{"as_of":"2026-08-19T22:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ab8dba80f1aacfc28eb45207570192c9dd32baeae9a4630f453d7ded1cf79379","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:22:21.596838Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2507.18372/citation-record","integrity":"/paper/2507.18372/integrity","json":"/paper/2507.18372/citation-record.json","paper":"/paper/2507.18372"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:22:22.030653Z","title":"Differentially private simple linear regression","venue":null,"work_id":"3bcf8b92-c032-4e25-8367-941015f1b67a","year":2022},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.459738Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:4bf44613d5655c3a10c6411f299581cad10f682877c09a9af0b72a1de82d3592","observation_id":"33855ecf-4da4-45a6-ae1b-7a264501eecc","resolution":{"observed_at":"2026-08-15T18:22:22.034950Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:22.017342Z","title":"Reconstructing training data with informed adversaries","venue":null,"work_id":"e24bdef6-772e-4c8f-ba61-f3edc7629f41","year":2022},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.464204Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:567d0f011b1cd186df7586724696b8aee1412f4003334ad42731c7f6521fe147","observation_id":"353b8a51-0e06-4084-902f-f4ccc1de80c6","resolution":{"observed_at":"2026-08-15T18:22:22.022072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:22.000872Z","title":null,"venue":null,"work_id":"040f9cbd-444e-4b0a-bd92-1a35b03a16b3","year":1994},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.468379Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:e234d154c72c6d2c2759d2aea0f8ca3267075c292062e0deb8fa2ba5c22b701b","observation_id":"8bca615c-f0bf-4f31-88fe-1082e79e7f6b","resolution":{"observed_at":"2026-08-15T18:22:22.005731Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.987670Z","title":"and Sheldon, D","venue":null,"work_id":"d88b9564-7145-47a2-94ea-5d3b430b2864","year":2019},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.473077Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:8ced54383f385654329bc8c7b1c498e900659292d8206db8fc988ea00f040a89","observation_id":"40eecf5e-6ed0-4a26-8ddd-eacc37dc0ff4","resolution":{"observed_at":"2026-08-15T18:22:21.992225Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.973601Z","title":"and Ramamoorthi, R","venue":null,"work_id":"d00761e5-ccf7-4127-9712-7cfee281dc42","year":1982},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.477664Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:ecfdd64b703b248425f29c3f6d2dc0f1b75216677f29ef27b1559e3324011e68","observation_id":"b5b52c8d-7cab-44fb-9e9a-8170b52e3e7f","resolution":{"observed_at":"2026-08-15T18:22:21.978197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01827","last_updated":"2023-11-02T20:05:44Z","snapshot_observed_at":"2026-08-16T15:18:47.260710Z","submitted_at":"2023-07-04T17:09:49Z","title":"Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.01827","snapshot_observed_at":"2026-08-15T18:22:21.482717Z","title":"Deconstructing data reconstruction: Multiclass, weight decay and general losses","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.482717Z"},"links":{"cited_paper":"/paper/2307.01827","citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:c80ae71a87b38a672ea416c9c41470b3114bf33925367dbd8a33c13661f8db79","observation_id":"117a6642-c722-4af4-a06e-fc2ab04b43e4","resolution":{"observed_at":"2026-08-15T18:22:21.482717Z","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":"2026-08-15T18:22:21.961317Z","title":"and Berger, R","venue":null,"work_id":"371d7a22-4e2a-4708-8a20-47dea927fec4","year":2024},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.488756Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:c77b322e5c9bb2a856e7e42e09b752db83eb18b9417837e773815c973c208bb9","observation_id":"de3ca582-3d26-4ccd-98b6-96818fa41d95","resolution":{"observed_at":"2026-08-15T18:22:21.964714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.950552Z","title":"and Steinwart, I","venue":null,"work_id":"383ce4ce-b0ef-4c07-a94e-cb7d485fd9f0","year":2008},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.493905Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:4e9b82a9ce381cd4f7cedb643e0ca4dff420467bbee722bb739f9469be2a4637","observation_id":"552c35f7-1275-46ec-a187-188bdbda0c04","resolution":{"observed_at":"2026-08-15T18:22:21.954010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.939157Z","title":"Exposed! a survey of attacks on private