{"as_of":"2026-08-09T21:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ef571d72847e687a39efcd353d3016fb23a335ee69f57163bad2fe1715824aa6","coverage":[{"denominator":53,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":53,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T21:08:31.700915Z","state":"measured"},{"denominator":53,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":53,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2507.00920/citation-record","integrity":"/paper/2507.00920/integrity","json":"/paper/2507.00920/citation-record.json","paper":"/paper/2507.00920"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T21:08:26.091266Z","title":"Federated learning: Challenges, methods, and future directions,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:26.091266Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:63c7b68dc7310ec5cfbf2689cf7225491cd3e1023d1a8a1471610a2f8d6e8bb1","observation_id":"226e806b-ffd1-445b-86ed-227c03f98570","resolution":{"observed_at":"2026-08-06T21:08:26.091266Z","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":"2026-08-06T21:08:41.351556Z","title":"Federated learning and wireless commu- nications,","venue":null,"work_id":"a5270686-04fe-42b1-9fad-19230f499d0e","year":2021},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:26.177276Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:88a219780ffd8912c60ab0b5e0e79eaf88b85976ed45ebbd6a0231622a396b1e","observation_id":"9cd174ed-6c33-4f1e-9150-33e5caae1f51","resolution":{"observed_at":"2026-08-06T21:08:41.447250Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:41.216715Z","title":"Federated learning: A signal processing perspective,","venue":null,"work_id":"2c1cb16c-bb5d-4008-9341-7a34fbe965e8","year":2022},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:26.242663Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:c78befac60a382d43ed4e303f37c083280a807990e13c47745afe6d05cde28bd","observation_id":"6a9278de-76f4-4daf-947e-34b3421e4515","resolution":{"observed_at":"2026-08-06T21:08:41.281459Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:41.003956Z","title":"Pretraining federated text models for next word prediction,","venue":null,"work_id":"346502c9-4109-40c2-8c6a-6b6707b7ed28","year":2021},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:26.289762Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:8b9ade9daeb4dfd0d25ccfe24aa1f4004bcd0a5b5b6a86257cc3a309561b2094","observation_id":"a48cb18f-e4e0-45b6-a776-2050965652e1","resolution":{"observed_at":"2026-08-06T21:08:41.143403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:40.751034Z","title":"FedNLP: Benchmarking federated learning methods for natural language processing tasks,","venue":null,"work_id":"a931f36b-9ca8-473a-8e19-a329d25ce090","year":null},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:26.352699Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:bfa4c2def45e373e5a4bc4d2a25492bc38ec97f9acee81f5303660a4d5734cc6","observation_id":"6575f376-4568-4779-8065-76045561dadb","resolution":{"observed_at":"2026-08-06T21:08:40.869352Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:40.543896Z","title":"Federated learning for connected and automated vehicles: A survey of existing approaches and challenges,","venue":null,"work_id":"20bad0f4-6c37-43b0-9531-368cfce9abea","year":2024},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:26.514690Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:ce23b2702fe1603861eb406183ae558e2f5d445a1ec142c2e5fea036eb7827d4","observation_id":"b7918b7f-41a0-4b10-8d75-21005dd247b4","resolution":{"observed_at":"2026-08-06T21:08:40.655017Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:26.573403Z","title":"Federated learning for internet of things: A comprehensive survey,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:26.573403Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:aa99598a7825ec1f74c63e76bd7ce6f46151f80d29311f308f53a7ef31c632df","observation_id":"0ffeeb74-56de-45e1-9e2a-b74467d4fef3","resolution":{"observed_at":"2026-08-06T21:08:26.573403Z","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":"2026-08-06T21:08:40.279112Z","title":"Scoring aided federated learning on long-tailed data for wireless iomt based healthcare system,","venue":null,"work_id":"52357962-3b31-4fca-8fed-7cc202207b52","year":2023},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:26.663930Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:878b03ecdba1bb9c081d4fc1c3ab13c75153c4f2cb9d1c30f9c89682de4cf4c7","observation_id":"32abb5f2-853b-4311-97d8-498fc28931a0","resolution":{"observed_at":"2026-08-06T21:08:40.412203Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:40.043631Z","title":"Federated learning for medical applications: A taxonomy, current trends, challenges, and future research