{"as_of":"2026-08-19T05:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:00a2739dda0274fac51409a3c8e38b49a887aaf48fff51c05c5bee6737405442","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T04:36:26.039400Z","state":"measured"},{"denominator":25,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":25,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-18T12:20:41.291944Z","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":"2026-05-18T12:21:21.233481Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"cited_work":{"arxiv_id":"2505.01007","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.01007","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Towards the resistance of neural network watermarking to fine-tuning.arXiv preprint arXiv:2505.01007","venue":null,"work_id":"49b36086-7189-4a3a-9a9f-5f498b235ed6","year":null},"citing_paper":{"arxiv_id":"2509.24496","last_updated":"2026-05-01T14:35:45Z","snapshot_observed_at":"2026-08-14T11:57:19.866501Z","submitted_at":"2025-09-29T09:09:57Z","title":"LLM DNA: Tracing Model Evolution via Functional Representations","version":3},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-18T12:20:41.291944Z"},"links":{"cited_paper":"/paper/2505.01007","citing_paper":"/paper/2509.24496"},"observation_digest":"sha256:24f537d829912c7d04f7a81364035f0f47517dc81018a4756259b0b49d426d61","observation_id":"ca12684f-2fdb-4ace-8971-bc22f2df64ed","resolution":{"observed_at":"2026-05-18T12:21:21.236731Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2505.01007/citation-record","integrity":"/paper/2505.01007/integrity","json":"/paper/2505.01007/citation-record.json","paper":"/paper/2505.01007"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:25.917585Z","title":"Turning your weakness into a strength: Watermarking deep neural networks by backdooring","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.917585Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:f7b8a4d56f4e752e774a67ec01c31cdc2323a561631e96a03641ece42b3a5cec","observation_id":"06a2d160-e701-4baa-9f28-2bccda6c5f32","resolution":{"observed_at":"2026-08-16T04:36:25.917585Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.403095Z","title":"Neural network laundering: Removing black-box backdoor watermarks from deep neural networks","venue":null,"work_id":"8d776d81-908a-42cb-96a8-70a6b099afdf","year":2021},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.925160Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:c359a7b5b1e37820779124f364858553eff58a7f06e4466ead51fe6295a84438","observation_id":"d95d35d9-2fd4-47a6-be23-36488e6a5c7a","resolution":{"observed_at":"2026-08-16T04:36:26.407928Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.386811Z","title":"Certified neural network watermarks with randomized smoothing","venue":null,"work_id":"0f724959-b961-4cd1-a9ce-4e8db2739fd4","year":2022},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.930462Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:10fb6807ee7b30183c6042f524e4fd8efc304344a548db3eb2a1b7e020b9ccaf","observation_id":"44312f7d-e45e-42fd-9fc3-e9943a6e2645","resolution":{"observed_at":"2026-08-16T04:36:26.391977Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.369375Z","title":"One-shot learning of object categories","venue":null,"work_id":"d0e3c1a0-14c3-42cd-bef3-2cbaafe15795","year":2006},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.935347Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:7dace734192b3bc7890724ffa8a2447cc13624d675f22b4f471dd3a1c8653088","observation_id":"5031bf0f-b436-4132-8b4e-9f0180739d39","resolution":{"observed_at":"2026-08-16T04:36:26.375348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:25.941059Z","title":"Functional invariants to watermark large transformers","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.941059Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:7d8bfbd1910e7fb1b5d4173e0839902a65e81bda549966e5338348707f5870ea","observation_id":"15046766-65aa-47de-973e-5b482861c45d","resolution":{"observed_at":"2026-08-16T04:36:25.941059Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:25.946075Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.946075Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:3625bdcd1adf58b662ff6a8ba99a3f3404ccf3853c305271a3632f3962713773","observation_id":"4e8090b0-861c-417f-88c5-0c5ee6ab165d","resolution":{"observed_at":"2026-08-16T04:36:25.946075Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.331766Z","title":"Fundamentals of digital image processing","venue":null,"work_id":"fae343e3-c14f-4382-9a5b-16c046a57c2f","year":1989},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.951723Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:b43c222d8c7b646baae0e99f327c19cba176a2b55f6c84498468c0107f22284d","observation_id":"43c04c02-6ee1-427d-a598-dbb06d43816b","resolution":{"observed_at":"2026-08-16T04:36:26.336775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:25.957053Z","title":"A