data","venue":null,"work_id":"294cb9bf-054f-4377-906a-30642aa2135b","year":2017},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.499169Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:b9a737bdd4c831378064d518a59a75e95a8edee5fc604f8c64eda21fcaaaef54","observation_id":"1410b380-2fc7-4ef8-b102-2bbdc26fe080","resolution":{"observed_at":"2026-08-15T18:22:21.943137Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.927269Z","title":"and Hill, J","venue":null,"work_id":"8f8b0caf-f9c3-4f5e-93bc-cbf05d69ad51","year":2006},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.505362Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:467f75b9a71dea0d42673052c5003b98c5a58f27aa80dc192bc9c0046062f9a7","observation_id":"5711b260-b454-45a4-aedb-b50ebfa44dd6","resolution":{"observed_at":"2026-08-15T18:22:21.931228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.915553Z","title":null,"venue":null,"work_id":"8119329c-cba2-4fe6-aafa-2766f260d046","year":2018},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.510781Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:abf0343c0fbc7bd0eb174a0029125c00d68f8d6d00677be851eaedee03192ad4","observation_id":"06af37e7-7ed1-4083-aa4b-68fce4c8773a","resolution":{"observed_at":"2026-08-15T18:22:21.919208Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.515834Z","title":"M., Rasch, M","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.515834Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:5a9053750595d0acdcd9625b0d0e3a2eae5dfadaa1b5211ce2bfab020da10e87","observation_id":"0a8c9bfe-972f-4d1f-9591-05b14fc7bc70","resolution":{"observed_at":"2026-08-15T18:22:21.515834Z","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":"2026-08-15T18:22:21.894568Z","title":"Bounding training data reconstruction in private (deep) learning","venue":null,"work_id":"8e8e2a80-3510-4b6a-9b81-7cdb3f861f25","year":2022},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.520433Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:3628320328c2a25c1a6bc81e5eda645316e2169dc5c1aa4935599014f119697c","observation_id":"999ae3c9-811f-4346-8ec7-7fdc6643851d","resolution":{"observed_at":"2026-08-15T18:22:21.898575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.882582Z","title":"Reconstructing training data from trained neural networks","venue":null,"work_id":"338484a4-c124-4ce9-a215-a4099cb0f813","year":2022},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.524328Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:ffe9b559502a190d7df213d7dc9c280a41b41119bd394159edd8d2b24b67e19b","observation_id":"6420bd97-5660-4c06-975e-4a1a221d9891","resolution":{"observed_at":"2026-08-15T18:22:21.886517Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.07225","last_updated":"2023-10-30T10:12:11Z","snapshot_observed_at":"2026-08-16T15:55:21.950937Z","submitted_at":"2023-02-14T18:02:34Z","title":"Bounding Training Data Reconstruction in DP-SGD","version":3},"cited_work":{"arxiv_id":"2302.07225","doi":null,"metadata_source":"pith","pith_arxiv_id":"2302.07225","snapshot_observed_at":"2026-08-15T18:22:21.679067Z","title":"Bounding Training Data Reconstruction in DP-SGD","venue":"cs.CR","work_id":"cffb09e4-4de8-4034-bd94-7263bbc852ef","year":2023},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.528494Z"},"links":{"cited_paper":"/paper/2302.07225","citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:825625e9bf569d0869905791c5517d9222b845653ef1e232ef823e827275fca2","observation_id":"7a39b92c-691e-43f9-bf74-2648d68103a3","resolution":{"observed_at":"2026-08-15T18:22:21.685394Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.532660Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.532660Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:97683525a585efabcba628bbceaa2591a7da0481aaae583d189b347a87d5a96f","observation_id":"0d137f1f-3d8d-42b9-b910-b67fa8d52e81","resolution":{"observed_at":"2026-08-15T18:22:21.532660Z","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":"2026-08-15T18:22:21.536357Z","title":"Estimation of non-normalized statistical models by score matching","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.536357Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:c1f54528757a08c5f87d138b7bf831945e114797b9e97f9c1400f188acb8d592","observation_id":"b169b1a1-1136-47a6-beea-afdb5b3deffe","resolution":{"observed_at":"2026-08-15T18:22:21.536357Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.03928","last_updated":"2023-07-08T08:02:47Z","snapshot_observed_at":"2026-08-16T22:27:26.454258Z","submitted_at":"2023-07-08T08:02:47Z","title":"Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.03928","snapshot_observed_at":"2026-08-15T18:22:21.539582Z","title":"Bounding data reconstruction attacks