{"as_of":"2026-08-13T06:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d6d470f47778acc045380f7c5b7bde7b5b47d5968f2376dae75210390dffdead","coverage":[{"denominator":30,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":30,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T11:04:07.916608Z","state":"measured"},{"denominator":30,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":30,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-13T06:32:02.005865+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/2411.18746/citation-record","integrity":"/paper/2411.18746/integrity","json":"/paper/2411.18746/citation-record.json","paper":"/paper/2411.18746"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T11:04:08.375133Z","title":"A survey of privacy attacks in machine learning,","venue":null,"work_id":"8f95b243-caad-4797-8882-fdbd66f4331a","year":2023},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.788509Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:9e89526a2b0b25d6634b1b984a0b83d5d886401f81034adf83dc76af8f7ff13e","observation_id":"20b207b4-2fc5-46e3-aca9-51316dd8b20a","resolution":{"observed_at":"2026-08-12T11:04:08.378653Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:04:07.793609Z","title":"The algorithmic foundations of differential privacy,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.793609Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:444f3dbeb6af035e345b4e26de0e2c3f4fc9d8d9833f9cae13abea40c2d5561d","observation_id":"c69ecf44-a55e-4ac3-9274-fa5fe2c83c7b","resolution":{"observed_at":"2026-08-12T11:04:07.793609Z","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":"2026-08-12T11:04:07.797966Z","title":"Deep learning with differential privacy,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.797966Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:bf3fbefb155c9450e7cb1692473d50fd74c560649b0b3b5a722b958e275f8714","observation_id":"79813d95-5e4c-4221-9133-9aad5ab29b2a","resolution":{"observed_at":"2026-08-12T11:04:07.797966Z","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":"2026-08-12T11:04:08.350932Z","title":"Deep learning with label differential privacy,","venue":null,"work_id":"87b34971-1485-4c81-ae64-dee02e6af95f","year":2021},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.802736Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:f20e1eb9f10cd6f12055b1d26ae19494619a293823a466ab5b11554555ca9052","observation_id":"d5190238-f562-4d98-b1ba-52745b74fa4e","resolution":{"observed_at":"2026-08-12T11:04:08.354853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:04:08.339802Z","title":"Survey: Leakage and privacy at inference time,","venue":null,"work_id":"1a895d57-1e9f-4ef5-8e5f-fa233ac6c87a","year":2022},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.806699Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:fd06b34c7a39524b7d765085877ddd7a8bc84be1afcb931aa25c9c5499809a29","observation_id":"c7934cb1-5ecb-4ffa-af56-4aef4760258e","resolution":{"observed_at":"2026-08-12T11:04:08.343829Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:04:08.328385Z","title":"Managing your private and public data: Bringing down inference attacks against your privacy,","venue":null,"work_id":"0499e9e3-fb08-4ad6-9b21-5dbee9ba08b4","year":2015},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.810636Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:847e962d057a34d1fab06e38132776ae3c87fc366122c5ed0e94c40f91b68ff9","observation_id":"ec7d1b32-a975-4b97-95bf-0e4da0275dff","resolution":{"observed_at":"2026-08-12T11:04:08.332293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.04223","last_updated":"2024-10-01T13:18:41Z","snapshot_observed_at":"2026-07-06T14:28:17.748673Z","submitted_at":"2022-12-08T12:05:50Z","title":"Vicious Classifiers: Assessing Inference-time Data Reconstruction Risk in Edge Computing","version":3},"cited_work":{"arxiv_id":"2212.04223","doi":null,"metadata_source":"pith","pith_arxiv_id":"2212.04223","snapshot_observed_at":"2026-08-12T11:04:08.049921Z","title":"Vicious Classifiers: Assessing Inference-time Data Reconstruction Risk in Edge Computing","venue":"cs.LG","work_id":"9f946a18-54ac-4b27-a077-c349b01cad47","year":2022},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.814852Z"},"links":{"cited_paper":"/paper/2212.04223","citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:cc413e28efe1aa2b4eb45b2e667d0254140bdc4be894bbf0e7f539e1ccd61b6a","observation_id":"9bca1ad8-b825-4404-9f73-f8e20f7f5edd","resolution":{"observed_at":"2026-08-12T11:04:08.054582Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:04:07.819294Z","title":"Local privacy and statistical minimax