{"as_of":"2026-08-19T02:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a81986fcc8eb39613c9c32d454d5551aedc392792b42a6018bc5884e16e441a1","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T05:56:06.001502Z","state":"measured"},{"denominator":31,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":31,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2504.21036/citation-record","integrity":"/paper/2504.21036/integrity","json":"/paper/2504.21036/citation-record.json","paper":"/paper/2504.21036"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T05:56:05.861762Z","title":"In: Proceedings of the 2016 ACM SIGSAC conference on computer and communications security","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.861762Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:60d3c8bf498b35c7a3ba59730aee71ae41e8c30cadb781c9ed4cd15db49dbe81","observation_id":"1344fce5-15fb-41c2-bb03-109dda75ad04","resolution":{"observed_at":"2026-08-16T05:56:05.861762Z","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":"2026-08-16T05:56:06.503207Z","title":"In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics","venue":null,"work_id":"1cb78efa-5fe0-465e-b555-d7a6759eb31a","year":2022},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.867483Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:097f84f3ce7b9236315fc31d082dbcffdd4bda2380f77979ba2b3f797c39cb19","observation_id":"eeb9e1b5-e4a0-42a0-84f0-476f2d531b9c","resolution":{"observed_at":"2026-08-16T05:56:06.508446Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.11822","last_updated":"2023-11-20T14:58:56Z","snapshot_observed_at":"2026-08-18T19:05:49.130385Z","submitted_at":"2023-11-20T14:58:56Z","title":"Zero redundancy distributed learning with differential privacy","version":1},"cited_work":{"arxiv_id":"2311.11822","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.11822","snapshot_observed_at":"2026-08-16T05:56:06.169075Z","title":"Zero redundancy distributed learning with differential privacy","venue":"cs.LG","work_id":"074f01f4-caee-46c9-8a9e-985aa98f3cb6","year":2023},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.872591Z"},"links":{"cited_paper":"/paper/2311.11822","citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:75dc124d11b4d685d5cd94420946f1d95dbb29e47db4ebb2e3e96596ac1d3b48","observation_id":"e9b49c36-a8ed-4152-9a2b-93905dafc913","resolution":{"observed_at":"2026-08-16T05:56:06.176356Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:06.486159Z","title":"In: Workshop on Trustworthy and Socially Respon- sible Machine Learning, NeurIPS 2022 (2022)","venue":null,"work_id":"1f630f76-66ef-40e5-8c37-ff23525eec14","year":2022},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.877780Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:6f7868e838a01329ca68a09a72c2aad706683e04d32b60833090ba0b83a3cb2b","observation_id":"b72fe04f-9aca-4c95-8d64-d2b568253f3d","resolution":{"observed_at":"2026-08-16T05:56:06.491707Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:06.468726Z","title":"In: Proceedings of the 40th International Conference on Machine Learning (2023)","venue":null,"work_id":"33672b17-c9b4-4bac-94f9-1c37a11937df","year":2023},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.882524Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:bac12742286d52fc951996f5329839025191daf0052db1d83ec26959209420d8","observation_id":"1561a3d0-109d-43f0-970a-979a555871f5","resolution":{"observed_at":"2026-08-16T05:56:06.473811Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:06.453596Z","title":"In: International Conference on Machine Learning","venue":null,"work_id":"5156db4b-2d9a-45c3-b047-87367001c938","year":2023},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.888186Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:63b4b848ff1107cdf2fc42295cfdb2f8c84bcff170226d5058b4e11e09b1f753","observation_id":"e9d84da6-b42e-48d2-8842-e5a2b1813ad1","resolution":{"observed_at":"2026-08-16T05:56:06.458283Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:06.438098Z","title":null,"venue":null,"work_id":"8bbc5fe9-fbc3-496c-8463-f0fffec4aa54","year":2019},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.894173Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:f691a71dc285b074faa32adbbf1b8a83d3b1e957c622526814fda3da2509b323","observation_id":"b5aebe2c-e041-4a30-9b20-005e79d8d737","resolution":{"observed_at":"2026-08-16T05:56:06.443245Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1810.04805","last_updated":"2019-05-24T20:37:26Z","snapshot_observed_at":"2026-08-14T18:16:28.847993Z","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":"2026-08-16T05:56:05.898647Z","title":"arXiv