with the hypothesis testing interpretation of differential privacy","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.539582Z"},"links":{"cited_paper":"/paper/2307.03928","citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:0415a362ec8f478ba5759fbf1607b9cd63c4762ee27490b2cb8ffa10f179bea4","observation_id":"cebbb96b-f3bf-4011-a865-66a515f45cd8","resolution":{"observed_at":"2026-08-15T18:22:21.539582Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.01428","last_updated":"2023-11-09T21:07:22Z","snapshot_observed_at":"2026-08-16T15:58:04.140766Z","submitted_at":"2023-02-02T21:41:59Z","title":"Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.01428","snapshot_observed_at":"2026-08-15T18:22:21.543176Z","title":"Understanding reconstruction attacks with the neural tangent kernel and dataset distillation","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.543176Z"},"links":{"cited_paper":"/paper/2302.01428","citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:fafb3e0bb407bf6d7c6c0d05c2258f32a79165c51049d111b9e385d8b5787c52","observation_id":"892a0039-8b30-4186-b792-de790f370563","resolution":{"observed_at":"2026-08-15T18:22:21.543176Z","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":"2026-08-15T18:22:21.856168Z","title":"posteriordb: a set of posteriors for Bayesian inference and probabilistic programming , October 2023","venue":null,"work_id":"8104b865-8799-4aa8-b89b-cdd0690112e5","year":2023},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.546759Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:99a80939d6d3a20780ab400f9ab41aa3a84b589aaa2518562888bf1090cc2e6f","observation_id":"c7b85a6b-f942-494b-9e4a-1a0045894f27","resolution":{"observed_at":"2026-08-15T18:22:21.860152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.843194Z","title":"Bayesian pseudocoresets","venue":null,"work_id":"7a87e7c3-fc19-419d-972b-3bbeaca84952","year":2020},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.549952Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:ff98e5576f7ef4f210318e921d1fa70a41aa5d927a1b3ff73f1441eb59ccb813","observation_id":"c4778b2f-5f47-4428-b473-14ed6ebd9096","resolution":{"observed_at":"2026-08-15T18:22:21.847194Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.830257Z","title":"Kernel mean embedding of distributions: A review and beyond","venue":null,"work_id":"e0631754-108c-445c-8a12-ad03425f7f55","year":2017},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.552936Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:b4e456448c7025b52dd2eae606283ad552790f155facecd1a1be580eb622be13","observation_id":"65fd2c98-4ebf-42fc-b69e-f8ec1d5a530c","resolution":{"observed_at":"2026-08-15T18:22:21.834576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.817647Z","title":"How to dp-fy ml: A practical tutorial to machine learning with differential privacy","venue":null,"work_id":"5f8c4055-108f-4afa-aba0-24cab568c045","year":2023},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.556084Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:9bd26d696625cd7d8c3fe77b335be5311f51226f1c55f9a4134b6d3d5cfcb7c7","observation_id":"cf0c2389-424c-4311-9fdc-79797e5222fd","resolution":{"observed_at":"2026-08-15T18:22:21.822120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.559478Z","title":"High-resolution image synthesis with latent diffusion models","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.559478Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:343e1509138f5021e9f487fcf3ce400fd8272f7c1e5d5560a8fbaf85b508a3be","observation_id":"778326b6-fb01-4d2c-93a9-2290fe37c743","resolution":{"observed_at":"2026-08-15T18:22:21.559478Z","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":"2026-08-15T18:22:21.796542Z","title":"V., Geiping, J., Schönlieb, C.-B., and Moeller, M","venue":null,"work_id":"1271adf2-cbc4-4b02-9de6-e88d63622391","year":2024},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.562633Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:a321fc3c2a128c22eed03230afd8697ac1baf064f6f77f39807b22bfe4c74eab","observation_id":"1291db9d-181b-4eea-b215-47340e59c908","resolution":{"observed_at":"2026-08-15T18:22:21.800596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.785985Z","title":"and