{"as_of":"2026-08-20T19:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bd303ea93f8b3857f3f269c7bbb5a8daa353d41b4eb1b948a61833f72104bd45","coverage":[{"denominator":63,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":63,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T23:45:41.679185Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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/2412.19989/citation-record","integrity":"/paper/2412.19989/integrity","json":"/paper/2412.19989/citation-record.json","paper":"/paper/2412.19989"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T23:45:42.640552Z","title":"Billion-scale feder- ated learning on mobile clients: A submodel design with tunable pri- vacy","venue":null,"work_id":"ba28cc65-63b3-4ebb-9c3d-a24a7a6a3b72","year":2020},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.396106Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:3cd747f1f2c76970719b308bd4150b28fea35190188218e9c559dd067ff58468","observation_id":"fd545326-425e-4469-bce3-0fa9b71523a8","resolution":{"observed_at":"2026-08-10T23:45:42.645079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.626279Z","title":"Aut- ofed: Heterogeneity-aware federated multimodal learning for rob ust autonomous driving","venue":null,"work_id":"5c6a6589-c55a-4972-943c-ce306b580d43","year":2023},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.401029Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:59c1de6da87d8e6cbc49ef169a8558af719978b49800f60d66bde4c8ebef77f1","observation_id":"2f59316d-465e-4bc6-96b7-536469d8987b","resolution":{"observed_at":"2026-08-10T23:45:42.631015Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.611979Z","title":"General data protection regulation — Wikipedia, the free encyclopedia, 2024","venue":null,"work_id":"ac77ebcc-36f5-44a0-9e3a-5de493f08031","year":2024},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.405727Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:46031667c7255e6326e8de2216a056f249c076473e6ab05b07bc33967151980b","observation_id":"b04dfb33-7533-40a3-8bd0-425ba804b8d9","resolution":{"observed_at":"2026-08-10T23:45:42.616828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.597222Z","title":"California consumer privacy act — Wikipedia, the free encyclopedia, 2024","venue":null,"work_id":"c2332b6b-6841-43be-b1f2-2d66f9e3a0a6","year":2024},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.410257Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:42bdef02236dab2d82143557f085cc9f5d0ff8554cfddb8757cbf6c1fbd0953a","observation_id":"fb118a55-ba91-4f4a-8cba-fafd3f5724c2","resolution":{"observed_at":"2026-08-10T23:45:42.601824Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.582243Z","title":"Communication-eﬃcient learning of deep net- works from decentralized data","venue":null,"work_id":"23760ac9-4d0c-49a1-8df8-e7357e61effe","year":2017},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.415075Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:51c662da449485471bbb3a94c8ac966c7210a9b4b7d01a126a3ce1b62f9f871c","observation_id":"310faefe-15b8-4354-979d-961a43434dc3","resolution":{"observed_at":"2026-08-10T23:45:42.587372Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.567179Z","title":"Yoga: Adaptive layer-wise model aggregation for decen- tralized federated learning","venue":null,"work_id":"c2b1647d-9fb8-41ca-8178-7ef9a2d21c46","year":2023},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.419846Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:94a16aeb224f84f253351da4d701c2328a078262cc36fa34f49990fb25e37b6e","observation_id":"c533cd64-9e49-490e-ae58-781c8c581b52","resolution":{"observed_at":"2026-08-10T23:45:42.572060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.552887Z","title":"Adaptive block-wise regularization and knowl- edge distillation for enhancing federated learning","venue":null,"work_id":"bb1c7d51-850e-4c0c-abf2-21e41d48a631","year":2023},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.424817Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:b36a2d748f55f9b7d838a2f8f025767a8c712ad26598b1e5a0969626314e70f1","observation_id":"1b9ed227-ed79-4fe2-b8a7-949107805b2d","resolution":{"observed_at":"2026-08-10T23:45:42.557687Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.538727Z","title":"Adaptive asynchronous federated learning in