preprint arXiv:1810.04805 (2018)","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.898647Z"},"links":{"cited_paper":"/paper/1810.04805","citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:c88e8b425b9d6b1abfdb2b83a385acdcb672b4a32b58c411b4b1a11091633f1e","observation_id":"2e6992ad-f0c2-4878-a6c4-fef28b603caf","resolution":{"observed_at":"2026-08-16T05:56:05.898647Z","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":"2026-08-16T05:56:06.420521Z","title":"In: International colloquium on automata, lan- guages, and programming","venue":null,"work_id":"5c504f1a-6d2f-470a-b15a-354f3991980d","year":2006},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.903151Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:0cd9c053020684b58ab625dfe69a7d0dc784028066c1f37e4424fded1f55e59c","observation_id":"7f324b8e-8195-42ca-91a8-6521ca464dda","resolution":{"observed_at":"2026-08-16T05:56:06.425715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:06.405580Z","title":"In: 2019 IEEE International Conference on Data Mining","venue":null,"work_id":"a66bf2ba-45d5-4e16-95ed-740e6425d97c","year":2019},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.907484Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:725a6caf44cf59b2e5c1dfdc14faaf7114570ab492eb73a1ee6486873735cc30","observation_id":"59173e20-2c1e-4269-8b36-3371b84c3b99","resolution":{"observed_at":"2026-08-16T05:56:06.410113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.06062","last_updated":"2024-11-26T03:19:15Z","snapshot_observed_at":"2026-08-18T08:50:41.247101Z","submitted_at":"2023-11-10T13:55:05Z","title":"Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2311.06062","snapshot_observed_at":"2026-08-16T05:56:05.911797Z","title":"arXiv preprint arXiv:2311.06062 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.911797Z"},"links":{"cited_paper":"/paper/2311.06062","citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:050264ca52f4868f02b93ca7ff21d038816ffd0dc73b6f31c6b661ab6e795a37","observation_id":"47ed0543-fa60-4c8d-8317-db25715210e5","resolution":{"observed_at":"2026-08-16T05:56:05.911797Z","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":"2026-08-16T05:56:05.916433Z","title":"Transactions on Machine Learning Research (2024)","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.916433Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:8e25a235b30df5bd8a36ae2ba72ddc3dc511ffbe40831d06ffd091214945f94e","observation_id":"8081e4e5-f360-4e8d-95c1-c08fe72e7ec0","resolution":{"observed_at":"2026-08-16T05:56:05.916433Z","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":"2026-08-16T05:56:05.920752Z","title":"In: International Con- ference on Learning Representations (2022)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.920752Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:492b65e1b4d4ae29b794cdff09e64b601ec071c040c0131b86caeae163552097","observation_id":"f64f552b-a290-4ed7-97ba-e4340e1e8690","resolution":{"observed_at":"2026-08-16T05:56:05.920752Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08305","last_updated":"2021-04-16T18:29:58Z","snapshot_observed_at":"2026-08-18T19:05:06.003659Z","submitted_at":"2021-04-16T18:29:58Z","title":"Membership Inference Attack Susceptibility of Clinical Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08305","snapshot_observed_at":"2026-08-16T05:56:05.925061Z","title":"arXiv preprint arXiv:2104.08305 (2021)","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.925061Z"},"links":{"cited_paper":"/paper/2104.08305","citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:3c32f56177adb417f13a86dd7069b3db0f89a19a33a8c0b6c099166e41af2fb9","observation_id":"9cc571b6-0d81-468c-a431-cd115d822cc2","resolution":{"observed_at":"2026-08-16T05:56:05.925061Z","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":"2026-08-16T05:56:05.929758Z","title":"In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.929758Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:aa3f0946a9512f18926cd2c9818df2a884310595ffcc49e2432dca7569ed9d51","observation_id":"f2fc7351-b1b1-4ee2-b91e-6bd3ba9dc4a8","resolution":{"observed_at":"2026-08-16T05:56:05.929758Z","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":"2026-08-16T05:56:06.361394Z","title":"In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Pro- cessing","venue":null,"work_id":"3291f4a5-19db-4d6d-b951-d55b2fc3fff0","year":2021},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.934723Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:7eb5e9f3b9289f5bc81e9fb3525ae3c4f310427e462c6912c1b2bb36f3133a30","observation_id":"7030c0c0-0ae0-4935-a95a-d2ecbec84b79","resolution":{"observed_at":"2026-08-16T05:56:06.366567Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:05.939118Z","title":"arXiv preprint arXiv:2305.06212 (2023) 18 Hao Du et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.939118Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:c99d8612d4b87296745f26414c11fa8c9b343978bd35038477a337f0e838aab6","observation_id":"2db07e0e-6eff-4e56-b1a4-e782d8b912d5","resolution":{"observed_at":"2026-08-16T05:56:05.939118Z","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":"2026-08-16T05:56:06.345565Z","title":"In: Oh, A.H., Agarwal, A., Belgrave, D., Cho, K","venue":null,"work_id":"8f0f3636-9c23-4051-9796-3d5cf752366f","year":2022},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.943053Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:73b9bdfbc8823d01d086275688d487c170ddd7702d61339cc16418a4e59f1d41","observation_id":"603e90d5-9b09-4ba2-945d-c805da88fce2","resolution":{"observed_at":"2026-08-16T05:56:06.350495Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:06.329524Z","title":"AI Open5, 208–215 (2024)","venue":null,"work_id":"fde9fcf2-03e5-43e9-9cb1-d710d660a48d","year":2024},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.946777Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:04a9f65c785db89eee7bf9c1e0caa2dc7d2bb43551e9fdd911558914e27ac4da","observation_id":"21552c46-1109-49a4-bfdc-9a312d8fbb84","resolution":{"observed_at":"2026-08-16T05:56:06.334669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:06.316086Z","title":"In: 2023 IEEE Symposium on Security and Privacy","venue":null,"work_id":"1e9878a1-6304-4b62-b388-077d79576dfc","year":2023},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.950959Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:4aaf463df06d8eb3adcd9e4526a9097758baf38a354e1ddb4ed44a033b1e5480","observation_id":"33684c8e-ff6e-4988-a677-9a69130dd474","resolution":{"observed_at":"2026-08-16T05:56:06.320140Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:06.302671Z","title":"https://github.com/ huggingface/peft (2022)","venue":null,"work_id":"0eee03af-7cfb-49e2-91da-8fa28253dc89","year":2022},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.954667Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:9c28773a0782b19bfdaa406c53427e5260012cd6d48a684853202c1ae462241a","observation_id":"aecaee86-e523-4162-8d7c-16509997507f","resolution":{"observed_at":"2026-08-16T05:56:06.306607Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:06.289676Z","title":null,"venue":null,"work_id":"08f3f0ed-4a76-402c-bfc3-4464697bdc85","year":2025},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.959816Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:d8eeb886086befb2546f71898a379fa367219ed2a69bdabb28cc5b9d614d255e","observation_id":"03809114-f624-46d6-a4e1-26600f2f8059","resolution":{"observed_at":"2026-08-16T05:56:06.293836Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:05.964425Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.964425Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:33878c3b8dd6f64fa63aa37ee7ea2f9204a4bc88db7a159570cb74cf03599291","observation_id":"99e618dc-a28e-432d-9728-147e10b74791","resolution":{"observed_at":"2026-08-16T05:56:05.964425Z","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":"2026-08-16T05:56:06.266161Z","title":"In: Goldberg, Y., Kozareva, Z., Zhang, Y","venue":null,"work_id":"287d75f0-3061-4ab9-b186-f92eb6e94422","year":2022},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.968972Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:61f03bc4598508825f5d69a828957bd6653bca29abfbbd2327c4dbaa881652f6","observation_id":"46d61b07-f5f7-4a6a-b61e-3a3ba170c2aa","resolution":{"observed_at":"2026-08-16T05:56:06.270588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:06.251557Z","title":"In: EMNLP","venue":null,"work_id":"98d4e5c2-53be-4ae9-b0e5-129db27df621","year":2022},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.973487Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:8163d52cfe338df93091dbba3f253af68f74f2e9d9d37cd57717f522b8461cee","observation_id":"76d85f8a-a4f7-4b63-a399-16ecf36f7d35","resolution":{"observed_at":"2026-08-16T05:56:06.256166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:06.236255Z","title":"In: The Thirteenth International Conference on Learning Representations (2025)","venue":null,"work_id":"632d7aa1-55c1-4c17-b977-b89e7198eafa","year":2025},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.978362Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:9dfca0e8315bf359ec90d448a1eec8aeafd9cef0b9993e5958d9167fed8e0dc5","observation_id":"7e85001c-d341-4ee0-a12d-6434db01e4be","resolution":{"observed_at":"2026-08-16T05:56:06.241134Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:05.983104Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.983104Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:e8e567cfcacad21157d0e310f7dc62b52f2576c93629d4ea9feb4d6d0498f9c1","observation_id":"6fc7ac41-9e8e-4d61-9226-9337cc2de712","resolution":{"observed_at":"2026-08-16T05:56:05.983104Z","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":"2026-08-16T05:56:06.211260Z","title":"https://github.com/kingoflolz/mesh-transformer-jax (May 2021)","venue":null,"work_id":"7fffc0ab-3c5c-49bc-a212-90907131dd62","year":2021},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.987592Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:106adc0c678c49cc5dbd3008666a0450a98ded9bfb487e51931930cec2124881","observation_id":"2c225c6c-2ec7-4308-968d-abdedfa82988","resolution":{"observed_at":"2026-08-16T05:56:06.216022Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T05:56:06.195895Z","title":"In: Proceedings ofthe2020ConferenceonEmpiricalMethodsinNaturalLanguageProcessing:Sys- tem Demonstrations","venue":null,"work_id":"8d69bba7-c7bb-4fae-adc5-797cc389e7c0","year":2020},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.992218Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:0cb9f6d83635947a4be9f2a6a0ceb87b76f2c4651b50a68c4d92a8fdcdd14d67","observation_id":"8f2dc6dd-0f4a-4696-989f-f63a2e7f664c","resolution":{"observed_at":"2026-08-16T05:56:06.200569Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.12148","last_updated":"2023-12-19T13:31:24Z","snapshot_observed_at":"2026-08-16T14:33:23.059607Z","submitted_at":"2023-12-19T13:31:24Z","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.12148","snapshot_observed_at":"2026-08-16T05:56:05.996779Z","title":"arXiv preprint arXiv:2312.12148 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:05.996779Z"},"links":{"cited_paper":"/paper/2312.12148","citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:4652621296206abf6e94211b38d2963b6e43ceb786d8d9ead733e068c443e60d","observation_id":"5716c7a4-c927-494b-8876-b8efd47c73f2","resolution":{"observed_at":"2026-08-16T05:56:05.996779Z","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":"2026-08-16T05:56:06.001502Z","title":"In: NIPS (2015)","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-16T05:56:06.001502Z"},"links":{"citing_paper":"/paper/2504.21036"},"observation_digest":"sha256:01018ea18638b4422f1a65af9131acee4665c35ceebb1653e114fca52eef75d7","observation_id":"82d0a8ac-758b-4976-8f99-905c5550a6b8","resolution":{"observed_at":"2026-08-16T05:56:06.001502Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2504.21036","last_updated":"2025-05-01T10:10:01Z","latest_version":2,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-18T19:47:13.332881Z","submitted_at":"2025-04-28T05:34:53Z","title":"Can Differentially Private Fine-tuning LLMs Protect Against Privacy Attacks?"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":16},"total_outbound_references":31},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 0 inbound Pith citation observations for arXiv:2504.21036."}