{"as_of":"2026-08-11T01:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8038d95d3d4f679cecd897296a32b49c72cd7d29e8937261d633098f1bf746a6","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":5,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":5,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":5,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":5,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T12:55:02.423410Z","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":"2026-07-02T13:46:59.650105Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2309.10544","last_updated":"2023-09-19T11:45:29Z","snapshot_observed_at":"2026-08-09T01:33:37.759144Z","submitted_at":"2023-09-19T11:45:29Z","title":"Model Leeching: An Extraction Attack Targeting LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.10544","snapshot_observed_at":"2026-08-09T12:55:02.423410Z","title":"Model leeching: An extraction attack targeting llms","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.05213","last_updated":"2025-08-03T03:58:10Z","snapshot_observed_at":"2026-08-09T12:49:06.723073Z","submitted_at":"2025-02-04T11:23:49Z","title":"DERMARK: A Dynamic, Efficient and Robust Multi-bit Watermark for Large Language Models","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-09T12:55:02.423410Z"},"links":{"cited_paper":"/paper/2309.10544","citing_paper":"/paper/2502.05213"},"observation_digest":"sha256:f6d8e11b3ad06922f3ea7a540b1dc471470e06eb2cc8c11038300bee91dbdeff","observation_id":"3a69a0b3-abf8-4a6c-9e65-ebd0b02b1853","resolution":{"observed_at":"2026-08-09T12:55:02.423410Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.10544","last_updated":"2023-09-19T11:45:29Z","snapshot_observed_at":"2026-08-09T01:33:37.759144Z","submitted_at":"2023-09-19T11:45:29Z","title":"Model Leeching: An Extraction Attack Targeting LLMs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.10544","snapshot_observed_at":"2026-08-06T22:23:07.300309Z","title":"arXiv preprint arXiv:2309.10544 (2023)","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.22521","last_updated":"2025-06-26T22:02:01Z","snapshot_observed_at":"2026-08-07T22:00:37.560675Z","submitted_at":"2025-06-26T22:02:01Z","title":"A Survey on Model Extraction Attacks and Defenses for Large Language Models","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-06T22:23:07.300309Z"},"links":{"cited_paper":"/paper/2309.10544","citing_paper":"/paper/2506.22521"},"observation_digest":"sha256:1f6a32e002aa781a636e6738b98e5093b3e0c79f575b021d50c6abd507944abc","observation_id":"73b10eb1-71ed-441d-88f6-30ce08ce716d","resolution":{"observed_at":"2026-08-06T22:23:07.300309Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.10544","last_updated":"2023-09-19T11:45:29Z","snapshot_observed_at":"2026-08-09T01:33:37.759144Z","submitted_at":"2023-09-19T11:45:29Z","title":"Model Leeching: An Extraction Attack Targeting LLMs","version":1},"cited_work":{"arxiv_id":"2309.10544","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.10544","snapshot_observed_at":"2026-07-02T13:46:59.650105Z","title":"arXiv preprint arXiv:2309.10544 , year =","venue":null,"work_id":"10855c9b-8034-4221-8f4f-de7c695f911d","year":2023},"citing_paper":{"arxiv_id":"2512.22753","last_updated":"2026-04-22T21:48:07Z","snapshot_observed_at":"2026-08-08T22:14:34.218223Z","submitted_at":"2025-12-28T02:55:49Z","title":"From Rookie to Expert: Manipulating LLMs for Automated Vulnerability Exploitation in Enterprise Software","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-16T20:02:47.746439Z"},"links":{"cited_paper":"/paper/2309.10544","citing_paper":"/paper/2512.22753"},"observation_digest":"sha256:22b69a4f1004759128f7fba9d73b59bc166ffdec0e3175cb515910c838f65405","observation_id":"3ca130f7-cf81-4ff7-bca1-729d12bf1e73","resolution":{"observed_at":"2026-05-16T20:03:22.216172Z","resolver_source":"arxiv_id","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":"2309.10544","last_updated":"2023-09-19T11:45:29Z","snapshot_observed_at":"2026-08-09T01:33:37.759144Z","submitted_at":"2023-09-19T11:45:29Z","title":"Model Leeching: An Extraction Attack Targeting LLMs","version":1},"cited_work":{"arxiv_id":"2309.10544","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.10544","snapshot_observed_at":"2026-07-02T13:46:59.650105Z","title":"arXiv preprint arXiv:2309.10544 , year =","venue":null,"work_id":"10855c9b-8034-4221-8f4f-de7c695f911d","year":2023},"citing_paper":{"arxiv_id":"2606.05725","last_updated":"2026-06-04T05:33:49Z","snapshot_observed_at":"2026-08-07T05:54:31.269699Z","submitted_at":"2026-06-04T05:33:49Z","title":"An Embarrassingly Simple Detector for Model Extraction Attacks in Large Language Model API Traffic","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-06-28T00:59:14.347069Z"},"links":{"cited_paper":"/paper/2309.10544","citing_paper":"/paper/2606.05725"},"observation_digest":"sha256:7e2b0a095de494f51dc4e0d9b95b441806f9429b459bbf49b69bc6afb79d9d13","observation_id":"a7f0a8dc-0324-41b5-b1c4-b932b4150b68","resolution":{"observed_at":"2026-07-02T13:46:59.651681Z","resolver_source":"arxiv_id","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":"2309.10544","last_updated":"2023-09-19T11:45:29Z","snapshot_observed_at":"2026-08-09T01:33:37.759144Z","submitted_at":"2023-09-19T11:45:29Z","title":"Model Leeching: An Extraction Attack Targeting LLMs","version":1},"cited_work":{"arxiv_id":"2309.10544","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2309.10544","snapshot_observed_at":"2026-07-02T13:46:59.650105Z","title":"arXiv preprint arXiv:2309.10544 , year =","venue":null,"work_id":"10855c9b-8034-4221-8f4f-de7c695f911d","year":2023},"citing_paper":{"arxiv_id":"2606.27948","last_updated":"2026-06-26T10:44:01Z","snapshot_observed_at":"2026-08-06T08:37:01.227511Z","submitted_at":"2026-06-26T10:44:01Z","title":"RECAST: Model Reconstruction via Counterfactual-Aware Wasserstein Geometry under Limited Data","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-06-29T05:16:50.471967Z"},"links":{"cited_paper":"/paper/2309.10544","citing_paper":"/paper/2606.27948"},"observation_digest":"sha256:77b1c189c3736f1edfe61d4e7bf9982f53cd54f6a80e4d1e512225eb7358126f","observation_id":"fde6ccbc-4cd0-4a6d-a098-eae3c262c79a","resolution":{"observed_at":"2026-06-29T17:33:45.652128Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2309.10544/citation-record","integrity":"/paper/2309.10544/integrity","json":"/paper/2309.10544/citation-record.json","paper":"/paper/2309.10544"},"outbound":[],"paper":{"arxiv_id":"2309.10544","last_updated":"2023-09-19T11:45:29Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T01:33:37.759144Z","submitted_at":"2023-09-19T11:45:29Z","title":"Model Leeching: An Extraction Attack Targeting LLMs"},"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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 11 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 5 inbound Pith citation observations for arXiv:2309.10544."}