{"as_of":"2026-08-19T18:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c6e6a0520e78e9171c96693df84aa09349848f3c256efee93138176fa482541b","coverage":[{"denominator":61,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":61,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-18T15:24:04.079011Z","state":"measured"},{"denominator":62,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":62,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-08T05:02:18.746700Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-05-11T21:36:13.686374Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"cited_work":{"arxiv_id":"2509.17398","doi":null,"metadata_source":"pith","pith_arxiv_id":"2509.17398","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","venue":"cs.NI","work_id":"6dab681c-f067-486a-bbb1-174620a909d0","year":2025},"citing_paper":{"arxiv_id":"2605.06027","last_updated":"2026-05-07T11:17:45Z","snapshot_observed_at":"2026-07-06T23:18:31.432422Z","submitted_at":"2026-05-07T11:17:45Z","title":"FluxShard: Motion-Aware Feature Cache Reuse for Collaborative Video Analytics in Mobile Edge Computing","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-08T05:02:18.746700Z"},"links":{"cited_paper":"/paper/2509.17398","citing_paper":"/paper/2605.06027"},"observation_digest":"sha256:eab47040ea57c45def84c1d88f62bf41332592819575558a8c0336606e19a147","observation_id":"dbe98b53-b2cc-4996-a74d-eb43c185b32a","resolution":{"observed_at":"2026-05-11T21:36:13.692687Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2509.17398/citation-record","integrity":"/paper/2509.17398/integrity","json":"/paper/2509.17398/citation-record.json","paper":"/paper/2509.17398"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"2023 edge AI technology report","venue":null,"work_id":"17e8a5d5-c9c0-4953-9504-e420aac7bf9b","year":2023},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:dd6bb2408e9ae57c923edba1d31d6127183c310ab55c68d2538375522b75c76c","observation_id":"3ec27c48-4c78-4e64-86ac-75d262b216f4","resolution":{"observed_at":"2026-05-18T15:26:34.441330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"MADRL-based model partition- ing, aggregation control, and resource allocation for cloud-edge-device collaborative split federated learning","venue":null,"work_id":"d65be621-76f9-4dae-93f9-f6338ac2b00c","year":2025},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:c0465c6f846c1fcfc46662a24e9a4a0c3377ce0304264fc7a7ce4f0762256fc1","observation_id":"f603b4f7-3251-44cc-affb-7f487a07acaf","resolution":{"observed_at":"2026-05-18T15:26:34.445086Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Split learning over wireless networks: Parallel design and resource management","venue":null,"work_id":"f54beb72-c110-4f79-85f2-662d6f2e0832","year":2023},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:583cc74481459a45217f49a18c30eae73aace91d2805bee5dcea47e0352e96cb","observation_id":"f71314d3-68b4-4d71-93cc-0511a9946db5","resolution":{"observed_at":"2026-05-18T15:26:34.408576Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2505.04368","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-01T11:55:42.411652Z","title":"Pipelining split learning in multi-hop edge networks","venue":null,"work_id":"fef62cac-4ec9-4cb6-8a5f-baea6e392d53","year":2025},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:e9e62146dab3b76e12bc1c1812302f4d731bdae588744758790251777e0a9d36","observation_id":"3ab017ee-d5eb-4ea7-b39c-3c286065a6bb","resolution":{"observed_at":"2026-05-18T15:26:33.759984Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Spectrum breathing: Protecting over-the-air federated learning against interference","venue":null,"work_id":"c472242d-5a89-4e11-8234-23041eb3a3d8","year":2024},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:9df190c3c49585207069d01a9a54b6a007322232311abc954432771dae147b62","observation_id":"237502f1-0631-486c-a5d2-d8d3c44ee280","resolution":{"observed_at":"2026-05-18T15:26:34.380029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"3U: Joint design