resource-constrained edge computing","venue":null,"work_id":"c37551bb-810b-4b0f-bbf1-54a2b51ba697","year":2021},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.429224Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:efd39a26dee0d28cf4cf08ba1f9cccf1deabdf068d6b4cf58899efe4f5162f71","observation_id":"f40d7671-b6fe-4c7d-ab4b-0ebaa1070a12","resolution":{"observed_at":"2026-08-10T23:45:42.543554Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.523873Z","title":"Fedmp: Federated learning through adaptive model pruning in heterogeneous edge computing","venue":null,"work_id":"98718137-59bc-4429-991a-adc906ac23ca","year":2022},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.433566Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:5ab93daa84a3340b9745ef09eb655a8529243b4cef4c647834350c1deff58574","observation_id":"4f3cd528-2de5-42ea-92f0-9f9425176ec2","resolution":{"observed_at":"2026-08-10T23:45:42.528555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.507804Z","title":"Bert: Pre-training of deep bidirectional transformers for language un- derstanding","venue":null,"work_id":"64ffe21d-59d8-48fa-b0b5-6f4df66d5c19","year":2019},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.438149Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:cffda0203719715c3976bef0c7d5cb692c8b97207fa5595b051ea8026df30823","observation_id":"cbe435f4-4d82-4d7d-b159-870198e90241","resolution":{"observed_at":"2026-08-10T23:45:42.513186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.492813Z","title":"Newsweeder: Learning to ﬁlter netnews","venue":null,"work_id":"71e6932f-c70d-480f-8add-76a18f0d87af","year":1995},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.442660Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:d8b0524833f1f9dc01545bd074ffd9a375f7d3c9eab7de298f6e777d34843ad7","observation_id":"cecbd5a7-f673-4406-a5b7-142e94802c06","resolution":{"observed_at":"2026-08-10T23:45:42.498025Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08815","last_updated":"2022-05-06T10:05:52Z","snapshot_observed_at":"2026-08-16T18:30:46.276818Z","submitted_at":"2021-04-18T11:04:49Z","title":"FedNLP: Benchmarking Federated Learning Methods for Natural Language Processing Tasks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08815","snapshot_observed_at":"2026-08-10T23:45:41.446862Z","title":"Fednlp: Benchmarking federated learn- ing methods for natural language processing tasks","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.446862Z"},"links":{"cited_paper":"/paper/2104.08815","citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:f6eea64b9feee73fd6d3fbf2bcb8035036d8316aa0bd761035aea0b3e8b066ff","observation_id":"0187a911-ca1f-43f0-8409-397c83c16e5e","resolution":{"observed_at":"2026-08-10T23:45:41.446862Z","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":"2026-08-10T23:45:42.477844Z","title":"Eﬃcient federated learning for modern nlp","venue":null,"work_id":"1a780ff7-4b30-404c-a7bb-769a27ea8e26","year":2023},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.452028Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:5f053808c24aa67b3c65c4761aebc0a3467b4235c6972c94d6f9dbf21aee282e","observation_id":"bee8d2ad-d865-4685-b524-f0bf81f8f3d2","resolution":{"observed_at":"2026-08-10T23:45:42.483119Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.462735Z","title":"Federated learning meets blockchain in edge computing: Oppor- tunities and challenges","venue":null,"work_id":"d79f3b8f-479c-4fd1-8f88-516c27eecc8b","year":2021},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.456603Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:3eff0de7fc89f8af72c5f17671a5e6de0cfb3c757b7b32a131da0808c1d3e0ad","observation_id":"52b1a553-1683-445e-8e1f-6b9fb29e4e51","resolution":{"observed_at":"2026-08-10T23:45:42.467379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.448160Z","title":"Advances and open problems in federated learning","venue":null,"work_id":"e5d0fdc0-bb32-4cc4-b4b2-880d14b9c79f","year":2021},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.461088Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:f3ad9126ce8d3de68a4f4688275f117a3ac1d7d522a9b014575d4fd3ff76e182","observation_id":"6225c973-f857-4261-a06c-79ac4b52ac15","resolution":{"observed_at":"2026-08-10T23:45:42.452844Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.433599Z","title":"Heterogeneity-aware