{"as_of":"2026-08-09T15:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d8228dd39410e215b0e6196b3ad58c56f174217f966f085771cf246b8ac04fe8","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":7,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":7,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":7,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":7,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T23:01:07.362202Z","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":"2026-05-23T08:17:43.726531Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2210.07543","last_updated":"2023-02-10T11:59:31Z","snapshot_observed_at":"2026-08-04T06:56:46.663360Z","submitted_at":"2022-10-14T05:42:39Z","title":"Watermarking Pre-trained Language Models with Backdooring","version":2},"cited_work":{"arxiv_id":"2210.07543","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2210.07543","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Watermarking pre- trained language models with backdooring","venue":null,"work_id":"ce1dd61b-9e58-497e-bded-46cba624264e","year":2022},"citing_paper":{"arxiv_id":"2412.00727","last_updated":"2026-04-07T12:10:40Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-01T08:39:12Z","title":"Perturb and Recover: Fine-tuning for Effective Backdoor Removal from CLIP","version":3},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-23T08:16:53.133986Z"},"links":{"cited_paper":"/paper/2210.07543","citing_paper":"/paper/2412.00727"},"observation_digest":"sha256:86d54409ec9316cd5757893a7da26c14b3ae3f2baa9d827b3bd48fb59a7a21ba","observation_id":"4a10f33a-4c07-44e4-b912-22c5b9305582","resolution":{"observed_at":"2026-05-23T08:17:43.731390Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2210.07543","last_updated":"2023-02-10T11:59:31Z","snapshot_observed_at":"2026-08-04T06:56:46.663360Z","submitted_at":"2022-10-14T05:42:39Z","title":"Watermarking Pre-trained Language Models with Backdooring","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.07543","snapshot_observed_at":"2026-08-06T23:01:07.362202Z","title":"Watermarking pre-trained language models with backdooring","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.20197","last_updated":"2025-06-25T07:37:16Z","snapshot_observed_at":"2026-08-07T22:38:48.008674Z","submitted_at":"2025-06-25T07:37:16Z","title":"Zero-Shot Attribution for Large Language Models: A Distribution Testing Approach","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-06T23:01:07.362202Z"},"links":{"cited_paper":"/paper/2210.07543","citing_paper":"/paper/2506.20197"},"observation_digest":"sha256:6b122467b2b7883de10b6306dfb5feb18ec520510d15e910aa8c7ba58b263049","observation_id":"f056cb75-b59c-4a3d-a54d-6a9b394a09e3","resolution":{"observed_at":"2026-08-06T23:01:07.362202Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.07543","last_updated":"2023-02-10T11:59:31Z","snapshot_observed_at":"2026-08-04T06:56:46.663360Z","submitted_at":"2022-10-14T05:42:39Z","title":"Watermarking Pre-trained Language Models with Backdooring","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.07543","snapshot_observed_at":"2026-08-06T18:33:05.191485Z","title":"Watermarking pre-trained language models with backdooring","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.08288","last_updated":"2025-07-11T03:24:47Z","snapshot_observed_at":"2026-08-09T00:25:43.056231Z","submitted_at":"2025-07-11T03:24:47Z","title":"Invariant-based Robust Weights Watermark for Large Language Models","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-06T18:33:05.191485Z"},"links":{"cited_paper":"/paper/2210.07543","citing_paper":"/paper/2507.08288"},"observation_digest":"sha256:13e0575da08d4bb5f2efa56bdfd1b0159eba8edb8a2a18e76bd0514b50a10b50","observation_id":"f3f7a0f1-d09b-4b12-ae53-4ea515d4f8a1","resolution":{"observed_at":"2026-08-06T18:33:05.191485Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.07543","last_updated":"2023-02-10T11:59:31Z","snapshot_observed_at":"2026-08-04T06:56:46.663360Z","submitted_at":"2022-10-14T05:42:39Z","title":"Watermarking Pre-trained Language Models with Backdooring","version":2},"cited_work":{"arxiv_id":"2210.07543","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2210.07543","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Watermarking pre- trained language models with backdooring","venue":null,"work_id":"ce1dd61b-9e58-497e-bded-46cba624264e","year":2022},"citing_paper":{"arxiv_id":"2508.11548","last_updated":"2026-04-07T07:06:44Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-08-15T15:50:20Z","title":"Copyright