of UA V-USV-UUV networks for cooperative target hunting","venue":null,"work_id":"8ddaa2f3-57b5-446e-9fd9-4366cfb8a811","year":2023},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:deb9c192c83e03092d18506fcf39cb12d15a5b62140f0cff3066f86b69b77ab8","observation_id":"3c2a5a05-427e-4884-b9cc-fed9a0a3ba20","resolution":{"observed_at":"2026-05-18T15:26:34.459514Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Underwater differential game: Finite-time target hunting task with communication delay","venue":null,"work_id":"45b6e1ba-13b4-45e7-aa3d-338f849bac2c","year":2022},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:95df37bc5f7205d586b38ec28945d7b31680b7a46e469504d3f3522839a2194a","observation_id":"a2573c2e-76ce-40a4-b2e9-603192c0b7f9","resolution":{"observed_at":"2026-05-18T15:26:34.466217Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Differential game-based deep reinforcement learning in underwater target hunting task","venue":null,"work_id":"aa24f399-610c-44d3-9d15-de299fd37d62","year":2025},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:ac0d1dca941e3a3fa96aad0baf5b4cf047853b554bf9b0a7a08d9a5efd224b88","observation_id":"99560d55-ca82-4d69-a50c-c96b7138f691","resolution":{"observed_at":"2026-05-18T15:26:34.373409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"NVIDIA Jetson Xavier","venue":null,"work_id":"826640de-db35-49ed-a246-d74b4532266a","year":2019},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:68ee56e0a0eda822bc06fea218d03911348e77b6376c9cc0d27020b5414d10b9","observation_id":"d6a11164-5a22-4bc3-8b2e-0b2a3a74a03a","resolution":{"observed_at":"2026-05-18T15:26:34.424028Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Split Learning for Health: Distributed Deep Learning Without Sharing Raw Patient Data","venue":null,"work_id":"93f9e269-71e4-46e3-90e9-25b3a0f03cba","year":2019},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:0cd41b0acbbf3b0e70902c7d4a5ae05098de52b846f66ec830eb4df2cae7fde3","observation_id":"542c3f82-7dc5-49a1-be8a-26ce153ed520","resolution":{"observed_at":"2026-05-18T15:26:34.449035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Split Learning in 6G Edge Networks","venue":null,"work_id":"11c595a9-6e3e-44bf-ae37-2e68a8b97131","year":2024},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:d4489a6baf954c8993e5e521987dd0520623f6d5c7f36ba8ece4fa4faf76d25d","observation_id":"ce4b2f3c-8f12-49a2-ae91-5b4963136939","resolution":{"observed_at":"2026-05-18T15:26:34.386638Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Pairingfl: Efficient federated learning with model splitting and client pairing","venue":null,"work_id":"f3846c6e-5286-4284-af88-2e3848369dad","year":2025},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:560d86b75334e8516277fec81241a7f62ddceeaba447528101dd4a16eb3b9218","observation_id":"8a48b149-99b0-44dc-9841-f81712320753","resolution":{"observed_at":"2026-05-18T15:26:34.405258Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Efficient parallel split learning over resource-constrained wireless edge networks","venue":null,"work_id":"f708df5b-fa39-46be-98b2-e35ca3f5ed02","year":2024},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:caddb621cf9ed73719b27b71f316e5d167ec5079e3b015e54d8450b6de28fbb0","observation_id":"6937e0a8-2972-4931-8166-93cfb4a30e4a","resolution":{"observed_at":"2026-05-18T15:26:34.402188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Leo-split: A semi-supervised split learning framework over leo satellite networks","venue":null,"work_id":"e0f16658-f2cd-4823-8fae-a6a040f6ea73","year":2025},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:b18e6aae86eb8d8c2c8ed64206d9777b636fcc5cad962862671f7eaca76ff24c","observation_id":"258a4c42-3c68-4b13-b94e-99e76ab6bea1","resolution":{"observed_at":"2026-05-18T15:26:34.370250Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Federated learning: Challenges, methods, and future