rates,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.819294Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:01ef2c4b71407128904656e082d275764b6b5410691338a472d5fb53ac5e6c87","observation_id":"3f62b9f3-50ed-4331-8848-b4310ee61ef8","resolution":{"observed_at":"2026-08-12T11:04:07.819294Z","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":"2026-08-12T11:04:07.823207Z","title":"What can we learn privately?","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.823207Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:d23ecd553d8123eb33f0fe536440b661901c9862f50437ae5323c01bbd215939","observation_id":"1c97deef-4293-4269-a3bf-3d427fbbd2d4","resolution":{"observed_at":"2026-08-12T11:04:07.823207Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1807.01860","last_updated":"2018-07-13T02:50:37Z","snapshot_observed_at":"2026-07-06T06:48:29.164157Z","submitted_at":"2018-07-05T06:21:48Z","title":"Privacy-preserving Machine Learning through Data Obfuscation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1807.01860","snapshot_observed_at":"2026-08-12T11:04:07.827141Z","title":"Privacy-preserving machine learning through data obfuscation,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.827141Z"},"links":{"cited_paper":"/paper/1807.01860","citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:5ff9b491e5cccffe41e60081062ef06121177eac65cfdf452b914ca7cd402e79","observation_id":"fee38d5a-5fce-4c97-a12d-1642a5e52057","resolution":{"observed_at":"2026-08-12T11:04:07.827141Z","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":"2026-08-12T11:04:08.302741Z","title":"Data sanitization for privacy preservation on social network,","venue":null,"work_id":"d72a910d-f9dd-4a19-a9d8-33dd29cb1dee","year":2016},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.831935Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:fa7d3aed35426f5bc3c1b29842dc939569e9235fa5964c7da4ad977bf100df2e","observation_id":"33cc87ce-db6b-4ec8-9f79-1f0417b35a23","resolution":{"observed_at":"2026-08-12T11:04:08.306666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1911.03030","last_updated":"2023-11-08T03:57:25Z","snapshot_observed_at":"2026-08-12T08:56:40.328268Z","submitted_at":"2019-11-08T03:57:41Z","title":"Certified Data Removal from Machine Learning Models","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.03030","snapshot_observed_at":"2026-08-12T11:04:07.837356Z","title":"Cer- tified data removal from machine learning models,","venue":null,"work_id":null,"year":1911},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.837356Z"},"links":{"cited_paper":"/paper/1911.03030","citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:6e059fb37d54c0477f6a27409c4e7b761f6284113a27171764c74af1a300e6f3","observation_id":"e4d41903-e61d-4415-90a3-f9953ef9d4b2","resolution":{"observed_at":"2026-08-12T11:04:07.837356Z","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":"2026-08-12T11:04:07.842268Z","title":"Distillation as a defense to adversarial perturbations against deep neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.842268Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:46a54869ba505a84f6af47db052a1661a76c03f60aca0d77e8446441cdc5c176","observation_id":"2ee094ed-1ec0-4645-9c01-fbb29b420b84","resolution":{"observed_at":"2026-08-12T11:04:07.842268Z","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":"2026-08-12T11:04:08.284641Z","title":"Eternal sunshine of the spotless net: Selective forgetting in deep networks,","venue":null,"work_id":"4591dbb0-c8ea-43a9-a237-38318872cd24","year":2020},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.846439Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:6ec28e6885fd4db8cb32fc67720276df31394bfd406af1093487655fc9d06d32","observation_id":"6a009f71-8ad7-4beb-8678-2f12e178db9e","resolution":{"observed_at":"2026-08-12T11:04:08.288537Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:04:07.850545Z","title":"Word2vec,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.850545Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:533e9061ecaf82ab7319b2a9a868d05ccdf5052fa17b6b6773071e1629606fe6","observation_id":"6795c222-57f5-4e98-a14e-e775b0a63de2","resolution":{"observed_at":"2026-08-12T11:04:07.850545Z","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":"2026-08-12T11:04:08.266538Z","title":"A normalized levenshtein distance metric,","venue":null,"work_id":"d317e8c8-fa32-48cd-a11e-180db7c1fc4a","year":2007},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.854678Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:340e40fffbe9c70043bb22e3cc3e4a4a6a885f548810abde689f4f4a80a9af60","observation_id":"b1116205-4d59-41b1-963d-d06c8b12ea7b","resolution":{"observed_at":"2026-08-12T11:04:08.270522Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:04:08.254908Z","title":"Local