federated learning with adaptive client selec- tion and gradient compression","venue":null,"work_id":"c8276042-2e5b-40b5-8b4e-2bb3953825fb","year":2023},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.465313Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:bc8d9eab15b64a2003f25c9b26b1fb58d415e982e4a3fa9f91a5f170ae6e1e89","observation_id":"d3a58248-8887-4b13-8711-f0d37eabf13d","resolution":{"observed_at":"2026-08-10T23:45:42.438260Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.419005Z","title":"Accelerating decentralized federated learning in heterogeneous edg e computing","venue":null,"work_id":"4909c076-6430-41ca-8491-53b0d54fe4c6","year":2023},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.469564Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:0130a47bceb83b0611bd951cbb40e01ef35466f72728d54e1384a580b975e264","observation_id":"4c40d160-0b1b-433a-ab0e-0e13b06f5f7a","resolution":{"observed_at":"2026-08-10T23:45:42.423913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.403903Z","title":"Optimizing federated learning on non-iid data with reinforcement learning","venue":null,"work_id":"e39594ce-43aa-4a95-abd5-64ba4b2d5b9a","year":2020},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.474126Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:1cd33a9493dbaa7cab1aec457e5209f4bbc8e105dbdf4bb8e8be89ad5615240b","observation_id":"c5e07571-697c-48ea-a195-64d1e48da94a","resolution":{"observed_at":"2026-08-10T23:45:42.408656Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.389394Z","title":"Enhancing federated learning with intelligent model migration in heterogeneous edge computing","venue":null,"work_id":"8656670b-06c2-4676-9f87-ae27e311c835","year":2022},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.478571Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:6b628ebc6b95e0dfc0cd3a6aac5c1148d1598b6a2606b28ebf46f73bffec4d96","observation_id":"237f1bf9-6d23-4fa8-b951-f5ac442872a3","resolution":{"observed_at":"2026-08-10T23:45:42.394238Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.374582Z","title":"Towards federated learning at scale: System design","venue":null,"work_id":"3b4c3d9f-7b8e-44ca-957b-eba732ba3bb6","year":2019},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.483158Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:01e9fadbc2b1a2fbd30de56c10cc54b6a1296267cb4b7f0bbed39f7bf0886482","observation_id":"b46a2e4b-a47b-426d-a897-f912a37e30d5","resolution":{"observed_at":"2026-08-10T23:45:42.379606Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.359965Z","title":"Op- timal rate adaption in federated learning with compressed commu- nications","venue":null,"work_id":"0ce7e7e8-9790-44e7-9fe7-b26e952d683c","year":2022},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.487656Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:46dac5c4c065ee8af74d73688a20e79e9245c613bc78bf534aa8390788ede362","observation_id":"e39675a0-74f7-48e2-b68d-3c6ee321fda1","resolution":{"observed_at":"2026-08-10T23:45:42.364740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.344898Z","title":"Deepreduce: A sparse-tensor communi- cation framework for federated deep learning","venue":null,"work_id":"80ae8e3a-2537-4d18-8a58-035e5636edf5","year":2021},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.492306Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:9c1cc5d2f663ae2743555d23355be7d301773b14967dfd850e6449fdfdd248ed","observation_id":"afd26656-e072-4ded-b62d-e542e1b110ac","resolution":{"observed_at":"2026-08-10T23:45:42.349808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.330671Z","title":null,"venue":null,"work_id":"68b7b155-4bcc-4d7c-82b4-dcc6ace0a5b8","year":2023},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.496976Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:7a1bce20626b1312f01dfe3fea5732390620862be0609aeb1e04e12c41ca11fe","observation_id":"2b2a4d7c-42b1-4cb2-ba3f-6a06d63e9bc3","resolution":{"observed_at":"2026-08-10T23:45:42.335148Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.315894Z","title":"signsgd: Compressed optimisation for non- convex