{"as_of":"2026-08-18T11:54:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7211d7e8cb56dcb582e20a3fe20989cbc220da1287db8e6a083a3346fa9aaa0f","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":9,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":9,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":9,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":9,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T12:30:12.730708Z","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":"2026-07-04T10:09:44.313949Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2003.14053","last_updated":"2020-09-11T11:41:10Z","snapshot_observed_at":"2026-08-15T06:18:22.062863Z","submitted_at":"2020-03-31T09:35:02Z","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.14053","snapshot_observed_at":"2026-08-11T12:49:37.522830Z","title":"Inverting gradients – how easy is it to break privacy in federated learning?","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.13818","last_updated":"2024-12-18T13:05:55Z","snapshot_observed_at":"2026-08-15T18:20:22.313652Z","submitted_at":"2024-12-18T13:05:55Z","title":"Fed-AugMix: Balancing Privacy and Utility via Data Augmentation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T12:49:37.522830Z"},"links":{"cited_paper":"/paper/2003.14053","citing_paper":"/paper/2412.13818"},"observation_digest":"sha256:ee2c2c0bf0a89e2ce416ee359f606e90812883fbb8c02e06e88eeca5a256291b","observation_id":"94019469-b930-430e-91cc-3ce0b17479a4","resolution":{"observed_at":"2026-08-11T12:49:37.522830Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.14053","last_updated":"2020-09-11T11:41:10Z","snapshot_observed_at":"2026-08-15T06:18:22.062863Z","submitted_at":"2020-03-31T09:35:02Z","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.14053","snapshot_observed_at":"2026-08-10T18:06:32.236774Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2501.11659","last_updated":"2025-01-20T18:42:21Z","snapshot_observed_at":"2026-08-14T04:14:02.016063Z","submitted_at":"2025-01-20T18:42:21Z","title":"BlindFL: Segmented Federated Learning with Fully Homomorphic Encryption","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T18:06:32.236774Z"},"links":{"cited_paper":"/paper/2003.14053","citing_paper":"/paper/2501.11659"},"observation_digest":"sha256:b589181f7df00b53bbac7d48cf83a40576a26b66eaaed3eb14352f888af442b8","observation_id":"888d612c-4034-4378-acff-53e86a41aa99","resolution":{"observed_at":"2026-08-10T18:06:32.236774Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.14053","last_updated":"2020-09-11T11:41:10Z","snapshot_observed_at":"2026-08-15T06:18:22.062863Z","submitted_at":"2020-03-31T09:35:02Z","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.14053","snapshot_observed_at":"2026-08-16T12:30:12.730708Z","title":"Inverting gradients - how easy is it to break privacy in federated learning?","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2504.12806","last_updated":"2025-05-07T09:01:00Z","snapshot_observed_at":"2026-08-17T19:32:43.239693Z","submitted_at":"2025-04-17T10:12:38Z","title":"A Numerical Gradient Inversion Attack in Variational Quantum Neural-Networks","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-16T12:30:12.730708Z"},"links":{"cited_paper":"/paper/2003.14053","citing_paper":"/paper/2504.12806"},"observation_digest":"sha256:bcadc03fae06ee5e806c71bbefcca17ad82e33f2b7e107bec9b85f2da73ab9af","observation_id":"1a9b9164-61de-4beb-8451-618c0f915957","resolution":{"observed_at":"2026-08-16T12:30:12.730708Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.14053","last_updated":"2020-09-11T11:41:10Z","snapshot_observed_at":"2026-08-15T06:18:22.062863Z","submitted_at":"2020-03-31T09:35:02Z","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.14053","snapshot_observed_at":"2026-08-16T04:28:00.361214Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.01177","last_updated":"2025-05-02T10:35:26Z","snapshot_observed_at":"2026-08-16T14:20:05.929905Z","submitted_at":"2025-05-02T10:35:26Z","title":"LLM Security: Vulnerabilities, Attacks, Defenses, and Countermeasures","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-16T04:28:00.361214Z"},"links":{"cited_paper":"/paper/2003.14053","citing_paper":"/paper/2505.01177"},"observation_digest":"sha256:045438193c3a08bdceae20f041d7bf6ac355e27baaaee1dfd5f2dd112a4c424b","observation_id":"b3d1e28b-f381-426e-a2ad-2d47ce7a099b","resolution":{"observed_at":"2026-08-16T04:28:00.361214Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.14053","last_updated":"2020-09-11T11:41:10Z","snapshot_observed_at":"2026-08-15T06:18:22.062863Z","submitted_at":"2020-03-31T09:35:02Z","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","version":2},"cited_work":{"arxiv_id":"2003.14053","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2003.14053","snapshot_observed_at":"2026-07-04T10:09:44.313949Z","title":"Geiping, H","venue":null,"work_id":"c1a16545-149b-48cc-bf40-8ad16e40e600","year":2020},"citing_paper":{"arxiv_id":"2606.23276","last_updated":"2026-06-24T01:41:10Z","snapshot_observed_at":"2026-08-13T18:49:43.934849Z","submitted_at":"2026-06-22T12:53:54Z","title":"Exposing the Illusion of Erasure in Knowledge Editing for