{"as_of":"2026-08-16T03:48:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3f840ed18f7d3d45b6ca1efae6e6dc9c7ce370734b1a5b65f33908536bc4e1a5","coverage":[{"denominator":22,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":22,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:01:29.009616Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2507.20060/citation-record","integrity":"/paper/2507.20060/integrity","json":"/paper/2507.20060/citation-record.json","paper":"/paper/2507.20060"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:01:28.877106Z","title":"Advances and open problems in federated learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.877106Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:4feb64447d44ec4ef8047db1c398f41031b1361817901ba436f174026b3e28b9","observation_id":"7cc1255c-46d8-4d6d-a3aa-4d0eccd92251","resolution":{"observed_at":"2026-08-15T18:01:28.877106Z","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":"2026-08-15T18:01:29.426241Z","title":"Privacy- preserving aggregation in federated learning: A survey,","venue":null,"work_id":"fd902ce1-50f0-418a-8d56-8bce86c64c66","year":2022},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.883994Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:56fbcf04834bbc0e7f915ae61b6ba95b6d2964abd07a3a63f70eaafb221ad452","observation_id":"f2dfac2c-8788-43fc-ac8d-df704267e9df","resolution":{"observed_at":"2026-08-15T18:01:29.431906Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-15T18:01:29.403581Z","title":"Practical secure aggregation for privacy-preserving machine learning,","venue":null,"work_id":"1f20ad37-6c8c-4aee-9fc4-a95d656d672f","year":2017},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.889327Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:e27a2734c4bc8e2e3053b9d77ba007892cf24a7372833e4695f7aa0b862edd14","observation_id":"fd593898-1118-4759-9b06-71bde0bc47ce","resolution":{"observed_at":"2026-08-15T18:01:29.410052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2009.11248","last_updated":"2020-09-23T16:49:02Z","snapshot_observed_at":"2026-08-06T06:39:17.292785Z","submitted_at":"2020-09-23T16:49:02Z","title":"FastSecAgg: Scalable Secure Aggregation for Privacy-Preserving Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.11248","snapshot_observed_at":"2026-08-15T18:01:28.894461Z","title":"Fast- secagg: Scalable secure aggregation for privacy-preserving federated learning,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.894461Z"},"links":{"cited_paper":"/paper/2009.11248","citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:eca4a0c6ee4e7ff7831cb2a00cea9df7f0392f15bb14aa41f047f7ee0e038e1e","observation_id":"277c0dbd-5889-4733-be66-d3fc4759b46a","resolution":{"observed_at":"2026-08-15T18:01:28.894461Z","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":"2026-08-15T18:01:28.900078Z","title":"Lightsecagg: a lightweight and versatile design for secure aggregation in federated learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.900078Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:d70f11332091c4af3138c656a38ac8badd9d5cd246b11b43020b484e56b55a53","observation_id":"9b8bda76-f637-4be0-b5f8-f672d48bd48d","resolution":{"observed_at":"2026-08-15T18:01:28.900078Z","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":"2026-08-15T18:01:28.905232Z","title":"Deep learning with differential privacy,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.905232Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:3bf4c40ccbf108424434bc92dd89e9f72fec51253dc3e23fec5752284895c6e1","observation_id":"e90f04e5-262e-4893-b0fb-3421297b07a5","resolution":{"observed_at":"2026-08-15T18:01:28.905232Z","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":"2026-08-15T18:01:29.354552Z","title":"Approx- imating functions with approximate privacy for applications in signal estimation and learning,","venue":null,"work_id":"095c99aa-0018-46ff-ba66-cd799d0bcea5","year":2023},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.910298Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:defec0a3052f0644b6948b58d2c77313f6087c8db495c77fd9098edd52941bf2","observation_id":"34ea1eb2-cf21-4555-bb26-9cdb3363de62","resolution":{"observed_at":"2026-08-15T18:01:29.360462Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-15T18:01:29.335063Z","title":"Privfl: Practical privacy-preserving federated regressions on high-dimensional data over mobile networks,","venue":null,"work_id":"b8cf2ac5-1d5d-44b8-ae21-fccf22fc5b7f","year":2019},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.914865Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:4fd43dbdcf49c5ac105c04c53a475773bd8a64f5bade88bc15811a2498afd749","observation_id":"21b55433-8e03-4156-b07a-f6ee2d9b52d1","resolution":{"observed_at":"2026-08-15T18:01:29.339939Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.09843","last_updated":"2021-08-15T16:48:08Z","snapshot_observed_at":"2026-08-13T19:42:13.601026Z","submitted_at":"2020-02-23T06:50:20Z","title":"An Accuracy-Lossless Perturbation Method for Defending Privacy Attacks in Federated Learning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.09843","snapshot_observed_at":"2026-08-15T18:01:28.920440Z","title":"Practical and bilat- eral privacy-preserving federated learning,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.920440Z"},"links":{"cited_paper":"/paper/2002.09843","citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:65352359ba0ef34f3abe5e5e6226d5207d1239d7043ee0506657924dcefccc9c","observation_id":"8273cdc0-1fbe-4bc9-996c-7497c2ce1eef","resolution":{"observed_at":"2026-08-15T18:01:28.920440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.02114","last_updated":"2025-04-02T20:20:13Z","snapshot_observed_at":"2026-08-07T16:13:32.119696Z","submitted_at":"2025-04-02T20:20:13Z","title":"On Model Protection in Federated Learning against Eavesdropping Attacks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.02114","snapshot_observed_at":"2026-08-15T18:01:28.926113Z","title":"On model protection in federated learning against eavesdropping attacks,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.926113Z"},"links":{"cited_paper":"/paper/2504.02114","citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:cef89182f869b761768d8707780ad8b0ae2dae9b6715fec94b60e0c4aa76cc57","observation_id":"fbaf3483-5a5d-4828-8671-a0c9bb67fc29","resolution":{"observed_at":"2026-08-15T18:01:28.926113Z","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":"2026-08-15T18:01:29.318771Z","title":"Guaranteed private communication with secret block structure,","venue":null,"work_id":"dd7b9db2-c96a-45e2-b81f-8984e727992c","year":2024},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.931601Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:919cc8f170aeeb86abecd378b4877842d5dfc04325e4c80b18a5b402389d1011","observation_id":"650f8282-7b64-4007-bd42-eb69090a53b6","resolution":{"observed_at":"2026-08-15T18:01:29.323663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-15T18:01:29.295750Z","title":"Channel state information-free location-privacy enhancement: Fake path injection,","venue":null,"work_id":"7991b832-6b05-457c-8e2e-2e6fc24051c9","year":2024},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.937506Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:b9ec3664f3170f1adb0c8ad62742d3cacece4e107b4a1129a06ec14b255037cc","observation_id":"f6360e74-13d7-40c9-ae46-64c4cb295260","resolution":{"observed_at":"2026-08-15T18:01:29.306159Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-15T18:01:29.271457Z","title":"Channel state information-free location-privacy enhancement: Delay-angle information spoofing,","venue":null,"work_id":"8fb59288-011f-4c3b-b850-381d56199737","year":2024},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.944277Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:53d2af6cfcaeb1158bc5e39daa447e59740918f36c9e7facc9a7a87237342c72","observation_id":"86d2d4e9-d60a-4d7b-b275-13c775d17d03","resolution":{"observed_at":"2026-08-15T18:01:29.280483Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-15T18:01:29.253628Z","title":"Optimized parameter design for channel state information-free location