directions,","venue":null,"work_id":"1ed25509-df44-4af4-bbf0-eacc3589f027","year":2024},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:26.750976Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:6632fc0ea6b2b24418c860810a8cbc7b6d92e727407a0e05aa2e1f3bf9b2822c","observation_id":"cea4b7f7-563b-4f91-ab7d-29a728ffd137","resolution":{"observed_at":"2026-08-06T21:08:40.171952Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.06963","last_updated":"2018-02-24T00:40:30Z","snapshot_observed_at":"2026-08-08T12:18:09.531945Z","submitted_at":"2017-10-18T23:46:57Z","title":"Learning Differentially Private Recurrent Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.06963","snapshot_observed_at":"2026-08-06T21:08:26.855347Z","title":"Learning differentially private recurrent language models,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:26.855347Z"},"links":{"cited_paper":"/paper/1710.06963","citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:be23aacfdb482620452983e2f0a7ba7c896b4a7c10db845b0e67c586320dd1d3","observation_id":"9fb0324c-3df1-4b9e-8a61-5c0671fedebf","resolution":{"observed_at":"2026-08-06T21:08:26.855347Z","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":"2026-08-06T21:08:39.816939Z","title":"OpenFedLLM: Training large language models on decentral- ized private data via federated learning,","venue":null,"work_id":"e0f9e578-579e-43f4-8ff0-4dface77ae4d","year":2024},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:26.979058Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:3f939cea5c0c910e69ca1d843a3bccbf9dc74c68b9c9a7da3f02e02c62e1c55d","observation_id":"3ee313ba-964c-447b-b10b-d15bef1586d3","resolution":{"observed_at":"2026-08-06T21:08:39.918077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:39.661273Z","title":"The distributed discrete gaussian mechanism for federated learning with secure aggregation,","venue":null,"work_id":"1f6ea7ab-bb67-4f96-b18e-d6906b32f514","year":2021},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:27.060369Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:04fd4fe30fcbe0c0a4c705222bbd8c816b63af8f442b163c908297f5a3a680b9","observation_id":"fa32d031-9063-42dc-a3d3-2d73114d509b","resolution":{"observed_at":"2026-08-06T21:08:39.734490Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:39.457466Z","title":"Deep leakage from gradients,","venue":null,"work_id":"419ce53d-70d4-46e3-aeed-8f798bdc0faf","year":2019},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:27.197385Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:3f97a27f60b4e2bbe2b8f9a2bdb7f397df81e6e07e9fb90f4c5edd566a401867","observation_id":"ee44365f-7185-4bef-99d5-426628ea2276","resolution":{"observed_at":"2026-08-06T21:08:39.543454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:39.199782Z","title":"Evaluating gradient inversion attacks and defenses in federated learning,","venue":null,"work_id":"c4b22695-8b78-4637-a498-5efb0232a3b2","year":2021},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:27.389920Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:6a1551befa8d94e9fe81fa5e40bfd23be66099a55047f54fd036cfa1e3d1ee93","observation_id":"ed83dbbc-ff40-4b68-8336-27c583045e57","resolution":{"observed_at":"2026-08-06T21:08:39.310355Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:38.912860Z","title":"Inverting gradients - how easy is it to break privacy in federated learning?","venue":null,"work_id":"fada8d85-bcf6-4cac-8238-a6da9276236d","year":2020},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:27.518332Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:92c4d521786451de0583df749ee27725deb417d92252c4e29af9ca5e909a9c32","observation_id":"2a4dcb7d-c118-4852-bbbc-d4670506286c","resolution":{"observed_at":"2026-08-06T21:08:39.042275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:38.697183Z","title":"The algorithmic foundations of differential privacy,","venue":null,"work_id":"b6ef1363-55db-4228-b812-fb8479a19747","year":2014},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:27.635795Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:035089d627c15151d68c06116658c238d0768273c7c18e39f2dd573cba84681b","observation_id":"511e2ef2-9cc5-4ae6-95c2-590f8ddca116","resolution":{"observed_at":"2026-08-06T21:08:38.775507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:38.381722Z","title":"Federated learning with differential privacy: Algorithms and performance analysis,","venue":null,"work_id":"37024ef1-4091-418f-a7bf-e99fe4864337","year":2020},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:27.789559Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:27bdf5f9526de3b5f702d5ac622458d02666d0c6754005d68a8d4a54c15f9b2d","observation_id":"6cca232e-c431-4d19-94b7-8e85530031ca","resolution":{"observed_at":"2026-08-06T21:08:38.523747Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:38.135815Z","title":"Differentially private Aircomp federated learning with power adaptation