McAuley, J","venue":null,"work_id":"a98e3a51-8a97-4bb4-be97-6a244d2612e5","year":2023},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.565707Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:d702164fab92f09c1c21c1262e8d6c67ef2801ae0ad6646beaef805b12925b08","observation_id":"2b14bb74-9eb4-40af-8714-211aef852194","resolution":{"observed_at":"2026-08-15T18:22:21.789683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.775556Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":"a162ea80-f473-4af2-b1ac-2f48ae89499f","year":2017},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.568690Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:66b008fac9dad81157b4c15a5613ff6281d29fbb580b18be82efbf98bd3d33f2","observation_id":"f1f2c2ca-2ab7-405c-bcd9-6fb04c1b3e69","resolution":{"observed_at":"2026-08-15T18:22:21.778758Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.764456Z","title":"and Ermon, S","venue":null,"work_id":"2d484e91-1f30-4f89-896c-12973020a4d8","year":2020},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.572584Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:23066dc211b07e4d9a4cc621aa7c43bbcddfd7db01871d125a25a6d91be9986a","observation_id":"ebbc4ca8-6892-4683-a64e-bb934ff90eb0","resolution":{"observed_at":"2026-08-15T18:22:21.768220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.576344Z","title":"Sliced score matching: A scalable approach to density and score estimation","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.576344Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:95d3264c2b4fb67a5cf208a8fe59b9e4d8851f1d3e8817512b83e9900a7bf75e","observation_id":"e6d1ee05-b0ac-49c8-a767-3c45c5092b3a","resolution":{"observed_at":"2026-08-15T18:22:21.576344Z","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":"2026-08-15T18:22:21.745059Z","title":"K., Fukumizu, K., and Lanckriet, G","venue":null,"work_id":"9a4efc29-e603-41ca-9ae4-2c9f7acd6268","year":2011},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.580391Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:1b33c16288f59db6d4cff83d4ba11cf400b6e4f82a6f6258a295deca1dc027f1","observation_id":"8641baec-d814-4674-9f33-49edb5a4cc94","resolution":{"observed_at":"2026-08-15T18:22:21.748843Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.732508Z","title":"An explicit description of the reproducing kernel hilbert spaces of gaussian rbf kernels","venue":null,"work_id":"65318bcb-2334-4bcf-ab36-5bf486595315","year":2006},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.584175Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:f2ec4645ca583f7306a10e353ebd8442fb2fcd2a8a07ce0a9ccd771f8ff7c437","observation_id":"f7b2553c-7a8d-4819-8a4d-c3dea909634f","resolution":{"observed_at":"2026-08-15T18:22:21.736962Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.11251","last_updated":"2023-04-21T21:03:01Z","snapshot_observed_at":"2026-08-19T03:28:16.037299Z","submitted_at":"2023-04-21T21:03:01Z","title":"Machine Learning and the Future of Bayesian Computation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.11251","snapshot_observed_at":"2026-08-15T18:22:21.588293Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.588293Z"},"links":{"cited_paper":"/paper/2304.11251","citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:6ea530d5a953b7f41225c5fcf13d5beebcc31f69cfe524e5ba03fb564134c14d","observation_id":"eae20397-f889-4209-8d9b-4359dcd72f9c","resolution":{"observed_at":"2026-08-15T18:22:21.588293Z","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":"2026-08-15T18:22:21.719824Z","title":"Bayes hilbert spaces for posterior approximation","venue":null,"work_id":"cd259d67-ee08-4efc-b451-a1f99fe31bf7","year":2023},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.592810Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:441482b535bd2346cd4de2c33d2700b6bea56af64d8498e9545148c36d6e019e","observation_id":"a026b754-3869-418d-8b66-e938d4583bb8","resolution":{"observed_at":"2026-08-15T18:22:21.724080Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-15T18:22:21.707734Z","title":"Deep leakage from gradients","venue":null,"work_id":"6e19371a-0632-44e7-b591-8c2e81914c37","year":2019},"citing_paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-15T18:22:21.596838Z"},"links":{"citing_paper":"/paper/2507.18372"},"observation_digest":"sha256:fb01110722e371580ac997d032d38c4fc9fade1cde3f47a18c8b9d211793339d","observation_id":"6fa075e6-5d1e-4f42-99fe-e0ac10258f04","resolution":{"observed_at":"2026-08-15T18:22:21.711427Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.18372","last_updated":"2025-07-24T12:49:41Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-18T10:47:22.890943Z","submitted_at":"2025-07-24T12:49:41Z","title":"On Reconstructing Training Data From Bayesian Posteriors and Trained Models"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":11,"verified_exact":1,"verified_fuzzy":22},"total_outbound_references":34},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 0 inbound Pith citation observations for arXiv:2507.18372."}