684Z","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":"2026-08-06T23:51:25.787220Z","title":"Hambardzumyan, K., Khachatrian, H., and May, J","venue":null,"work_id":"6ed796f3-1bb0-4036-a8dc-ddd707afbf68","year":2021},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:19.860167Z"},"links":{"citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:7e5c06bd93a445058122e1e8a1391650ffa6bf08fdd626a8a1e0d306ef8e0318","observation_id":"ba6051aa-b2c9-497f-8b36-ff74c6ed5b70","resolution":{"observed_at":"2026-08-06T23:51:25.854993Z","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":"2302.03668","last_updated":"2023-06-01T12:26:45Z","snapshot_observed_at":"2026-08-08T08:28:54.214867Z","submitted_at":"2023-02-07T18:40:18Z","title":"Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.03668","snapshot_observed_at":"2026-08-06T23:51:21.598507Z","title":"Hard prompts made easy: Gradient-based discrete optimization for prompt tuning and discovery.ArXiv, abs/2302.03668,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-06T23:51:21.598507Z"},"links":{"cited_paper":"/paper/2302.03668","citing_paper":"/paper/2506.16196"},"observation_digest":"sha256:53c79c95e0f69837a3a854689c17039fa8ab742fb228feeddfa66c26319eb734","observation_id":"c899c6ad-5ee1-4016-b8f2-01d072ed3f1f","resolution":{"observed_at":"2026-08-06T23:51:21.598507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.16196","last_updated":"2025-06-19T10:25:16Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T10:56:44.567048Z","submitted_at":"2025-06-19T10:25:16Z","title":"Efficient and Privacy-Preserving Soft Prompt Transfer for LLMs"},"reference_resolution":{"displayed":38,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":20,"verified_exact":3,"verified_fuzzy":14},"total_outbound_references":38},"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 38 of 38 outbound references and 0 inbound Pith citation observations for arXiv:2506.16196."}