directions","venue":null,"work_id":"9b83166f-5e13-49a5-aaca-1d1cb0771678","year":2020},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:e586207a44b3a5293cbe4945784f4cbae6da9d4dcafcda8d15c5dfc9ede7c328","observation_id":"da46627a-5382-40d8-bdc2-1ad6f4809439","resolution":{"observed_at":"2026-05-18T15:26:34.360043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Fedsn: A federated learning framework over heterogeneous leo satellite networks","venue":null,"work_id":"d947dd0d-7e0f-4c9c-bb84-1e8050ed8291","year":2024},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:417b72b044fb166cf39db78eea221d81580c6968db3856bfc7206ed02e0e511e","observation_id":"6aec83a4-c823-4a9b-9c45-cf6cfa66a368","resolution":{"observed_at":"2026-05-18T15:26:34.416181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1610.05492","last_updated":"2017-10-30T20:52:14Z","snapshot_observed_at":"2026-08-13T17:19:46.488095Z","submitted_at":"2016-10-18T09:11:51Z","title":"Federated Learning: Strategies for Improving Communication Efficiency","version":2},"cited_work":{"arxiv_id":"1610.05492","doi":null,"metadata_source":"pith","pith_arxiv_id":"1610.05492","snapshot_observed_at":"2026-07-04T19:50:10.985326Z","title":"Federated Learning: Strategies for Improving Communication Efficiency","venue":"cs.LG","work_id":"dbe54fa3-b463-4453-844f-8aba26dcf434","year":2016},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"cited_paper":"/paper/1610.05492","citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:ebcd7470af7c477b1bf2658cbc5a652f7dff61bb5616e17fb5c06edc48c844fb","observation_id":"32b5bf43-40f9-4436-b1af-8780d23371f0","resolution":{"observed_at":"2026-05-18T15:26:33.792288Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Splitfed: When federated learning meets split learning","venue":null,"work_id":"cac70f2e-50da-4def-941f-409d23922186","year":2022},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:a530d20e8ef293f4b8e4b0bb8ec5b0b72b1fe0dbb39715855194e86f10a2bf3e","observation_id":"5a0f7072-0538-467d-813d-0f6c1e2ba2d1","resolution":{"observed_at":"2026-05-18T15:26:34.392738Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.08426","last_updated":"2025-06-10T04:00:01Z","snapshot_observed_at":"2026-08-13T23:43:25.145426Z","submitted_at":"2025-06-10T04:00:01Z","title":"HASFL: Heterogeneity-aware Split Federated Learning over Edge Computing Systems","version":1},"cited_work":{"arxiv_id":"2506.08426","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.08426","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Hasfl: Heterogeneity- aware split federated learning over edge computing systems","venue":null,"work_id":"749b88de-2e35-42fd-912f-b45c10c1cd4d","year":2025},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"cited_paper":"/paper/2506.08426","citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:4baf92527b37410431d51b294269a089cfa14d368ef6182cb5a2286c5f07cdcf","observation_id":"c06dbd26-60a5-42e0-ab7e-5ba5fd6845fb","resolution":{"observed_at":"2026-05-18T15:26:33.745801Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Wireless distributed learning: A new hybrid split and federated learning approach","venue":null,"work_id":"36942528-431c-4f34-9870-7989aaa3089c","year":2023},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:b2df148d3294687bac458763de9f8a124881ab78547490f2aa6743fc86205c66","observation_id":"be6399a9-e092-42d8-b6fa-628924710a32","resolution":{"observed_at":"2026-05-18T15:26:34.438239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.02795","last_updated":"2025-05-05T17:09:19Z","snapshot_observed_at":"2026-08-19T00:13:38.877984Z","submitted_at":"2025-05-05T17:09:19Z","title":"HSplitLoRA: A Heterogeneous Split Parameter-Efficient Fine-Tuning Framework for Large Language Models","version":1},"cited_work":{"arxiv_id":"2505.02795","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.02795","snapshot_observed_at":"2026-07-03T11:58:06.025426Z","title":"Hsplitlora: A heterogeneous split parameter- efficient fine-tuning framework for large language