watermark for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.957053Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:93e481a7f825ce0f79c1d14d71b914c343602fdfb371a6131dfa83076bbc7f4e","observation_id":"b84d7a70-1c74-4866-96b1-945da41b2a02","resolution":{"observed_at":"2026-08-16T04:36:25.957053Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.304464Z","title":"Similarity of neural network representations revisited","venue":null,"work_id":"b97c7813-5468-4e02-b823-d0b82a302c49","year":2019},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.962036Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:eb90d7a680789291e9d6b6e6a2ff6abdad2ef5fc0bc7807334f271ff013bf391","observation_id":"ed651bbf-7581-45d4-af55-b261c80a158c","resolution":{"observed_at":"2026-08-16T04:36:26.309974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"0906.4835","last_updated":"2009-06-26T03:32:32Z","snapshot_observed_at":"2026-08-15T05:45:04.879463Z","submitted_at":"2009-06-26T03:32:32Z","title":"The Complex Gradient Operator and the CR-Calculus","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"0906.4835","snapshot_observed_at":"2026-08-16T04:36:25.967926Z","title":"The complex gradient operator and the cr-calculus","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.967926Z"},"links":{"cited_paper":"/paper/0906.4835","citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:b1cbd884eb971d8ec5498a28d234c42b58345c82c438f279f31e3a8cf976cb15","observation_id":"a79498f4-ad1c-450f-b34d-8a16629cbfb7","resolution":{"observed_at":"2026-08-16T04:36:25.967926Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:25.973619Z","title":"Learning multiple layers of features from tiny images","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.973619Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:ae97196524c58d00a748c007293f084b4c2161b02400ccd007a4d5fdd1acde26","observation_id":"ee7b0e53-693b-4d7f-89d9-af4a2911f5fb","resolution":{"observed_at":"2026-08-16T04:36:25.973619Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:25.978505Z","title":"Imagenet classification with deep convolutional neural networks","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.978505Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:3c58235c23466b3c96880eca6f1e7cc0e7ffbbcf3916cac642609883ae76e230","observation_id":"aea1929a-9892-4b31-842a-9829f06b2571","resolution":{"observed_at":"2026-08-16T04:36:25.978505Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:25.984320Z","title":"Watermarking deep neural networks with greedy residuals","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.984320Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:b264435836f541033a3ca0f5be09c4e87cd7066be18797d06a45d9db3c3c9b2e","observation_id":"daf0748b-95d5-49da-902d-7005d1b10829","resolution":{"observed_at":"2026-08-16T04:36:25.984320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.254732Z","title":"Deep neural network fingerprinting by conferrable adversarial examples","venue":null,"work_id":"3d1fc7a4-f54a-4aae-99ea-33d8b61b1d3d","year":2021},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.989199Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:d3282f6d28cd7cf7468dad9ae560b66031355e189b4cc58ed54f0a4515649218","observation_id":"25177505-fe24-4a1f-a133-81a4a6ff87c8","resolution":{"observed_at":"2026-08-16T04:36:26.260187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.237459Z","title":"Digital watermarking","venue":null,"work_id":"c1b50d32-baf7-4833-a126-bf5d0b143fdf","year":2017},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.994320Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:5834714791503a2fee6bd779231b08cb4549faea7d019b24b2f0f616c6e6432c","observation_id":"87b95d4c-e8b0-4134-adcf-66d7a595c332","resolution":{"observed_at":"2026-08-16T04:36:26.242701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.219989Z","title":"Dimension-independent certified neural network watermarks via mollifier smoothing","venue":null,"work_id":"1ca5ccc0-dc27-405c-a752-b2796e92a706","year":2023},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:25.999203Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:e1ad95b43fe0931acc64a94cd8a385e5e3242e86127efdec2eb05af0c67f3d7d","observation_id":"6c683702-1213-43f2-8249-28c12bb58a9f","resolution":{"observed_at":"2026-08-16T04:36:26.225272Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.202691Z","title":"On the robustness of backdoor-based watermarking in deep neural