LLMs","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-26T09:10:39.422141Z"},"links":{"cited_paper":"/paper/2003.14053","citing_paper":"/paper/2606.23276"},"observation_digest":"sha256:48a98df0cf19bd16bc7a9876df7eed63db36094841b8b97298051bb0c02d6ff9","observation_id":"abe4a983-2244-486f-ac99-b736b66075d9","resolution":{"observed_at":"2026-07-04T10:09:44.316443Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2003.14053","last_updated":"2020-09-11T11:41:10Z","snapshot_observed_at":"2026-08-15T06:18:22.062863Z","submitted_at":"2020-03-31T09:35:02Z","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.14053","snapshot_observed_at":"2026-08-02T02:54:04.056448Z","title":"Inverting gradients — how easy is it to break privacy in federated learning? Advances in Neural Information Processing Systems (NeurIPS) 2020; 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.14205","last_updated":"2026-07-15T17:57:53Z","snapshot_observed_at":"2026-08-18T09:00:08.368564Z","submitted_at":"2026-07-15T17:57:53Z","title":"Privacy Leakage in Federated Learning in Radiology Reports: A Comparative Evaluation of Tokenizer-Driven Privacy Risks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-02T02:54:04.056448Z"},"links":{"cited_paper":"/paper/2003.14053","citing_paper":"/paper/2607.14205"},"observation_digest":"sha256:ac7b3feb9a5747f8052d4746bb297dafb7544a721cbcf938ea78034e07827624","observation_id":"363e6b18-501c-47ef-acd7-63c613010722","resolution":{"observed_at":"2026-08-02T02:54:04.056448Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.14053","last_updated":"2020-09-11T11:41:10Z","snapshot_observed_at":"2026-08-15T06:18:22.062863Z","submitted_at":"2020-03-31T09:35:02Z","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.14053","snapshot_observed_at":"2026-07-31T22:47:13.239611Z","title":"(2020).In- verting Gradients — How easy is it to break privacy in federated learning?Advances in Neural Information Processing Systems 33 (NeurIPS 2020)","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.27940","last_updated":"2026-07-31T04:21:25Z","snapshot_observed_at":"2026-08-09T12:34:14.004122Z","submitted_at":"2026-07-30T09:49:13Z","title":"TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-07-31T22:47:13.239611Z"},"links":{"cited_paper":"/paper/2003.14053","citing_paper":"/paper/2607.27940"},"observation_digest":"sha256:60eda192e405c062b9a5c3514d35ab9dc5cfe3ba8e8bd6ae34964787c4e011ae","observation_id":"d23328f3-20e6-4a3c-a5a3-b9d36851d6a5","resolution":{"observed_at":"2026-07-31T22:47:13.239611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.14053","last_updated":"2020-09-11T11:41:10Z","snapshot_observed_at":"2026-08-15T06:18:22.062863Z","submitted_at":"2020-03-31T09:35:02Z","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.14053","snapshot_observed_at":"2026-08-03T01:42:09.708146Z","title":"(2020).In- verting Gradients — How easy is it to break privacy in federated learning?Advances in Neural Information Processing Systems 33 (NeurIPS 2020)","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.27940","last_updated":"2026-07-31T04:21:25Z","snapshot_observed_at":"2026-08-09T12:34:14.004122Z","submitted_at":"2026-07-30T09:49:13Z","title":"TriShield: Zero-Utility-Loss Defense Against Privacy Backdoors in Federated Language Model Fine-Tuning via Orthogonal Gradient Projection and Optimizer State Entanglement","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T01:42:09.708146Z"},"links":{"cited_paper":"/paper/2003.14053","citing_paper":"/paper/2607.27940"},"observation_digest":"sha256:a19e3f1d6bbbb1a75431e20b6a8d88ff07166db8bf4126c9d97a0568befa8dd0","observation_id":"835afc7b-6c25-4b9a-8ea9-2bb57a03bbf5","resolution":{"observed_at":"2026-08-03T01:42:09.708146Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.14053","last_updated":"2020-09-11T11:41:10Z","snapshot_observed_at":"2026-08-15T06:18:22.062863Z","submitted_at":"2020-03-31T09:35:02Z","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2003.14053","snapshot_observed_at":"2026-08-15T15:20:19.537986Z","title":"Inverting gradients – how easy is it to break privacy in federated learning?","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2608.00872","last_updated":"2026-08-01T21:23:32Z","snapshot_observed_at":"2026-08-18T11:40:49.186232Z","submitted_at":"2026-08-01T21:23:32Z","title":"Similarity Weighted Aggregation with Global Differential Privacy for Federated Brain Lesion Segmentation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T15:20:19.537986Z"},"links":{"cited_paper":"/paper/2003.14053","citing_paper":"/paper/2608.00872"},"observation_digest":"sha256:22918ee2ec07bb8ffabbea3b3afdd92e12f340ccdf433d36859bd9fb7b4ee528","observation_id":"21b60cd9-a31d-47c3-b3f5-a7ffe8aef171","resolution":{"observed_at":"2026-08-15T15:20:19.537986Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2003.14053/citation-record","integrity":"/paper/2003.14053/integrity","json":"/paper/2003.14053/citation-record.json","paper":"/paper/2003.14053"},"outbound":[],"paper":{"arxiv_id":"2003.14053","last_updated":"2020-09-11T11:41:10Z","latest_version":2,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-15T06:18:22.062863Z","submitted_at":"2020-03-31T09:35:02Z","title":"Inverting Gradients -- How easy is it to break privacy in federated learning?"},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 9 inbound Pith citation observations for arXiv:2003.14053."}