models","venue":null,"work_id":"abc7d472-ce98-4b8a-9bc9-10a0992fee5a","year":2025},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"cited_paper":"/paper/2505.02795","citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:57aeaa98d2147e6c0280d7b5a7a3b3cad57c6cea935e66c76735866eb884159f","observation_id":"044d148c-8c73-4f1f-9f57-0d7be1200d1e","resolution":{"observed_at":"2026-05-18T15:26:33.751108Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Federated learning in mobile edge networks: A comprehensive survey","venue":null,"work_id":"97230ee9-e92f-43de-b076-c65b39004c67","year":2031},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:aee44915a1c376dfadded2fac9dd9d96922cfa59326a2523356b7d1eaa89f587","observation_id":"505cb576-abf2-4ad5-bed4-b2a03ed1346b","resolution":{"observed_at":"2026-05-18T15:26:34.389757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Fed- erated learning under heterogeneous and correlated client availability","venue":null,"work_id":"f098c48f-a10b-45ae-b8f6-5277ce68a2c4","year":2024},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:e17ca2e41bd96e758956af0efb8461c39e45c15f6ef61accd15a912f515b20b7","observation_id":"90b0081b-6506-44b6-ab4d-a1ad26015126","resolution":{"observed_at":"2026-05-18T15:26:34.501889Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2412.17231","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"FedMeld: A model-dispersal feder- ated learning framework for space-ground integrated networks","venue":null,"work_id":"7415019c-d132-45cd-94bc-f9eaf3458ad2","year":2024},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:6f300ca4c6a7a925bd5bcc616f610a97287bff515cb95f86d608403220c0e0d5","observation_id":"e502b2ea-8c45-40c3-b4e7-cf86172feb25","resolution":{"observed_at":"2026-05-18T15:26:33.805001Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Accelerating federated learning with model segmentation for edge networks","venue":null,"work_id":"f75b02aa-c950-4a8c-8de8-799a828c989c","year":2024},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:4101717ad4e7e1b7aa476428e9892b9dd2e1980ee4a1a4900e6e98e64a672bd6","observation_id":"e888af87-d67e-4fa6-85f6-02b67072bde5","resolution":{"observed_at":"2026-05-18T15:26:34.395849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Smart split-federated learning over noisy channels for embryo image segmentation","venue":null,"work_id":"ff68b84f-7b8c-41f5-9fbf-5f09b0e2075e","year":2023},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:9309f6e21159ae001e64d7c490467b5ef392dbf4ce8c8315c28e9b9abd49f05c","observation_id":"d2f7f724-b21d-4d7a-8d71-1cb2d988f598","resolution":{"observed_at":"2026-05-18T15:26:34.356345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"SplitFed resilience to packet loss: Where to split, that is the question","venue":null,"work_id":"2e800d99-0a5a-484c-8f7b-b2f4da4d9eb4","year":2023},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:afc6f0cff8bf4501674672a66c5e8d4cf2cc4e2018f185b4757dbe4b88cb0435","observation_id":"e642ab64-1da0-4999-98de-db997ff55aef","resolution":{"observed_at":"2026-05-18T15:26:34.452554Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":"09fbe9f7-2faa-4827-97fc-76174afe776f","year":2017},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:30d966e8975f10a2787b8872f850f99a33a46f6d44b231b35a217339aeeeb921","observation_id":"9d8dfd48-820d-4408-a3bd-4524e498ab17","resolution":{"observed_at":"2026-05-18T15:26:34.398867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Cooperative SGD: a unified framework for the design and analysis of local-update sgd algorithms","venue":null,"work_id":"a3b78a1d-5669-4618-9581-e600cb5eb976","year":2021},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:7a1834d24f6ce76c317bc529dd4ade7af13fe9d1f8d5a4998f9ef0973f296a01","observation_id":"ff83b55d-db8a-466f-a4fb-dafa27a9ad82","resolution":{"observed_at":"2026-05-18T15:26:34.469329Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Graph oracle models, lower bounds, and gaps for parallel stochastic