problems","venue":null,"work_id":"f43a01f8-3714-4368-bee8-6cee3dad5156","year":2018},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.501482Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:b5e54757dea142330843941101a336edf7c07d9d68ff376a93e108b1fd95fb97","observation_id":"8670b4be-08e1-4ff9-9c44-8b8188f289de","resolution":{"observed_at":"2026-08-10T23:45:42.320603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.301104Z","title":"To talk or to work: Flexible communication compression for en- ergy eﬃcient federated learning over heterogeneous mobile edge devices","venue":null,"work_id":"5f9ade39-efc1-42a2-95a2-63786807a722","year":2021},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.505681Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:533f5b2607d58e0075c110f7a385cf5f520e42f2734ecaba44d609def15d0bea","observation_id":"f18e2584-c702-4d07-b507-1540902bca76","resolution":{"observed_at":"2026-08-10T23:45:42.305974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.286320Z","title":"Adaptive control of local updating and model compres- sion for eﬃcient federated learning","venue":null,"work_id":"a980ce86-422d-42cd-b012-a2607d485652","year":2022},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.510023Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:66040343698919eec8229007fb5651f2a12c264aa57fa4f8ca6b5fff3928b214","observation_id":"1db302aa-e29c-4b40-a5a5-5a20b0eca164","resolution":{"observed_at":"2026-08-10T23:45:42.291147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.270639Z","title":"Resource- adaptive federated learning with all-in-one neural composition","venue":null,"work_id":"75d7976d-3b72-4198-9a86-a37df9d12669","year":2022},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.514209Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:7d9d45d0987d45d8aab2e85c1bc91d671868488e295c1bfe1fe81d44abef3b1b","observation_id":"9dd190c9-8a57-436c-9f4a-a346ce1bc8ed","resolution":{"observed_at":"2026-08-10T23:45:42.276038Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.254211Z","title":"Communication-eﬃcient federated learning for heterogeneous edge devices based on adapt ive gradient quantization","venue":null,"work_id":"492fd661-bb00-4555-b626-dd76e7597ef3","year":2023},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.518668Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:3f12e680e18cfeaacbd8f63ac57496085f68bf5161b1773f51c2475dbb62085c","observation_id":"07c58ba3-cd85-451e-9366-65d19071b67a","resolution":{"observed_at":"2026-08-10T23:45:42.259688Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.238944Z","title":"Peaches: Personalized federated learning with neural ar- chitecture search in edge computing","venue":null,"work_id":"be163850-4ca2-458e-bdaf-e4c018d597f5","year":2024},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.523693Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:543c1e22f18e52dc7636b1afe38ca355124247c214cfa0a30dbc8c10dbbb040e","observation_id":"eadca8d7-2b32-4c6b-a97d-b6374cf3cdaa","resolution":{"observed_at":"2026-08-10T23:45:42.244001Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2305.19229","last_updated":"2023-05-30T17:20:51Z","snapshot_observed_at":"2026-08-17T22:52:56.719704Z","submitted_at":"2023-05-30T17:20:51Z","title":"FedDisco: Federated Learning with Discrepancy-Aware Collaboration","version":1},"cited_work":{"arxiv_id":"2305.19229","doi":null,"metadata_source":"pith","pith_arxiv_id":"2305.19229","snapshot_observed_at":"2026-08-10T23:45:41.746517Z","title":"FedDisco: Federated Learning with Discrepancy-Aware Collaboration","venue":"cs.LG","work_id":"5a7137b8-3fe0-4f6f-9c00-0f94de921b4d","year":2023},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.528071Z"},"links":{"cited_paper":"/paper/2305.19229","citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:6a82d12bb7cbe977d2fa2174f74d77ceca9e1105d0209a7befa38b1d58293df6","observation_id":"e700ba7e-d345-4b21-ab47-a9c56aaa67a5","resolution":{"observed_at":"2026-08-10T23:45:41.753950Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.223594Z","title":"Bose: Block-wise federated learning in hetero- geneous edge computing","venue":null,"work_id":"fdf2cea7-136b-475c-a7bc-bb425787ab78","year":2023},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.532737Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:1263b8747c6231714843c3bd66e1caf6e7380352c636cca9177077558c0f24fd","observation_id":"e67cde5e-3c08-48e6-98b3-84f9036242da","resolution":{"observed_at":"2026-08-10T23:45:42.228507Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.208540Z","title":"Eﬃcient