{"as_of":"2026-08-09T17:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c37e21a605c4a5977eb8c8b250cf4c35f6e566f298179710f4961ab251f4a2a9","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":"2026-08-09T06:31:02.800959+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":"2026-08-05T18:12:36.532173Z","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":"2026-05-20T16:58:41.198048Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2207.13321","last_updated":"2022-07-27T06:49:39Z","snapshot_observed_at":"2026-07-06T13:35:47.057503Z","submitted_at":"2022-07-27T06:49:39Z","title":"DynaMarks: Defending Against Deep Learning Model Extraction Using Dynamic Watermarking","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2207.13321","snapshot_observed_at":"2026-08-05T18:12:36.532173Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.15031","last_updated":"2025-08-27T05:10:26Z","snapshot_observed_at":"2026-08-06T09:22:49.031430Z","submitted_at":"2025-08-20T19:49:59Z","title":"A Systematic Survey of Model Extraction Attacks and Defenses: State-of-the-Art and Perspectives","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T18:12:36.532173Z"},"links":{"cited_paper":"/paper/2207.13321","citing_paper":"/paper/2508.15031"},"observation_digest":"sha256:81249faf02f4a949a700e407e2af4931abba16f127a652e83a7fb6cc406e6310","observation_id":"40670c1c-329b-4802-9b1f-d11379400cad","resolution":{"observed_at":"2026-08-05T18:12:36.532173Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2207.13321","last_updated":"2022-07-27T06:49:39Z","snapshot_observed_at":"2026-07-06T13:35:47.057503Z","submitted_at":"2022-07-27T06:49:39Z","title":"DynaMarks: Defending Against Deep Learning Model Extraction Using Dynamic Watermarking","version":1},"cited_work":{"arxiv_id":"2207.13321","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2207.13321","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"DynaMarks: Defending against deep learn- ing model extraction using dynamic watermarking","venue":null,"work_id":"732bbf8b-0905-47bf-a73f-a571e372b188","year":2022},"citing_paper":{"arxiv_id":"2605.16227","last_updated":"2026-05-15T17:38:06Z","snapshot_observed_at":"2026-07-29T16:12:51.400715Z","submitted_at":"2026-05-15T17:38:06Z","title":"LymphNode: A Plug-and-Play Access Control Method for Deep Neural Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-20T16:58:04.893296Z"},"links":{"cited_paper":"/paper/2207.13321","citing_paper":"/paper/2605.16227"},"observation_digest":"sha256:e904b6f5470eb7df56bab42cc4812b238d3200d3e093fe32318f549754c12d42","observation_id":"4457e9af-7ef7-4b42-b2d7-d82a589a2e43","resolution":{"observed_at":"2026-05-20T16:58:41.200533Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2207.13321/citation-record","integrity":"/paper/2207.13321/integrity","json":"/paper/2207.13321/citation-record.json","paper":"/paper/2207.13321"},"outbound":[],"paper":{"arxiv_id":"2207.13321","last_updated":"2022-07-27T06:49:39Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-07-06T13:35:47.057503Z","submitted_at":"2022-07-27T06:49:39Z","title":"DynaMarks: Defending Against Deep Learning Model Extraction Using Dynamic Watermarking"},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2207.13321."}