spoofing,","venue":null,"work_id":"da6fa14c-e44d-40a5-97cf-05b01eb97890","year":2024},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.951333Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:24be63b022321280f3cc139f6e6c0d00f474196c14cded68dd1b0302f96ad6b5","observation_id":"8e5de3e6-421c-4631-a2b5-65e1cdee89d7","resolution":{"observed_at":"2026-08-15T18:01:29.259655Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-15T18:01:28.957615Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.957615Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:9c23c2f2f83e052f19a5928e322b3d9d25e87e687f758393d5038e566970988b","observation_id":"b98df06c-8a0f-4195-9977-2abfbe126141","resolution":{"observed_at":"2026-08-15T18:01:28.957615Z","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":"2026-08-15T18:01:29.217049Z","title":"Maximal dissent: a state-dependent way to agree in distributed convex optimization,","venue":null,"work_id":"135797b1-56e6-466e-a0ca-065505cfd6c3","year":2023},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.963169Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:c550505d7b75e4f3a98f6b0a1964a8899d55c79de1d9758a72499f5f95a4a749","observation_id":"9906c162-814c-4f86-b7b1-3a0bd1fe1e21","resolution":{"observed_at":"2026-08-15T18:01:29.223038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+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":"2026-08-15T18:01:28.968825Z","title":"Scaffold: Stochastic controlled averaging for federated learn- ing,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.968825Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:b2a0b9d66db53ee1ae3eeb13af666923c33254f1a829c789cdbcd1641fffb5d6","observation_id":"317c1689-f7b1-4628-8245-51c138830009","resolution":{"observed_at":"2026-08-15T18:01:28.968825Z","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":"2026-08-15T18:01:28.974647Z","title":"Feddc: Federated learning with non-iid data via local drift decoupling and correction,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.974647Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:a07c274e3738520c6e85b6cb2cd87e42b8d35341c70c3076fe9efeef7abb0dc8","observation_id":"c29b6c8e-df16-47a7-b848-2f75a9387797","resolution":{"observed_at":"2026-08-15T18:01:28.974647Z","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":"2026-08-15T18:01:28.985010Z","title":"Goldsmith, Wireless communications","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.985010Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:a78aa17680b16be0b84966e09bef97285a12baebb5be70754b99af9d773fada6","observation_id":"2c399fc6-5c9e-4d07-b99b-dc37980b4730","resolution":{"observed_at":"2026-08-15T18:01:28.985010Z","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":"2026-08-15T18:01:28.994890Z","title":null,"venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:28.994890Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:d16280865b1538abba1e7703b3d73ffe23e54a59eeba4a92a760baa02d472a55","observation_id":"00961bb4-85fd-4498-8e2e-43e813837e3e","resolution":{"observed_at":"2026-08-15T18:01:28.994890Z","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":"2026-08-15T18:01:29.004212Z","title":null,"venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:29.004212Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:3a068838c0b58816be17917ec51b829ac599ca1c3b5f361019dd96103ac7e4e6","observation_id":"c537b0a8-9c0c-4a6e-9772-109918e6d686","resolution":{"observed_at":"2026-08-15T18:01:29.004212Z","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":"2026-08-15T18:01:29.118222Z","title":"Pinchover and J","venue":null,"work_id":"89801f48-42fc-41dc-8e46-cfe8b3357d93","year":2005},"citing_paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T18:01:29.009616Z"},"links":{"citing_paper":"/paper/2507.20060"},"observation_digest":"sha256:6b917d5885592088519a1455f40c01d283f30dd5349453047df5f06ae5797002","observation_id":"03346c24-a63b-4adf-8b72-31aa8ebfb2c1","resolution":{"observed_at":"2026-08-15T18:01:29.126672Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.20060","last_updated":"2025-07-26T21:00:56Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T21:53:17.236759Z","submitted_at":"2025-07-26T21:00:56Z","title":"ModShift: Model Privacy via Designed Shifts"},"reference_resolution":{"displayed":22,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":0,"verified_fuzzy":10},"total_outbound_references":22},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 22 of 22 outbound references and 0 inbound Pith citation observations for arXiv:2507.20060."}