mini-batch training for stochastic optimization","venue":null,"work_id":"48730900-4b77-40ec-ba28-c46fc4551925","year":2014},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.537019Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:11a8db73d48419918f7bf1367a6ad8e110a01b234cec4da2a69644cd96e06ce6","observation_id":"67ef57b2-0bd8-4d61-acff-d45eeb1f91e7","resolution":{"observed_at":"2026-08-10T23:45:42.213293Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1909.06335","last_updated":"2019-09-13T17:26:20Z","snapshot_observed_at":"2026-08-16T05:00:17.345539Z","submitted_at":"2019-09-13T17:26:20Z","title":"Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1909.06335","snapshot_observed_at":"2026-08-10T23:45:41.541495Z","title":"Measuring the eﬀects of non-identical data distribution for federated visual class iﬁ- cation","venue":null,"work_id":null,"year":1909},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.541495Z"},"links":{"cited_paper":"/paper/1909.06335","citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:29b60ade1b3e00864253f4589b7d6542a9374849e56632f2590ce04a2b0fa512","observation_id":"cb59f31c-9848-469b-92b0-9031f48fb8e3","resolution":{"observed_at":"2026-08-10T23:45:41.541495Z","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":"2026-08-10T23:45:42.193250Z","title":"Bayesian nonparamet- ric federated learning of neural networks","venue":null,"work_id":"6b6d4d02-9137-4018-84e2-676fd7c87879","year":2019},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.546325Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:ee04a821bedd00e01d328772ab145732742dddb2ff5a1b0ba3b592fdedc627d8","observation_id":"61690f8c-c694-4337-a55e-ba244c336e32","resolution":{"observed_at":"2026-08-10T23:45:42.198458Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.550860Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.550860Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:4649b2a4649f6952293d9c9b6dc1dc45720ae48843eb6bc45f8aac79deb5b69c","observation_id":"d5321a4b-9e66-4edb-b5fb-68fbf878b70c","resolution":{"observed_at":"2026-08-10T23:45:41.550860Z","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":"2026-08-10T23:45:42.168585Z","title":"Pyramidﬂ: A ﬁne-grained client selection framework for eﬃcient federated learn- ing","venue":null,"work_id":"4d9ee325-5def-4b3b-b609-b6d3a30716bc","year":2022},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.555208Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:5113168ab93655ddebb7ae6546bbdefcfc4285a9affab9b26996b9df1f9d4bdf","observation_id":"7229561b-7423-4aa9-a632-e0420fb11e97","resolution":{"observed_at":"2026-08-10T23:45:42.173347Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.153639Z","title":"Oort: Eﬃcient federated learning via guided participant selec- tion","venue":null,"work_id":"317fe0b2-29d4-4f58-8ce4-41988ae66e6c","year":2021},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.560032Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:ff66d2e07aa186955b7810fc174e17e825f11a34102e5755bd4d8457d3a7a674","observation_id":"72f75ba9-5dc2-4ab0-a4c4-d8c712766b16","resolution":{"observed_at":"2026-08-10T23:45:42.158542Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.138113Z","title":"The convergence of sparsi- ﬁed gradient methods","venue":null,"work_id":"57e35df7-0153-4869-883e-0d1824676e36","year":2018},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.564352Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:c097c62e88596099173ff8207c1fd32dc82b91e89e07e39fec59de67e44fd129","observation_id":"900f83fa-1592-4790-ad60-e5ab01cf50ad","resolution":{"observed_at":"2026-08-10T23:45:42.143768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.122794Z","title":"Mergesﬂ: Split federated learning with feature merging and batch size regulation","venue":null,"work_id":"dbb040f3-e49e-4507-9591-de4a4a79d84c","year":2024},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.568663Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:c7bda2687021d2ae49e6369aaf07fcd4b6e2640777fd7a6bc668697f263d2875","observation_id":"0d57c6ca-2e62-4ad0-9eb8-3667df39026a","resolution":{"observed_at":"2026-08-10T23:45:42.127981Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.108419Z","title":"Approximating the kull- back leibler divergence between