Protection for Large Language Models: A Survey of Methods, Challenges, and Trends","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-18T22:45:31.935618Z"},"links":{"cited_paper":"/paper/2210.07543","citing_paper":"/paper/2508.11548"},"observation_digest":"sha256:a016e02c8a3cef802341a1c3e2b7c900feb81324c2c2d3c4c82447306aceef8d","observation_id":"6ba644b4-508d-4335-b94b-ecda4a386530","resolution":{"observed_at":"2026-05-18T22:46:53.235656Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2210.07543","last_updated":"2023-02-10T11:59:31Z","snapshot_observed_at":"2026-08-04T06:56:46.663360Z","submitted_at":"2022-10-14T05:42:39Z","title":"Watermarking Pre-trained Language Models with Backdooring","version":2},"cited_work":{"arxiv_id":"2210.07543","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2210.07543","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Watermarking pre- trained language models with backdooring","venue":null,"work_id":"ce1dd61b-9e58-497e-bded-46cba624264e","year":2022},"citing_paper":{"arxiv_id":"2605.04305","last_updated":"2026-05-05T21:13:30Z","snapshot_observed_at":"2026-08-02T12:48:52.880246Z","submitted_at":"2026-05-05T21:13:30Z","title":"SWAN: Semantic Watermarking with Abstract Meaning Representation","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-05-08T17:00:12.024370Z"},"links":{"cited_paper":"/paper/2210.07543","citing_paper":"/paper/2605.04305"},"observation_digest":"sha256:2e99157e4516303f6f904e2031b6c9b672e726f9a112c79e2579509c66b61319","observation_id":"1d784b85-3214-494a-a428-35f8d2bf5897","resolution":{"observed_at":"2026-05-11T17:51:09.588132Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2210.07543","last_updated":"2023-02-10T11:59:31Z","snapshot_observed_at":"2026-08-04T06:56:46.663360Z","submitted_at":"2022-10-14T05:42:39Z","title":"Watermarking Pre-trained Language Models with Backdooring","version":2},"cited_work":{"arxiv_id":"2210.07543","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2210.07543","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Watermarking pre- trained language models with backdooring","venue":null,"work_id":"ce1dd61b-9e58-497e-bded-46cba624264e","year":2022},"citing_paper":{"arxiv_id":"2605.18474","last_updated":"2026-05-19T08:19:47Z","snapshot_observed_at":"2026-07-06T23:29:20.279470Z","submitted_at":"2026-05-18T14:30:32Z","title":"Prompt2Fingerprint: Plug-and-Play LLM Fingerprinting via Text-to-Weight Generation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-20T09:34:59.995475Z"},"links":{"cited_paper":"/paper/2210.07543","citing_paper":"/paper/2605.18474"},"observation_digest":"sha256:3487ab3312db6043ac2a9082d90878a8c4c0f334ea4a43a3ae7c860e8859d67a","observation_id":"5551e841-70e8-45e0-a984-1160472c8db7","resolution":{"observed_at":"2026-05-20T09:38:10.903472Z","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"}},{"citation":{"cited_paper":{"arxiv_id":"2210.07543","last_updated":"2023-02-10T11:59:31Z","snapshot_observed_at":"2026-08-04T06:56:46.663360Z","submitted_at":"2022-10-14T05:42:39Z","title":"Watermarking Pre-trained Language Models with Backdooring","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.07543","snapshot_observed_at":"2026-08-02T14:19:36.147773Z","title":"Wa- termarking pre-trained language models with backdooring.arXiv preprint arXiv:2210.07543, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.20440","last_updated":"2026-05-12T04:36:20Z","snapshot_observed_at":"2026-08-05T02:51:39.347998Z","submitted_at":"2026-05-12T04:36:20Z","title":"Answer-then-Edit: Reasoning Skeleton Editing for Anti-Distillation with Preserved Utility","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-02T14:19:36.147773Z"},"links":{"cited_paper":"/paper/2210.07543","citing_paper":"/paper/2607.20440"},"observation_digest":"sha256:8ed80302568c428cdfd4e1707ee14a4bdef7b1a593e448cdb343dcf30521d7ec","observation_id":"fb7c27ed-89f1-43e4-ac59-e76c4764d945","resolution":{"observed_at":"2026-08-02T14:19:36.147773Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2210.07543/citation-record","integrity":"/paper/2210.07543/integrity","json":"/paper/2210.07543/citation-record.json","paper":"/paper/2210.07543"},"outbound":[],"paper":{"arxiv_id":"2210.07543","last_updated":"2023-02-10T11:59:31Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-04T06:56:46.663360Z","submitted_at":"2022-10-14T05:42:39Z","title":"Watermarking Pre-trained Language Models with Backdooring"},"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 7 inbound Pith citation observations for arXiv:2210.07543."}