differential privacy on metric spaces: optimizing the trade-off with utility,","venue":null,"work_id":"c7c7ede3-c848-494e-9fb0-8b5edfc68343","year":2018},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.858889Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:0664727bbe4f410e33f332430cf9f967eff8ad6cadb794df697121607d0cc4ba","observation_id":"1e39a8ee-c1cf-4a95-a328-86cd192a10bf","resolution":{"observed_at":"2026-08-12T11:04:08.259330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.02665","last_updated":"2026-07-03T23:13:32Z","snapshot_observed_at":"2026-08-13T04:10:15.811732Z","submitted_at":"2024-05-04T13:29:11Z","title":"Metric Differential Privacy at the User-Level Via the Earth Mover's Distance","version":3},"cited_work":{"arxiv_id":"2405.02665","doi":null,"metadata_source":"pith","pith_arxiv_id":"2405.02665","snapshot_observed_at":"2026-08-12T11:04:08.002783Z","title":"Metric Differential Privacy at the User-Level Via the Earth Mover's Distance","venue":"cs.CR","work_id":"8831d649-7513-4cba-bf79-5f9c68152916","year":2024},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.863356Z"},"links":{"cited_paper":"/paper/2405.02665","citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:f641c252d84c50473983eaaf989557807b5173a90c8d12bf4c6bd14d16096310","observation_id":"4ebd9d9e-0017-4f74-b319-d1869841094a","resolution":{"observed_at":"2026-08-12T11:04:08.007072Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:04:07.867909Z","title":"Lipschitz regularity of deep neural networks: analysis and efficient estimation,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.867909Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:319f742992e296e30627cb0086fd65f66b90b3851288c5e95b36e782d66179b2","observation_id":"72ea6ba0-81cf-428b-af46-14d1874f9359","resolution":{"observed_at":"2026-08-12T11:04:07.867909Z","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":"2026-08-12T11:04:08.135920Z","title":"Efficient and accurate estimation of lipschitz constants for deep neural networks,","venue":null,"work_id":"803cd4d2-190d-4e98-83ad-cdfd79b86132","year":2019},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.872057Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:fa7638a8c51adcb6ab5b1c4354ec4d7571287bdcdabc4157b8ebfff02c5c5688","observation_id":"f59f8dc5-166d-45c6-ac80-602f8e370236","resolution":{"observed_at":"2026-08-12T11:04:08.139957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.03169","last_updated":"2023-10-26T21:53:21Z","snapshot_observed_at":"2026-07-06T14:59:10.875394Z","submitted_at":"2023-03-06T14:31:09Z","title":"A Unified Algebraic Perspective on Lipschitz Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.03169","snapshot_observed_at":"2026-08-12T11:04:07.875868Z","title":"A unified algebraic perspective on lipschitz neural networks,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.875868Z"},"links":{"cited_paper":"/paper/2303.03169","citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:5eb531bbb1139111ac9eff165e2006d975d36ee55194691b4d05ae63e77de819","observation_id":"a74c43fa-bd85-4f8c-ad7a-3f3de546ec9e","resolution":{"observed_at":"2026-08-12T11:04:07.875868Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.07167","last_updated":"2021-04-14T23:54:55Z","snapshot_observed_at":"2026-08-06T20:02:41.487392Z","submitted_at":"2021-04-14T23:54:55Z","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","version":1},"cited_work":{"arxiv_id":"2104.07167","doi":null,"metadata_source":"pith","pith_arxiv_id":"2104.07167","snapshot_observed_at":"2026-08-12T11:04:07.976660Z","title":"Orthogonalizing Convolutional Layers with the Cayley Transform","venue":"cs.LG","work_id":"0d4eab4f-39a6-4a0d-bb8a-404bca62fa87","year":2021},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.880234Z"},"links":{"cited_paper":"/paper/2104.07167","citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:73a6a4045ca31c5150ed12cb77ba54f2820428620a4e28f748bb2a4332ff6bfe","observation_id":"ebdf0bc0-18a5-4d5c-89b6-190e8358f38f","resolution":{"observed_at":"2026-08-12T11:04:07.980517Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:04:08.124432Z","title":"Lot: Layer-wise orthogonal training on improving l2 certified robustness,","venue":null,"work_id":"85a0c33e-c1f4-4927-88c9-821d9d6ae5f7","year":2022},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.884849Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:82c497c45b2f2c9b120d41680761d865dfa612aeb5e9b7eb567c6e3973561aee","observation_id":"58430a4e-4dc5-411d-8458-c78629d2b926","resolution":{"observed_at":"2026-08-12T11:04:08.128209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:04:07.888871Z","title":"Learning