{"as_of":"2026-08-09T03:51:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:30804f496e29c1ff216be7fc0501cecd2856a52e46376d83390e23304cef1f76","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":11,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":11,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":11,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":11,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T18:59:12.756789Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T07:37:45.320291Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2108.04417","last_updated":"2021-09-22T05:05:56Z","snapshot_observed_at":"2026-08-09T02:16:51.504444Z","submitted_at":"2021-08-10T02:58:31Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","version":2},"cited_work":{"arxiv_id":"2108.04417","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04417","snapshot_observed_at":"2026-07-03T07:37:45.320291Z","title":"Privacy-preserving ma- chine learning: Methods, challenges and directions","venue":null,"work_id":"ab78d09f-b07a-440e-a023-5465f926feb1","year":2021},"citing_paper":{"arxiv_id":"2403.02780","last_updated":"2026-04-22T07:55:01Z","snapshot_observed_at":"2026-07-06T17:39:45.571775Z","submitted_at":"2024-03-05T08:52:16Z","title":"Data Collaboration Analysis with Orthonormal Basis Selection and Alignment","version":9},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-24T03:36:32.068663Z"},"links":{"cited_paper":"/paper/2108.04417","citing_paper":"/paper/2403.02780"},"observation_digest":"sha256:40ae93005751961b660fa5c95399d48021ca37dfad4142b76974a68a6cc5fdc4","observation_id":"50cb02b7-ecbf-496a-b2d2-5a6dbdeb31c2","resolution":{"observed_at":"2026-05-24T03:38:50.175860Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04417","last_updated":"2021-09-22T05:05:56Z","snapshot_observed_at":"2026-08-09T02:16:51.504444Z","submitted_at":"2021-08-10T02:58:31Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","version":2},"cited_work":{"arxiv_id":"2108.04417","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04417","snapshot_observed_at":"2026-07-03T07:37:45.320291Z","title":"Privacy-preserving ma- chine learning: Methods, challenges and directions","venue":null,"work_id":"ab78d09f-b07a-440e-a023-5465f926feb1","year":2021},"citing_paper":{"arxiv_id":"2503.16251","last_updated":"2026-04-21T02:49:19Z","snapshot_observed_at":"2026-07-06T20:56:05.172444Z","submitted_at":"2025-03-20T15:46:03Z","title":"RESFL: An Uncertainty-Aware Framework for Responsible Federated Learning by Balancing Privacy, Fairness and Utility","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-22T23:06:39.764310Z"},"links":{"cited_paper":"/paper/2108.04417","citing_paper":"/paper/2503.16251"},"observation_digest":"sha256:35ffe85d96bde7f2b81af6c789d15df6f94600d83c04a88308f1bc11c7a75253","observation_id":"acc363dd-ac97-4851-8e9e-aa1bf3e264e0","resolution":{"observed_at":"2026-05-22T23:07:14.184539Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04417","last_updated":"2021-09-22T05:05:56Z","snapshot_observed_at":"2026-08-09T02:16:51.504444Z","submitted_at":"2021-08-10T02:58:31Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04417","snapshot_observed_at":"2026-08-06T22:06:52.961384Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.22606","last_updated":"2025-09-11T10:59:50Z","snapshot_observed_at":"2026-08-07T02:24:23.241126Z","submitted_at":"2025-06-27T20:05:46Z","title":"A User-Centric, Privacy-Preserving, and Verifiable Ecosystem for Personal Data Management and Utilization","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T22:06:52.961384Z"},"links":{"cited_paper":"/paper/2108.04417","citing_paper":"/paper/2506.22606"},"observation_digest":"sha256:f7bf6397988d9614604deaca0b60a7474cb30fd26e0efdb828f35a9bfa93eea3","observation_id":"c85340cf-acac-4f50-aead-880a0646d9b4","resolution":{"observed_at":"2026-08-06T22:06:52.961384Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04417","last_updated":"2021-09-22T05:05:56Z","snapshot_observed_at":"2026-08-09T02:16:51.504444Z","submitted_at":"2021-08-10T02:58:31Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","version":2},"cited_work":{"arxiv_id":"2108.04417","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04417","snapshot_observed_at":"2026-07-03T07:37:45.320291Z","title":"Privacy-preserving ma- chine learning: Methods, challenges and directions","venue":null,"work_id":"ab78d09f-b07a-440e-a023-5465f926feb1","year":2021},"citing_paper":{"arxiv_id":"2510.26841","last_updated":"2026-04-29T15:16:42Z","snapshot_observed_at":"2026-07-06T22:34:33.419178Z","submitted_at":"2025-10-30T07:14:55Z","title":"FedPF: Accurate Target Privacy Preserving Federated Learning Balancing Fairness and Utility","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-18T02:56:38.973027Z"},"links":{"cited_paper":"/paper/2108.04417","citing_paper":"/paper/2510.26841"},"observation_digest":"sha256:7b784035397a6a0998e9ee302a4e9bf274ceacd25085da99d56abbfbb3ac253e","observation_id":"277b96ed-ec0e-4b41-906d-2a270faba24e","resolution":{"observed_at":"2026-05-18T03:00:48.653006Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04417","last_updated":"2021-09-22T05:05:56Z","snapshot_observed_at":"2026-08-09T02:16:51.504444Z","submitted_at":"2021-08-10T02:58:31Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04417","snapshot_observed_at":"2026-08-03T19:21:36.350529Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.01039","last_updated":"2025-11-30T19:16:30Z","snapshot_observed_at":"2026-08-07T14:55:02.267471Z","submitted_at":"2025-11-30T19:16:30Z","title":"Joint Partitioning and Placement of Foundation Models for Real-Time Edge AI","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T19:21:36.350529Z"},"links":{"cited_paper":"/paper/2108.04417","citing_paper":"/paper/2512.01039"},"observation_digest":"sha256:7ca2d5cfc08dc317bb00b93f7085a5bd974be45ac969c4abf6cefbbda310c6c2","observation_id":"61eb1354-c5ce-4133-a0a0-1283f41d4443","resolution":{"observed_at":"2026-08-03T19:21:36.350529Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04417","last_updated":"2021-09-22T05:05:56Z","snapshot_observed_at":"2026-08-09T02:16:51.504444Z","submitted_at":"2021-08-10T02:58:31Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","version":2},"cited_work":{"arxiv_id":"2108.04417","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04417","snapshot_observed_at":"2026-07-03T07:37:45.320291Z","title":"Privacy-preserving ma- chine learning: Methods, challenges and directions","venue":null,"work_id":"ab78d09f-b07a-440e-a023-5465f926feb1","year":2021},"citing_paper":{"arxiv_id":"2604.05571","last_updated":"2026-04-07T08:13:45Z","snapshot_observed_at":"2026-07-06T22:54:16.913706Z","submitted_at":"2026-04-07T08:13:45Z","title":"Understanding User Privacy Perceptions of GenAI Smartphones","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-05-10T19:18:29.955515Z"},"links":{"cited_paper":"/paper/2108.04417","citing_paper":"/paper/2604.05571"},"observation_digest":"sha256:77aea5c79a305d3d022ad7c7d79663b51725ba54225d575b589f8c6e2ac0ea6f","observation_id":"3662ac51-a24d-4aa0-8e40-2fb2ee9b9664","resolution":{"observed_at":"2026-05-10T23:10:51.626769Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04417","last_updated":"2021-09-22T05:05:56Z","snapshot_observed_at":"2026-08-09T02:16:51.504444Z","submitted_at":"2021-08-10T02:58:31Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","version":2},"cited_work":{"arxiv_id":"2108.04417","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04417","snapshot_observed_at":"2026-07-03T07:37:45.320291Z","title":"Privacy-preserving ma- chine learning: Methods, challenges and directions","venue":null,"work_id":"ab78d09f-b07a-440e-a023-5465f926feb1","year":2021},"citing_paper":{"arxiv_id":"2604.12335","last_updated":"2026-04-14T06:17:35Z","snapshot_observed_at":"2026-07-06T23:00:32.607699Z","submitted_at":"2026-04-14T06:17:35Z","title":"All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-05-10T15:26:55.369840Z"},"links":{"cited_paper":"/paper/2108.04417","citing_paper":"/paper/2604.12335"},"observation_digest":"sha256:3c7ce6bc2e7d604a9f53ebd04a013bd57e7041bcac3a52c255e6014daf915a15","observation_id":"3756e64a-3b9a-4294-ad72-43ce4a1e7f0c","resolution":{"observed_at":"2026-05-11T10:31:03.883767Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04417","last_updated":"2021-09-22T05:05:56Z","snapshot_observed_at":"2026-08-09T02:16:51.504444Z","submitted_at":"2021-08-10T02:58:31Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","version":2},"cited_work":{"arxiv_id":"2108.04417","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04417","snapshot_observed_at":"2026-07-03T07:37:45.320291Z","title":"Privacy-preserving ma- chine learning: Methods, challenges and directions","venue":null,"work_id":"ab78d09f-b07a-440e-a023-5465f926feb1","year":2021},"citing_paper":{"arxiv_id":"2604.18966","last_updated":"2026-05-17T12:00:22Z","snapshot_observed_at":"2026-08-01T19:53:45.797959Z","submitted_at":"2026-04-21T01:29:52Z","title":"Self-Improving