gaussian mixture models","venue":null,"work_id":"9fc978fd-b52a-4ad2-8130-70bc0ee6a1f8","year":2007},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.573140Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:ccc7b299bca11ec5b5466ff103be30d06b73d2b01458118f33a58d3834d72bee","observation_id":"a0bd52d9-0413-431c-95d6-b9937dcd8d29","resolution":{"observed_at":"2026-08-10T23:45:42.113166Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.093194Z","title":"An eﬃcient image similarity measure based on approximations of kl-divergence between two gaussian mixtures","venue":null,"work_id":"b8ab2777-96ae-4fd4-9439-c159e1f3a313","year":2003},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.577432Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:44c2faf8fbbf03dc4948235025b9a85da6e244a67a41c4eeac2ae39ce7ea1fb9","observation_id":"65cf4ca3-0f78-44fa-97ad-04608ec8c271","resolution":{"observed_at":"2026-08-10T23:45:42.098127Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.078365Z","title":"Adaptive batch size for federated learning in resource-constrained edge computing","venue":null,"work_id":"d4240e0c-6107-4f0e-98fb-324185666992","year":2023},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.581822Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:e405b27f2ace1d7162875dd92c5c7cc3146d66ca31b8273fa8709550b10f8514","observation_id":"10fab5a6-04b4-4d8a-af44-ac73c626671c","resolution":{"observed_at":"2026-08-10T23:45:42.083259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.063494Z","title":"Pytorch: An imperative style, high- performance deep learning library","venue":null,"work_id":"1fbf55be-ed63-47c4-b1ef-b3b001c792b0","year":2019},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.586008Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:0e7a0ab8f0548e16074a86bd53ae9f8ff15d7d49d9691ac69a618f5c84d8dfc3","observation_id":"dcf43e84-d793-449a-ae0b-239a2d775ec0","resolution":{"observed_at":"2026-08-10T23:45:42.068494Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.048414Z","title":"Mnn: A universal and eﬃcient inference engine","venue":null,"work_id":"f7c04f6f-affb-442c-b58a-f6fb113fe95c","year":2020},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.590578Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:90c65f4430de25753d7954d82229a45660ece3e13443c6f494841b8167f6daf3","observation_id":"4d4e5faa-6fef-4ecf-a405-67a03f6624be","resolution":{"observed_at":"2026-08-10T23:45:42.053404Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.033270Z","title":"Building a virtual system of systems using docker swar m in multiple clouds","venue":null,"work_id":"4aec1ec1-d27b-479e-9a12-79b9c48758ea","year":2016},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.595231Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:f1789e9061c3a69a075023d403ff7a28e882161c78b2272ca99b4712028f745c","observation_id":"4500ab8c-a2dc-4f5d-9836-6096eb5d7dee","resolution":{"observed_at":"2026-08-10T23:45:42.038292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.018395Z","title":"mpi4py: Status update afte r 12 years of development","venue":null,"work_id":"7e8f0457-b12a-4c00-8c6e-3c1e4abf023f","year":2021},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.599590Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:9c17f767d8c7da3500914c72860a8796f663949b54d1373fc1eb7ec46d745a4d","observation_id":"7eae45a8-a9d3-4320-bb5a-833a08fe3775","resolution":{"observed_at":"2026-08-10T23:45:42.023386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:42.003495Z","title":"Array programming with numpy","venue":null,"work_id":"4e021bce-236a-4ed0-b2a3-ce3aed73d59f","year":2020},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.603888Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:68435ce34ddcc9741ce0cdac3f521ebf3fcc00336ba86c89afc5f9cbd4456940","observation_id":"e73aa9d0-38c3-40a5-86ed-b862a0b80f01","resolution":{"observed_at":"2026-08-10T23:45:42.008465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.988695Z","title":"Learning multiple layer s of features from tiny images","venue":null,"work_id":"44d7b1f3-5722-4165-8625-3059954f292d","year":2009},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.608224Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:2f5463d4b18b372ebc388f41e482ce45a9145649ffad339fc26d8789197b887d","observation_id":"51961f7f-411a-42fe-b77d-2beadf4cab50","resolution":{"observed_at":"2026-08-10T23:45:41.993506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.973339Z","title":"A