{"as_of":"2026-08-18T06:39:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:e5c71d006fe5aa516a637d2eb15c721aa795ff6443c205733a841166cab8a19d","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:39:04.552704Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-24T04:13:53.165607Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2104.07762","last_updated":"2021-04-22T22:57:03Z","snapshot_observed_at":"2026-08-16T19:27:40.613403Z","submitted_at":"2021-04-15T20:40:05Z","title":"Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?","version":2},"cited_work":{"arxiv_id":"2104.07762","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2104.07762","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"72a3da0e-e62f-4369-9874-625dc82469da","year":2021},"citing_paper":{"arxiv_id":"2401.02458","last_updated":"2026-04-29T07:43:10Z","snapshot_observed_at":"2026-07-29T23:57:44.096283Z","submitted_at":"2024-01-04T08:00:32Z","title":"Data-Centric Foundation Models in Computational Healthcare: A Survey","version":3},"reference_index":155,"source":"pdf_text","source_observed_at":"2026-05-24T04:13:05.328492Z"},"links":{"cited_paper":"/paper/2104.07762","citing_paper":"/paper/2401.02458"},"observation_digest":"sha256:888bebe71175e36b3fc3a928ec630b7cdbef4a2a6df6f4d471ca5b66a0b58907","observation_id":"3db5a586-8310-4533-83fb-df13a4585802","resolution":{"observed_at":"2026-05-24T04:13:53.168057Z","resolver_source":"arxiv_id","status":"verified_exact"},"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":"2104.07762","last_updated":"2021-04-22T22:57:03Z","snapshot_observed_at":"2026-08-16T19:27:40.613403Z","submitted_at":"2021-04-15T20:40:05Z","title":"Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?","version":2},"cited_work":{"arxiv_id":"2104.07762","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2104.07762","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"72a3da0e-e62f-4369-9874-625dc82469da","year":2021},"citing_paper":{"arxiv_id":"2409.18169","last_updated":"2026-04-23T18:48:49Z","snapshot_observed_at":"2026-08-14T15:55:00.676298Z","submitted_at":"2024-09-26T17:55:22Z","title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","version":6},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-05-23T20:58:16.237327Z"},"links":{"cited_paper":"/paper/2104.07762","citing_paper":"/paper/2409.18169"},"observation_digest":"sha256:91774acae981cb1eeb1063435ab805d8ffb0eeb416e4fc11951271040a2c244f","observation_id":"437e6b98-c95f-48a6-9ec8-85228a19c429","resolution":{"observed_at":"2026-05-23T20:58:26.049784Z","resolver_source":"arxiv_id","status":"verified_exact"},"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":"2104.07762","last_updated":"2021-04-22T22:57:03Z","snapshot_observed_at":"2026-08-16T19:27:40.613403Z","submitted_at":"2021-04-15T20:40:05Z","title":"Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.07762","snapshot_observed_at":"2026-08-12T11:29:29.428886Z","title":"Does bert pretrained on clinical notes reveal sensitive data? arXiv preprint arXiv:2104.07762 , 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.18191","last_updated":"2024-11-29T08:33:49Z","snapshot_observed_at":"2026-08-14T20:43:41.329249Z","submitted_at":"2024-11-27T10:14:38Z","title":"InputSnatch: Stealing Input in LLM Services via Timing Side-Channel Attacks","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-12T11:29:29.428886Z"},"links":{"cited_paper":"/paper/2104.07762","citing_paper":"/paper/2411.18191"},"observation_digest":"sha256:44775681a8f7621a83c50ee38bc4c8ea06e58f37eacc0acfce4564dc41f103a5","observation_id":"37fcec31-ba01-48e2-848d-39f4cac1b8c9","resolution":{"observed_at":"2026-08-12T11:29:29.428886Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.07762","last_updated":"2021-04-22T22:57:03Z","snapshot_observed_at":"2026-08-16T19:27:40.613403Z","submitted_at":"2021-04-15T20:40:05Z","title":"Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.07762","snapshot_observed_at":"2026-08-15T23:39:04.552704Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.06284","last_updated":"2025-05-07T07:21:37Z","snapshot_observed_at":"2026-08-17T06:33:37.325126Z","submitted_at":"2025-05-07T07:21:37Z","title":"DMRL: Data- and Model-aware Reward Learning for Data Extraction","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T23:39:04.552704Z"},"links":{"cited_paper":"/paper/2104.07762","citing_paper":"/paper/2505.06284"},"observation_digest":"sha256:fd324d26dfd36166a47b134d1d446b72ed1e0467911c3dbae4e524c421b06ed1","observation_id":"0e70d11f-103d-4448-ac26-2bf7cf4802e8","resolution":{"observed_at":"2026-08-15T23:39:04.552704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2104.07762/citation-record","integrity":"/paper/2104.07762/integrity","json":"/paper/2104.07762/citation-record.json","paper":"/paper/2104.07762"},"outbound":[],"paper":{"arxiv_id":"2104.07762","last_updated":"2021-04-22T22:57:03Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-16T19:27:40.613403Z","submitted_at":"2021-04-15T20:40:05Z","title":"Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2104.07762."}