{"as_of":"2026-08-20T07:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:846ae79879fe20e595ffd72dbf4387cf73b63bf237ac73c5fba8ee4b8f9ccd0e","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T22:45:34.196559Z","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":"2026-05-14T23:28:17.132439Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.07925","last_updated":"2021-06-15T07:27:39Z","snapshot_observed_at":"2026-08-16T18:17:06.574057Z","submitted_at":"2021-06-15T07:27:39Z","title":"Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.07925","snapshot_observed_at":"2026-08-15T22:45:34.196559Z","title":"Machine learning with electronic health records is vulnerable to backdoor trigger attacks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.06477","last_updated":"2025-05-10T00:33:15Z","snapshot_observed_at":"2026-08-19T20:55:22.611592Z","submitted_at":"2025-05-10T00:33:15Z","title":"Learning from the Good Ones: Risk Profiling-Based Defenses Against Evasion Attacks on DNNs","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T22:45:34.196559Z"},"links":{"cited_paper":"/paper/2106.07925","citing_paper":"/paper/2505.06477"},"observation_digest":"sha256:672dc4bd81319a63b5f89531633ba61aaa0e13a76ca2816d6a5c509bb7388a4b","observation_id":"7e49f74c-f71d-4677-af6b-539d2aada85c","resolution":{"observed_at":"2026-08-15T22:45:34.196559Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.07925","last_updated":"2021-06-15T07:27:39Z","snapshot_observed_at":"2026-08-16T18:17:06.574057Z","submitted_at":"2021-06-15T07:27:39Z","title":"Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks","version":1},"cited_work":{"arxiv_id":"2106.07925","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.07925","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Machine learning with electronic health records is vulnerable to backdoor trigger attacks","venue":null,"work_id":"8c55c252-3bea-4de3-bf1c-bcdd8fbbe12e","year":2021},"citing_paper":{"arxiv_id":"2603.26093","last_updated":"2026-04-17T00:02:56Z","snapshot_observed_at":"2026-08-02T11:03:18.306126Z","submitted_at":"2026-03-27T05:47:48Z","title":"ROAST: Risk-aware Outlier-exposure for Adversarial Selective Training of Anomaly Detectors Against Evasion Attacks","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-14T23:24:12.883229Z"},"links":{"cited_paper":"/paper/2106.07925","citing_paper":"/paper/2603.26093"},"observation_digest":"sha256:095245d2ad1b9731f225566c4e9a9e6b90c33ebef1de111e022659b7164d7130","observation_id":"ae20ae7e-437b-4851-98ff-9e0cb437e170","resolution":{"observed_at":"2026-05-14T23:28:17.135737Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2106.07925/citation-record","integrity":"/paper/2106.07925/integrity","json":"/paper/2106.07925/citation-record.json","paper":"/paper/2106.07925"},"outbound":[],"paper":{"arxiv_id":"2106.07925","last_updated":"2021-06-15T07:27:39Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-16T18:17:06.574057Z","submitted_at":"2021-06-15T07:27:39Z","title":"Machine Learning with Electronic Health Records is vulnerable to Backdoor Trigger Attacks"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2106.07925."}