networks","venue":null,"work_id":"fca3306d-9d6a-41c7-8e85-a2fc5a30c288","year":2021},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:26.003976Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:a159474f08d369071d38039382308f5848de116c60848c86175c3704cfa8e76b","observation_id":"9bb688b1-63d4-427b-9a92-7e2b6e788e3d","resolution":{"observed_at":"2026-08-16T04:36:26.208141Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.185531Z","title":"Deep neural network watermarking against model extraction attack","venue":null,"work_id":"be39cc59-b644-448f-9e0a-d0ea55ddf57f","year":2023},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:26.008690Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:6763205fc3830e96401176e7d791cf841b5448ec65986e03587dac249e545733","observation_id":"b98cbb67-98fa-4e42-a74a-3b10b92ad9da","resolution":{"observed_at":"2026-08-16T04:36:26.190913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.167639Z","title":"Defects of convolutional decoder networks in frequency representation","venue":null,"work_id":"d46890c4-a68c-4797-9bb4-17e5938fc883","year":2023},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:26.013420Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:40b7137d02e833e38dfb35edb4ae92c835a93276bfeb5572b766834f97dbfa06","observation_id":"2b889da6-9330-47ff-b220-7b4e8a3b56a9","resolution":{"observed_at":"2026-08-16T04:36:26.173093Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.019241Z","title":"Embedding watermarks into deep neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:26.019241Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:4b931bc1874db248bbc69e009194e86fd5779dc6d7d81498133f78060cba7017","observation_id":"12f2c8ea-ece0-40ca-a306-9dda472e44b7","resolution":{"observed_at":"2026-08-16T04:36:26.019241Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.137177Z","title":"Watermarking in deep neural networks via error back-propagation","venue":null,"work_id":"16a9d2a5-5878-40fd-936d-0b5f690e905e","year":2020},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:26.024726Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:8404d6f941619507424c03676fab3141ed2d589a160a438b1df65a913e8541e2","observation_id":"207c13e3-4983-4357-aeb7-acdd5bf3707e","resolution":{"observed_at":"2026-08-16T04:36:26.145189Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2401.12255","last_updated":"2024-04-03T06:23:34Z","snapshot_observed_at":"2026-08-16T14:25:49.705409Z","submitted_at":"2024-01-21T09:51:45Z","title":"Instructional Fingerprinting of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.12255","snapshot_observed_at":"2026-08-16T04:36:26.029471Z","title":"Instructional fingerprinting of large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:26.029471Z"},"links":{"cited_paper":"/paper/2401.12255","citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:7870443a874a789ac437bda1d0ade0164068372a3dad73192d57a181560331b3","observation_id":"2f5c1141-88bf-4c85-8f1a-3c625aeb0a79","resolution":{"observed_at":"2026-08-16T04:36:26.029471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T04:36:26.034680Z","title":"Huref: Human-readable fingerprint for large language models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:26.034680Z"},"links":{"citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:4b0bcc61bf76532eb6fc7e930c1097d9b7a5e2f37c27f6e4d685788e1fcee076","observation_id":"912fff5a-a2ee-4496-8f5e-2905a9cbfefb","resolution":{"observed_at":"2026-08-16T04:36:26.034680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.14273","last_updated":"2024-10-18T08:27:02Z","snapshot_observed_at":"2026-08-19T01:34:23.821278Z","submitted_at":"2024-10-18T08:27:02Z","title":"REEF: Representation Encoding Fingerprints for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.14273","snapshot_observed_at":"2026-08-16T04:36:26.039400Z","title":"Reef: Representation encoding fingerprints for large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-16T04:36:26.039400Z"},"links":{"cited_paper":"/paper/2410.14273","citing_paper":"/paper/2505.01007"},"observation_digest":"sha256:04125b62de82d8e7832eb8144e52cf22a11e2bea9e52274ab1e4d3eff90cb69e","observation_id":"92f8e7b5-4432-4920-8de7-63d9e5ad5aaa","resolution":{"observed_at":"2026-08-16T04:36:26.039400Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2505.01007","last_updated":"2025-05-02T05:11:17Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-18T20:14:48.706084Z","submitted_at":"2025-05-02T05:11:17Z","title":"Towards the Resistance of Neural Network Watermarking to Fine-tuning"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":0,"verified_fuzzy":12},"total_outbound_references":24},"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 19 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 1 inbound Pith citation observation for arXiv:2505.01007."}