harnessing receiver noise,","venue":null,"work_id":"f0df8b62-ee7b-4ac5-b92b-5236254dd529","year":2020},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:27.881243Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:639eb4542318d31d4e50b73bc7f0bb9e926604f51973450ffa9a10a9374605b9","observation_id":"9ec619aa-67cc-44a1-a501-d967b40256d5","resolution":{"observed_at":"2026-08-06T21:08:38.256103Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:37.870135Z","title":"Privacy for free: Wireless federated learning via uncoded transmission with adaptive power control,","venue":null,"work_id":"8a4a6f7d-f52a-40c3-a088-c5161a7ae137","year":2021},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:28.056552Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:71a0d2b7f47ed7030aae6e2cf0ce0f9d3143c8ad55a127cb691cde95ea3830e5","observation_id":"8fdd7eb2-fcd9-4ab8-9e74-c90ed30c9bdf","resolution":{"observed_at":"2026-08-06T21:08:38.028750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:37.669049Z","title":"Privacy amplification for federated learning via user sampling and wireless aggregation,","venue":null,"work_id":"a0e888ae-c1a0-442d-86c8-106036a4d4d7","year":2021},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:28.174746Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:f9560cb0002a6e0365ce1a47a2c1bfa19ca2d63f8160f0837f6667ed2c73d580","observation_id":"c520853a-5d5c-4d42-b860-5198f4c02c33","resolution":{"observed_at":"2026-08-06T21:08:37.734903Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:37.498565Z","title":"Federated learning with local differential privacy: Trade-offs between privacy, utility, and communica- tion,","venue":null,"work_id":"7d7a5dac-46ae-47a0-ae7a-ed0f88c356d7","year":2021},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:28.254752Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:8b2197deab80e37beab944871c88dde666c5c72f656fb3c3ae1df99dc4a8c724","observation_id":"1329a5d0-84a2-41b1-9b2b-860866c80018","resolution":{"observed_at":"2026-08-06T21:08:37.605836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:28.383694Z","title":"User- level privacy-preserving federated learning: Analysis and performance optimization,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:28.383694Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:1d3692079c7e4537a5c6c03904a47245be95a6ecd2b933110901fc22d056c063","observation_id":"2534b41f-d6e5-4a95-ad57-3d6fc1b95573","resolution":{"observed_at":"2026-08-06T21:08:28.383694Z","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":"2026-08-06T21:08:37.375122Z","title":"Time-varying noise perturbation and power control for differential-privacy-preserving wireless federated learning,","venue":null,"work_id":"f4d31450-3723-45c6-af8c-8e14ab2b4579","year":2023},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:28.505970Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:a2fab047ab405d65971522b56b3119b5d428dc64c8ca382711b66108a5879f4e","observation_id":"725a77d6-2dd4-4d36-91ad-1206239730f3","resolution":{"observed_at":"2026-08-06T21:08:37.442546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:37.225047Z","title":"Breaking the communication- privacy-accuracy trilemma,","venue":null,"work_id":"f62d854f-6339-4b9a-b64c-505518c766af","year":2020},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:28.576788Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:8324ae331ca8382a91f8cbc2cc3d9e680d3c9f690e45ab62f6e658b0dccab692","observation_id":"7719dc26-213b-446a-9c3e-4125faa47707","resolution":{"observed_at":"2026-08-06T21:08:37.305488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.11913","last_updated":"2023-06-20T21:54:13Z","snapshot_observed_at":"2026-08-09T16:12:26.909748Z","submitted_at":"2023-06-20T21:54:13Z","title":"Randomized Quantization is All You Need for Differential Privacy in Federated Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.11913","snapshot_observed_at":"2026-08-06T21:08:28.698580Z","title":"Randomized quantization is all you need for differential privacy in federated learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:28.698580Z"},"links":{"cited_paper":"/paper/2306.11913","citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:ebcd15e46395ed32fbf9390753e833c1b875de952b38e4e906a401d1452a9290","observation_id":"19c604ce-9ba2-40a9-8787-16f2d3dcac4e","resolution":{"observed_at":"2026-08-06T21:08:28.698580Z","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":"2026-08-06T21:08:37.061623Z","title":"QMGeo: Differentially private federated learning via stochastic quantization with mixed truncated geometric dis- tribution,","venue":null,"work_id":"57102fbe-8f3d-48b9-b8b3-5f693a9f7e82","year":2024},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:28.799095Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:b3ed4767c3f524ecef2950fd292a2e0aab46b10eaa8e723c2ac8a6c7386fc745","observation_id":"fbf3bec7-3220-4ca1-af83-6b5356e7a21c","resolution":{"observed_at":"2026-08-06T21:08:37.131327Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:36.905655Z","title":"Joint