optimization","venue":null,"work_id":"9c0934e0-5da1-42d4-8dde-c457d534dd66","year":2018},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:ebbdc50bbe9c19a701a495f8d99950fc76f264e97e4b3a940a9de2c684df08fd","observation_id":"e098f5fa-ef47-499a-9870-5084705f5049","resolution":{"observed_at":"2026-05-18T15:26:34.491849Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Federated learning over wireless networks: Convergence analysis and resource allocation","venue":null,"work_id":"2ded0884-4f1d-4b4c-b9d4-a90b465c9794","year":2021},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:0fc34c3f714ea3bf9fc93e3e8233b28f24ee8a0eb541941182c246ef3a7b59e7","observation_id":"01ad84ba-4989-4ba4-b294-78a086f70120","resolution":{"observed_at":"2026-05-18T15:26:34.383577Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.01243","last_updated":"2020-10-03T01:04:17Z","snapshot_observed_at":"2026-08-16T19:16:12.111735Z","submitted_at":"2020-10-03T01:04:17Z","title":"Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies","version":1},"cited_work":{"arxiv_id":"2010.01243","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.01243","snapshot_observed_at":"2026-07-03T00:07:27.814732Z","title":"Client selection in federated learning: Convergence analysis and power-of-choice selection strategies","venue":null,"work_id":"498e6c2b-ac56-4d50-b6c1-b1d8efaf81e1","year":2010},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"cited_paper":"/paper/2010.01243","citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:75e269278491d15286735cdf86f28a578b781da55165b98d94af6a5aadec764b","observation_id":"1bc55b9b-dbbb-477f-9aec-e41afbded25d","resolution":{"observed_at":"2026-05-18T15:26:33.771784Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.13723","last_updated":"2022-08-22T15:38:15Z","snapshot_observed_at":"2026-08-17T12:06:47.084175Z","submitted_at":"2020-10-26T17:05:13Z","title":"Optimal Client Sampling for Federated Learning","version":3},"cited_work":{"arxiv_id":"2010.13723","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.13723","snapshot_observed_at":"2026-07-03T00:07:27.802978Z","title":"Optimal client sampling for federated learning","venue":null,"work_id":"2d52c910-06e6-43d7-8a00-bd7d9fe93ad4","year":2010},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"cited_paper":"/paper/2010.13723","citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:1f6f09c8053e3347188aa6a7a79d777c91cb37f8dd963bb7074dd1d1b753f6dd","observation_id":"7e87d133-6fd2-4b16-a5e9-5e68d63f03e7","resolution":{"observed_at":"2026-05-18T15:26:33.786095Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Federated learning under impor- tance sampling","venue":null,"work_id":"ab68f0ef-1b5d-474c-b9c6-ca712927b3d4","year":2022},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:f5448f129d5130c74cbb8c4794f057ca1871f2add2b65712828be76ab6c3d74c","observation_id":"df4dd5dc-2f90-4428-9888-64cc1cf2056b","resolution":{"observed_at":"2026-05-18T15:26:34.482172Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Towards understanding biased client selection in federated learning","venue":null,"work_id":"7ff9e1cb-f43e-40bf-ba03-8d16c9c5d101","year":2022},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:9ac4096d28adb084881374f016fa044ee0a21317f173548df54ce7fbb5564e2b","observation_id":"5862dbe3-f364-45d2-931f-a36332aaaa78","resolution":{"observed_at":"2026-05-18T15:26:34.363331Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Clustered sampling: Low-variance and improved representativity for clients selection in federated learning","venue":null,"work_id":"10746cc0-ae62-44e6-97b0-2e530e14d9fb","year":2021},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:99586b65b59b3f4ddae45c29f9e4692d0a00d82d1f2fcea71ffc852254c502f7","observation_id":"81ae1d54-99b0-401b-a490-ee17b16b931b","resolution":{"observed_at":"2026-05-18T15:26:34.462555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Heterogeneity-guided client sampling: Towards fast and efficient Non-IID federated