Tabular Language Models via Iterative Reward-Guided Post-Training","version":1},"reference_index":191,"source":"arxiv_source","source_observed_at":"2026-05-10T03:04:54.146481Z"},"links":{"cited_paper":"/paper/2108.04417","citing_paper":"/paper/2604.18966"},"observation_digest":"sha256:75549d4925c9bc09e3ad925d283be564a710c67131c683cfa17f1f870897e54d","observation_id":"8ae63e78-effa-4f65-9f1b-7ff38c48d552","resolution":{"observed_at":"2026-05-11T12:46:03.873599Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04417","last_updated":"2021-09-22T05:05:56Z","snapshot_observed_at":"2026-08-09T02:16:51.504444Z","submitted_at":"2021-08-10T02:58:31Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","version":2},"cited_work":{"arxiv_id":"2108.04417","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04417","snapshot_observed_at":"2026-07-03T07:37:45.320291Z","title":"Privacy-preserving ma- chine learning: Methods, challenges and directions","venue":null,"work_id":"ab78d09f-b07a-440e-a023-5465f926feb1","year":2021},"citing_paper":{"arxiv_id":"2605.27219","last_updated":"2026-05-26T16:07:32Z","snapshot_observed_at":"2026-08-02T01:50:54.996516Z","submitted_at":"2026-05-26T16:07:32Z","title":"Nonlinear Data Integration via Kernel Methods for Data Collaboration Analysis","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-29T18:32:15.604526Z"},"links":{"cited_paper":"/paper/2108.04417","citing_paper":"/paper/2605.27219"},"observation_digest":"sha256:3a6cc4718ffe7ab6ee891e6c6cf399f84cd94b09e5dc8d03e8f25f63a465d833","observation_id":"1e000401-e5e8-4931-882d-9cf30c99c065","resolution":{"observed_at":"2026-06-29T18:33:50.308633Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04417","last_updated":"2021-09-22T05:05:56Z","snapshot_observed_at":"2026-08-09T02:16:51.504444Z","submitted_at":"2021-08-10T02:58:31Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","version":2},"cited_work":{"arxiv_id":"2108.04417","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2108.04417","snapshot_observed_at":"2026-07-03T07:37:45.320291Z","title":"Privacy-preserving ma- chine learning: Methods, challenges and directions","venue":null,"work_id":"ab78d09f-b07a-440e-a023-5465f926feb1","year":2021},"citing_paper":{"arxiv_id":"2606.10361","last_updated":"2026-06-09T03:21:48Z","snapshot_observed_at":"2026-07-31T01:48:34.598968Z","submitted_at":"2026-06-09T03:21:48Z","title":"Near-Exponential Convergence Rates for kNN Classification based on Boltzmann Margin","version":1},"reference_index":111,"source":"arxiv_source","source_observed_at":"2026-06-27T12:00:48.263093Z"},"links":{"cited_paper":"/paper/2108.04417","citing_paper":"/paper/2606.10361"},"observation_digest":"sha256:ba61c49c7da21c715eab393bd055b65ddd61120e25442fe9abbb674cf3b5fb2e","observation_id":"b4c27865-f635-4817-aaad-b91d270fef78","resolution":{"observed_at":"2026-07-03T07:37:45.321523Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2108.04417","last_updated":"2021-09-22T05:05:56Z","snapshot_observed_at":"2026-08-09T02:16:51.504444Z","submitted_at":"2021-08-10T02:58:31Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2108.04417","snapshot_observed_at":"2026-08-08T18:59:12.756789Z","title":"Privacy-preserving machine learning: Methods, challenges and directions,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.04366","last_updated":"2026-08-05T02:13:37Z","snapshot_observed_at":"2026-08-08T23:11:31.702226Z","submitted_at":"2026-08-05T02:13:37Z","title":"Combating Knowledge Corruption in Agent Systems: A Byzantine-Tolerant Secure Collaborative RAG Framework","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-08T18:59:12.756789Z"},"links":{"cited_paper":"/paper/2108.04417","citing_paper":"/paper/2608.04366"},"observation_digest":"sha256:82492e5d169f7d151f50ce1a0192264b761bf6e8f20985abdd18727343feb746","observation_id":"dbbe4e87-09d1-4c7c-8650-b7873168f6e3","resolution":{"observed_at":"2026-08-08T18:59:12.756789Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2108.04417/citation-record","integrity":"/paper/2108.04417/integrity","json":"/paper/2108.04417/citation-record.json","paper":"/paper/2108.04417"},"outbound":[],"paper":{"arxiv_id":"2108.04417","last_updated":"2021-09-22T05:05:56Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T02:16:51.504444Z","submitted_at":"2021-08-10T02:58:31Z","title":"Privacy-Preserving Machine Learning: Methods, Challenges and Directions"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 11 inbound Pith citation observations for arXiv:2108.04417."}