privacy en- hancement and quantization in federated learning,","venue":null,"work_id":"9df445ad-2dc9-41ce-b9cd-17995e146489","year":2023},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:28.881182Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:8dcdc3ff4f67e5a70616927f895178eac46f0d1df243fed9941e82bb41d78e8b","observation_id":"534b032d-5bd5-4e74-a0f8-e0f37a83200c","resolution":{"observed_at":"2026-08-06T21:08:36.984703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:36.749149Z","title":"Dynamic aggregation for heterogeneous quantization in federated learning,","venue":null,"work_id":"e7767468-eca1-444f-aeef-67c683dde6a3","year":2021},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:28.951470Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:21ea733980d22b67bc963df082c2d49c3d887d40b798f045a14cd04606165b84","observation_id":"6fa8b7e8-47d5-4fe8-a683-827317c3a34d","resolution":{"observed_at":"2026-08-06T21:08:36.831146Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:36.640654Z","title":"Federated learning with heterogeneous quantization bit allocation and aggregation for internet of things,","venue":null,"work_id":"9659d16a-2713-4793-abfe-1316a222cb8e","year":2024},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:29.058963Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:eec98fec1f92a08061ffd5642b0bfc878d79f4da11432bc2070c410553e4d2e4","observation_id":"5768290e-3496-4159-a944-b512318f0c3e","resolution":{"observed_at":"2026-08-06T21:08:36.697040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:29.129749Z","title":"Quantized federated learning under transmission delay and outage constraints,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:29.129749Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:4e7b753a3595ab1d9f44cc1f1489de5df37fd144bee764f4188d788433464c0e","observation_id":"2d12813d-a1d2-4f82-8022-3281a3aa8047","resolution":{"observed_at":"2026-08-06T21:08:29.129749Z","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":"2026-08-06T21:08:36.482854Z","title":"QSGD: communication-efficient SGD via gradient quantization and encoding,","venue":null,"work_id":"ab702d37-8967-44ae-9c97-9f3e21a1c61b","year":2017},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:29.212176Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:b74b93551ff1e5a87ab32a08c5c46cf4b620e84f65adefbba1689a07277263d0","observation_id":"12efffb1-5c74-4a31-8050-fd97bc5daf8c","resolution":{"observed_at":"2026-08-06T21:08:36.568205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:36.339405Z","title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization,","venue":null,"work_id":"387a3ffe-5270-413f-bf95-07aff1bef2e3","year":2020},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:29.297977Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:afa8a73bf27e169d645ca529a16ffd25cb7f612e7598f5d943472640c0cd5b01","observation_id":"d7f89f78-0525-4a1d-a0a8-730b3d5ed94a","resolution":{"observed_at":"2026-08-06T21:08:36.396138Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:36.155985Z","title":"Quantized federated learning under transmission delay and outage constraints,","venue":null,"work_id":"af30ed8a-970e-42c0-8608-b72a70921bae","year":2021},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:29.437429Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:17b9d7e233111e304165524ffaa9366205e36d81454bb2f31c227e7a12ee8c88","observation_id":"13e42ae3-1d38-4910-b942-73a06cc1757d","resolution":{"observed_at":"2026-08-06T21:08:36.244439Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:35.974904Z","title":"The dual simplex algorithm for bounded variables,","venue":null,"work_id":"51b9eed8-9460-492c-85e1-a83fc86a8ca5","year":1958},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:29.592164Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:c40fca79f9959faeec939a0a6cf96442bec037b6946bc03a59bd4c417c3bad94","observation_id":"cae605fe-fc0f-47c8-b8ab-d40df6b77d5d","resolution":{"observed_at":"2026-08-06T21:08:36.060890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:35.824372Z","title":null,"venue":null,"work_id":"22c5395d-fb42-4924-8bd3-9d93c424faba","year":1984},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:29.726427Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:be231d34ec3d71b8332d2c642432e9059d99fc7feb505725185c2dfe0dbd3f10","observation_id":"eb6bff2d-2de7-483b-8c50-e23f91b587c9","resolution":{"observed_at":"2026-08-06T21:08:35.892487Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:35.560972Z","title":"A new polynomial-time algorithm for linear