multiple layers of features from tiny images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.888871Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:d4319fa1384fa9ccada16efff35124a43d38c0e8ad2e394f4cb14e54537db369","observation_id":"717a329f-d50b-4e6d-a81a-1299e649b87f","resolution":{"observed_at":"2026-08-12T11:04:07.888871Z","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":"2026-08-12T11:04:07.893218Z","title":"Pytorch image models,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.893218Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:3ba55b513a195aee762369ac89c8c49f171c028b77dc94681f66c9dfd298daf1","observation_id":"e3e5cdfe-aa12-4880-93df-c715781f1791","resolution":{"observed_at":"2026-08-12T11:04:07.893218Z","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":"2026-08-12T11:04:08.098508Z","title":"Direct parameterization of lipschitz- bounded deep networks,","venue":null,"work_id":"c92e5f03-6ef3-4fec-999d-5d314822d821","year":2023},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.899432Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:af999c65489f7cd0fbb71437ff46aebfd62a55d0c1797edcdb38ee0c58845e28","observation_id":"91586cb3-a56e-4638-b63b-f9e718313bff","resolution":{"observed_at":"2026-08-12T11:04:08.101866Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.02811","last_updated":"2025-07-31T18:56:04Z","snapshot_observed_at":"2026-08-12T23:29:56.045658Z","submitted_at":"2024-07-03T05:13:28Z","title":"SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothing","version":3},"cited_work":{"arxiv_id":"2407.02811","doi":null,"metadata_source":"pith","pith_arxiv_id":"2407.02811","snapshot_observed_at":"2026-08-12T11:04:07.959272Z","title":"SPLITZ: Certifiable Robustness via Split Lipschitz Randomized Smoothing","venue":"cs.LG","work_id":"2e1d0054-5493-4e00-9e62-7e03ff3212f9","year":2024},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.903664Z"},"links":{"cited_paper":"/paper/2407.02811","citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:8f2b3beaf822f68d36621466e4d03b84dd1358d4e688dab2e5f54abaa9a048fb","observation_id":"4e20244e-c078-4d0b-881b-e3824cab26fa","resolution":{"observed_at":"2026-08-12T11:04:07.965156Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:04:08.087261Z","title":"Busemann, The geometry of geodesics","venue":null,"work_id":"9672bc05-5271-476f-9fc9-cfdd12de233a","year":2012},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.908181Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:a79125f9376cea9595abd1d868a0a39f4152b0b4c91b3e604633302a54f5a923","observation_id":"e606f139-7e55-4f65-aca7-f2ea2d4ca3f0","resolution":{"observed_at":"2026-08-12T11:04:08.090746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:04:08.075473Z","title":"(47) Notice that: Z Z2∈S′ 2 fz(Z2)dz = Z Z2|ln fz (Z2 ) fz (Z2 −(C(xb )−C(xa )) >ϵ fu(Z2)dz","venue":null,"work_id":"4e764ac7-5db1-4157-a7af-766163063043","year":null},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.912595Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:77eabfe0dea47fc560630ed13fdbd68e93408e37e251a9a9e46097d61c172b83","observation_id":"c32437f1-9c6e-4777-9244-0ea7eb726ff3","resolution":{"observed_at":"2026-08-12T11:04:08.079426Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+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":"2026-08-12T11:04:08.063607Z","title":"(64) Notice that: Z Z3∈S′ 2 fz(Z3)dz = Z Z3|ln fz (Z3 ) fz (Z3 −(xb −xa )) >ϵ fz(Z3)dz","venue":null,"work_id":"1e6b448a-7e3a-4465-8024-b05088c49b11","year":null},"citing_paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-12T11:04:07.916608Z"},"links":{"citing_paper":"/paper/2411.18746"},"observation_digest":"sha256:a6fc098a87f7c5b0ff1ddad93aa098cd9ff4619403bd773ec29c3d615ecaccef","observation_id":"3abdf3c4-6665-4116-ad47-c49fe244a5de","resolution":{"observed_at":"2026-08-12T11:04:08.067621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-13T06:32:02.005865+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2411.18746","last_updated":"2024-11-27T20:47:28Z","latest_version":1,"primary_category":"cs.CR","snapshot_observed_at":"2026-08-12T18:09:25.108022Z","submitted_at":"2024-11-27T20:47:28Z","title":"Inference Privacy: Properties and Mechanisms"},"reference_resolution":{"displayed":30,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":4,"verified_fuzzy":14},"total_outbound_references":30},"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":"2026-08-13T06:32:02.005865+00:00","source":"crossref"},{"observed_at":"2026-08-13T06:31:53.387327+00:00","source":"retraction_watch"}],"thesis":"As of 13 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2411.18746."}