public domain dataset for human a c- tivity recognition using smartphones","venue":null,"work_id":"cbfd38c7-c689-47d2-bbdc-da29b877feea","year":2013},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.612846Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:0788f7f2d91d39ab0be83738d9ce07fa3a6f4f3ccd2ef38fd7815f3ce29b30f1","observation_id":"7c571963-8b89-450b-afd3-bd6059f1ff30","resolution":{"observed_at":"2026-08-10T23:45:41.978344Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1804.03209","last_updated":"2018-04-09T19:58:17Z","snapshot_observed_at":"2026-08-15T16:28:51.252929Z","submitted_at":"2018-04-09T19:58:17Z","title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1804.03209","snapshot_observed_at":"2026-08-10T23:45:41.617585Z","title":"Speech commands: A dataset for limited-vocabu lary speech recognition","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.617585Z"},"links":{"cited_paper":"/paper/1804.03209","citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:239f362d47c4fab8f82157eb994ed7aea911a1bfc9dd48c92d18ef72949a0eea","observation_id":"fca04295-7c46-489a-9383-ff404561f85d","resolution":{"observed_at":"2026-08-10T23:45:41.617585Z","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":"2026-08-10T23:45:41.958270Z","title":"Bitwidth heterogeneous federated learning with progressive weight dequantization","venue":null,"work_id":"d6883598-6319-49a7-b114-084cb50566c8","year":2022},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.622169Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:0025acd3d2f120e3307393ace7b5161c1701ab1476a178542c68a652300a130b","observation_id":"4b82c127-be5d-4dfe-af1e-9724d69cabc8","resolution":{"observed_at":"2026-08-10T23:45:41.963289Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.943714Z","title":"Towards eﬃcient communications in fed- erated learning: A contemporary survey","venue":null,"work_id":"8d67c70d-b9ef-4f67-8c2e-3633a2523d3e","year":2023},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.626618Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:cadd095f1a0e8b7d8ccf19a58584afcd0970e4dd2f5ad5d9466de35fdf5f42c2","observation_id":"7613dc71-05b3-4200-bbc7-e452af41d0ec","resolution":{"observed_at":"2026-08-10T23:45:41.948654Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.928739Z","title":"Dadaquant: Doubl y- adaptive quantization for communication-eﬃcient federated learning","venue":null,"work_id":"c31c596e-5187-485f-8776-6f6910b1d455","year":2022},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.631425Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:fc3685a53e129b474efae173369e081e742094f26a7c2176594314ba356e6ff9","observation_id":"d2a960a4-5c9b-4ed3-96ce-43f9ca91cd92","resolution":{"observed_at":"2026-08-10T23:45:41.933371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.913855Z","title":"Qsgd: Communication-eﬃcient sgd via gradient quantization and encoding","venue":null,"work_id":"57bca3d5-0ff8-47d5-a416-2237aca9eae4","year":2017},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.635719Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:318ba5d43b05df93f0cb6828bfe7eb12df64ce1c03cbe94123398e10546f81ce","observation_id":"33116ca4-9117-4c85-9df6-f6544490d1ac","resolution":{"observed_at":"2026-08-10T23:45:41.918708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.898599Z","title":"Robust and communication-eﬃcient federated learning from non-iid data","venue":null,"work_id":"d8c8633c-0324-4dcf-94ae-07cf004d69e5","year":2019},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.640453Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:34e5e14a04fb8d8c2dc82fe18fefeb1fde761372c8f813dba08ba362b90f1604","observation_id":"93d899ce-2e14-4638-9825-fce88ebf3b02","resolution":{"observed_at":"2026-08-10T23:45:41.903714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.882583Z","title":"Fjord: Fair and accurate fed- erated learning under heterogeneous targets with ordered dropout","venue":null,"work_id":"68bf8b78-c850-4ddf-b24a-e8a9553b2680","year":2021},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.644759Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:113cb03819a7fd19f417cfde6433b24fff5149db917d5d0f20c6af06c545acce","observation_id":"7bccc519-8b16-455e-a1a4-a2b1ad91ce50","resolution":{"observed_at":"2026-08-10T23:45:41.888133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.866337Z","title":"Heteroﬂ: Computation and communication eﬃcient federated learning for heterogeneous clients","venue":null,"work_id":"bd9b212e-779a-4966-8d66-390dfdebc660","year":2020},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.649157Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:6a70ce7a2f63ee5d1b01e0040ad807536fa6f96110d27ad201e72ee31bc911e0","observation_id":"64d0f591-80ac-4b41-9b82-9307f9d6925a","resolution":{"observed_at":"2026-08-10T23:45:41.871302Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.851322Z","title":"Svdfed: Enabling communication-eﬃcient federated learning via singular- value-decomposition","venue":null,"work_id":"36bcb7f7-4a19-4e24-8313-dadc27cb1ccc","year":2023},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.654016Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:2d3a19b74395b37c7fbdb18725a0c0d233ac7922aa3fd8d92b4ff67aa318d736","observation_id":"4237dd76-50ca-4f99-a1a1-c59ebc5922d0","resolution":{"observed_at":"2026-08-10T23:45:41.856193Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.836133Z","title":"Fedpara: Low- rank hadamard product for communication-eﬃcient federated learn- ing","venue":null,"work_id":"7f959c1b-afb7-4c4b-99e7-3d065d1a6d1d","year":2021},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.658863Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:076e86ce9a547925e0123381c2330ef7778eec32cc86f0dfb5ff49ba9449153a","observation_id":"71e8d022-9c3e-4421-aa52-65a9166729e0","resolution":{"observed_at":"2026-08-10T23:45:41.840930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.821334Z","title":"Hermes: an eﬃcient federated learning framework for heterogeneous mobile clients","venue":null,"work_id":"b1a65cb4-83cc-4e3e-b8b2-32757a122f0b","year":2021},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.663201Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:0f8bfbf8e26b2174590ba70035a24cb715be137667937f0e24c7c0eb40175fb3","observation_id":"c52a4786-f987-42ad-a1b7-1956d5d59d29","resolution":{"observed_at":"2026-08-10T23:45:41.826070Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.805093Z","title":"When edge meets learning: Adaptive control for resource-constrained distributed ma- chine learning","venue":null,"work_id":"26a205b2-3dc9-42e7-b073-a4e67a3c60d7","year":2018},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.668654Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:4c0f26c3a7865ee3fe3b4ec4026f7720e8c7c7240ec9b1aea8e07141f88b3bde","observation_id":"881a61b1-3a1f-4608-aed0-e80107fe275f","resolution":{"observed_at":"2026-08-10T23:45:41.811245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T23:45:41.673482Z","title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.673482Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:b4facd83bf6677539a9c283506559354dff508c48ff7d507f0b726eafad809d5","observation_id":"f0828192-251a-421a-b913-9e2e82d6ee61","resolution":{"observed_at":"2026-08-10T23:45:41.673482Z","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":"2026-08-10T23:45:41.780567Z","title":"Tackling system and statistical heterogeneity for feder ated learning with adaptive client sampling","venue":null,"work_id":"b5e03577-fc01-4825-91c8-43c062c167ea","year":2022},"citing_paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-10T23:45:41.679185Z"},"links":{"citing_paper":"/paper/2412.19989"},"observation_digest":"sha256:3e5e714ab38092721d1cd3f30a4a1d2946efeb6e2a9022806322d78729ebce1e","observation_id":"fe07a42d-bfc7-4ae0-b811-13cdb5ec4a60","resolution":{"observed_at":"2026-08-10T23:45:41.785815Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.19989","last_updated":"2024-12-28T03:20:36Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T11:13:44.559381Z","submitted_at":"2024-12-28T03:20:36Z","title":"Caesar: A Low-deviation Compression Approach for Efficient Federated Learning"},"reference_resolution":{"displayed":63,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":6,"verified_exact":1,"verified_fuzzy":56},"total_outbound_references":63},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 0 inbound Pith citation observations for arXiv:2412.19989."}