program- ming,","venue":null,"work_id":"21a9e428-5b0b-4bb6-a576-782fb9a2115f","year":1984},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:29.825823Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:7060e60cf8a5958ef583a087c2ce2a4564a5fb2e242ddee2e5de6dcebb716b08","observation_id":"4f7a3c0b-9992-4fee-a705-3fb14dd25bb9","resolution":{"observed_at":"2026-08-06T21:08:35.727856Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:35.302565Z","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data,","venue":null,"work_id":"7ec69338-9d8d-4388-a6d7-e274f0062e34","year":2017},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:29.949388Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:1e80bf4b344a1c8230f0892bf4b34ad0aed6f9e48c9f0a0df80be25e5475a0f6","observation_id":"ba976b62-5dd3-4cbb-b571-1e80795673b5","resolution":{"observed_at":"2026-08-06T21:08:35.428951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:34.995841Z","title":"Efficient mini-batch training for stochastic optimization,","venue":null,"work_id":"90322207-90ff-408c-85cf-383e723e552b","year":2014},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:30.054071Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:546c7ff2b0b4f24370b5957e8cd026088987ef122912a8e815806e1ca694e81c","observation_id":"08ffb05e-56c4-4bf4-85cb-7d2455a16796","resolution":{"observed_at":"2026-08-06T21:08:35.121364Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:34.723525Z","title":"Deep learning with differential privacy,","venue":null,"work_id":"ae3218f6-0a2b-41d3-ac35-6335a25d7186","year":2016},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:30.215085Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:258428bab5a682ea0d97c67d72c3b761bcd495b8f2047780b1bee5a9b87e38ed","observation_id":"c4c62f09-c3db-4a90-8fcb-30d3a3d55c74","resolution":{"observed_at":"2026-08-06T21:08:34.882465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:34.455934Z","title":"Federated learning over noisy channels: Conver- gence analysis and design examples,","venue":null,"work_id":"4e293d4a-3cbe-496f-9717-aa6c2a0098eb","year":2022},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:30.378431Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:ece0797c1a17ed591efc1b3d2a13d2428ecb4fb1c997e12cddbd3e9d0c930020","observation_id":"212e7e87-e169-4767-9822-b808270ba85d","resolution":{"observed_at":"2026-08-06T21:08:34.567513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:34.267508Z","title":"Optimizing federated averaging over fading channels,","venue":null,"work_id":"272a1fc2-e58a-4a25-9f7d-35fbfff982c3","year":2022},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:30.505838Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:7b7b2cbe1670fff093946a0b8e13e38ed0841d9ce859fca7cf96ff3f0c6b03c9","observation_id":"8f4ff76b-ef40-48b9-9a39-5911c2f70358","resolution":{"observed_at":"2026-08-06T21:08:34.369546Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:34.017983Z","title":"Nesterov, Introductory Lectures on Convex Optimization: A Basic Course, 1st ed","venue":null,"work_id":"7d628556-8675-4712-adef-e6c0de224040","year":2014},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:30.604971Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:36477900887d7d00cd149b2f9cc99ce678b295f02b314765bb87768bf7f0310d","observation_id":"900a3faa-21b1-4cc0-bdae-28a79b088a09","resolution":{"observed_at":"2026-08-06T21:08:34.148650Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:33.754255Z","title":"Revisiting gradient clip- ping: Stochastic bias and tight convergence guarantees,","venue":null,"work_id":"e76ea0a1-7f5d-4a59-835f-26e6e391b171","year":2023},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:30.742689Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:bf0807342c0a2c4d0294d349c542a460cb8b2193343f890cff939cf04811ad27","observation_id":"2f5895cb-cba0-4479-8a15-788e48bea36f","resolution":{"observed_at":"2026-08-06T21:08:33.842779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:33.564599Z","title":"A guide through the zoo of biased SGD,","venue":null,"work_id":"b7099230-366b-4a6f-8615-22456a144067","year":2023},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:30.834929Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:6c0c403cad1bf6daad2b557e89487863d67264020ede33d8f3a5251f420fad1e","observation_id":"04774242-9fed-49c3-9828-afd7db3652bf","resolution":{"observed_at":"2026-08-06T21:08:33.646197Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:33.336933Z","title":"On biased compression for distributed learning,","venue":null,"work_id":"be2f5a5a-b7fa-4073-8c50-879955287295","year":2023},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:30.963351Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:916bb1b9ca03c88b54947771fd62fb5189295310b3a020f32eea853d08034597","observation_id":"1535ee47-a91f-4fa1-9382-821f788c41b8","resolution":{"observed_at":"2026-08-06T21:08:33.462288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:32.957084Z","title":"Supplement to Privacy-Preserving Quantized Federated Learning with Diverse Precision,","venue":null,"work_id":"c8ee228f-9e84-46e3-840c-92f8727d931a","year":2025},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:31.085929Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:f432b1624277554ad170321cd88d0762d9f233e18d5d10f10ad26438f33e5e14","observation_id":"08ff5540-8118-4b29-bb2c-fc64900e9d57","resolution":{"observed_at":"2026-08-06T21:08:33.125837Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:32.746998Z","title":"Amplitude- varying perturbation for balancing privacy and utility in federated learning,","venue":null,"work_id":"04e05ffa-ae50-4564-9be3-b71e63822ec7","year":2023},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:31.215480Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:dcf5ee8cac810dfc018da11995bc8d4f9905367dbacce233b7b83a0ad14fc6e4","observation_id":"d4c81696-aadd-4e84-a32a-78ee3c092748","resolution":{"observed_at":"2026-08-06T21:08:32.859876Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:32.481707Z","title":"Li and X","venue":null,"work_id":"351f3ae4-50a2-4f78-a288-2af54dc23407","year":2006},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:31.295575Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:e0160cd7c090450a6ac74382ceea44ad7aa6d6866bc02381d27e417ff40e01c9","observation_id":"443c94da-74b8-48ac-9df0-0c685b763143","resolution":{"observed_at":"2026-08-06T21:08:32.645231Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:32.310223Z","title":"An approach to sensor network throughput enhancement by PHY-Aided MAC,","venue":null,"work_id":"71bf8516-fb0b-4db5-8a23-ad3681cefc7d","year":2015},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:31.425036Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:bf47266e612347c67a6c7f3ded6b5adec7efb36211d004f49cb338374e423663","observation_id":"ba0c68f0-9c4e-4f90-aea6-5f61b2e79ac3","resolution":{"observed_at":"2026-08-06T21:08:32.388319Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:32.171834Z","title":"Backpropagation applied to handwritten zip code recognition,","venue":null,"work_id":"1c170b82-94a6-4fda-bd0a-27669c6271c4","year":1989},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:31.513257Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:f6781d4b6c6e90e97da2027119a34b3d3248c25886fe274621b6abb570e8eedc","observation_id":"2478e36d-29cc-4eed-a77d-fa9583cf840c","resolution":{"observed_at":"2026-08-06T21:08:32.240804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:31.972556Z","title":"MNIST handwritten digit database,","venue":null,"work_id":"b1aae99a-f8a9-4bd3-9536-42e3b9ad7464","year":2010},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:31.625872Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:44c6c511d7ae381f626aaf8122b211e9b451a9ecd8a29924a825bdf58af3f62a","observation_id":"85235303-f26f-44e3-9fe5-ce258fc62135","resolution":{"observed_at":"2026-08-06T21:08:32.069597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-06T21:08:31.700915Z","title":"Image quality assess- ment: from error visibility to structural similarity,","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:31.700915Z"},"links":{"citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:b97a5eb505e1d3a542f8b858a8237aa3bead39e6e50d5318815e8954a139f406","observation_id":"1fcd8f31-45a6-486e-b586-c2578fa41011","resolution":{"observed_at":"2026-08-06T21:08:31.700915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08815","last_updated":"2022-05-06T10:05:52Z","snapshot_observed_at":"2026-07-06T11:01:05.577957Z","submitted_at":"2021-04-18T11:04:49Z","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","version":3},"cited_work":{"arxiv_id":"2104.08815","doi":null,"metadata_source":"pith","pith_arxiv_id":"2104.08815","snapshot_observed_at":"2026-08-06T21:08:31.831211Z","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","venue":"cs.CL","work_id":"5249e401-241e-4f0e-98a3-225416b62050","year":2021},"citing_paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T21:08:26.443175Z"},"links":{"cited_paper":"/paper/2104.08815","citing_paper":"/paper/2507.00920"},"observation_digest":"sha256:9efe54c611f83001804e4095861b30e91e1c007ded501caab79f13f5097b85a7","observation_id":"d7fdc2d4-54e9-49c9-82c3-f93f1c929ace","resolution":{"observed_at":"2026-08-06T21:08:31.870015Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.00920","last_updated":"2025-07-03T01:49:31Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T06:50:03.270678Z","submitted_at":"2025-07-01T16:26:20Z","title":"Privacy-Preserving Quantized Federated Learning with Diverse Precision"},"reference_resolution":{"displayed":53,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":44},"total_outbound_references":53},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 0 inbound Pith citation observations for arXiv:2507.00920."}