learning","venue":null,"work_id":"969c7d8c-65a1-4b4c-94c8-ebb7de466ad2","year":2024},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:e2afbb90c6bdfcc337993ddf8bdeddef53ff4c1d7a8435769f87fe39e6000f40","observation_id":"8e73e250-e092-4007-b8ad-d6aff0220e97","resolution":{"observed_at":"2026-05-18T15:26:34.485402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Tackling system and statistical heterogeneity for federated learning with adaptive client sampling","venue":null,"work_id":"7f3e07c3-786b-4fa5-b68f-2a25de55ba78","year":2022},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:0107c25d35077319048aadb32c66bd30d131af29c33af21575671ee460180a69","observation_id":"a22f1134-cedc-43f8-862b-e8bf87a01c75","resolution":{"observed_at":"2026-05-18T15:26:34.430674Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Eiffel: Efficient and fair scheduling in adaptive federated learning","venue":null,"work_id":"b5a8a676-6c67-470b-9744-d5a9ec59ee91","year":2022},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:4ad766923caf308239d8d8d14f7261386eb12df33c47e19a1e6a41fc46d71604","observation_id":"6714c528-6bc9-4f5e-aabc-70eb7c88d655","resolution":{"observed_at":"2026-05-18T15:26:34.494826Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Ultra-low- latency edge inference for distributed sensing","venue":null,"work_id":"b7a7bf44-a29b-4999-ab55-42e873185c4b","year":2024},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:71bbc5f44135fa923f452f606cbf94f74c15e7c76f26faa334a5591903345b97","observation_id":"2e68aa7f-6d70-4e3e-bec5-745aa3575acb","resolution":{"observed_at":"2026-05-18T15:26:34.427237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2504.03686","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T11:06:53.271324Z","title":"Revisiting outage for edge inference systems","venue":null,"work_id":"1dc32033-a4c6-4116-8256-70fff5fd0ea0","year":2025},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:050f4dd55c1dc7a7d18fed7e46e01a156842f33735345b75b1f39750d18b1a20","observation_id":"5c1ee379-0dd3-42c0-bf35-56c138a8eb05","resolution":{"observed_at":"2026-05-18T15:26:33.765849Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Adaptsfl: Adaptive split federated learning in resource-constrained edge networks","venue":null,"work_id":"09de95a0-6d7d-4b7d-b9b2-06acf51a6b6c","year":2025},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:07c83b1df7b30f6b16acb4dc8a37aa1fadfb4b53e6f5ec9a860e34db0ae426e8","observation_id":"8d2a68b6-27d0-46d4-b2dd-8293f3f4df66","resolution":{"observed_at":"2026-05-18T15:26:34.455838Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Hierarchical split federated learning: Convergence analysis and system optimization","venue":null,"work_id":"ad4ab180-6672-424f-a613-2792d364ae62","year":2025},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:179ce22dbd3147fce62dd78b1d31bbd92d694654cd2488f8b06338a6b8737ca3","observation_id":"f3e4ed7c-99b0-4e28-b208-e0ce2ff114c9","resolution":{"observed_at":"2026-05-18T15:26:34.411970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Accelerating split federated learning over wireless communication networks","venue":null,"work_id":"874ced47-fb10-4a79-9985-13bcca47c267","year":2024},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:d21013ad0ec36b768a69fdb5d3fd53e6200cfa0f19c2e34d5414ffd71c7cdb75","observation_id":"5507b370-9011-4382-8aff-9fd44d876dbd","resolution":{"observed_at":"2026-05-18T15:26:34.420581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Unleashing the tiger: Inference attacks on split learning","venue":null,"work_id":"e6e85d44-d6bf-4793-a39c-9f4bdd80c731","year":2021},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:df2154102144f3322b4692005d0f0b13cc8073bccc045620f084760d19a0ca42","observation_id":"a9f2b48b-8b84-4ff5-91f3-ca2581f59199","resolution":{"observed_at":"2026-05-18T15:26:34.472415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"SCAFFOLD: Stochastic controlled averaging for federated learning","venue":null,"work_id":"bb72a519-ee85-47a1-9395-56f16cff708e","year":2020},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:2ef3b0678489d06e2e73914f95dcc137794ee756e6e3174ea3633070e5ed30fa","observation_id":"a65cd979-9e07-4840-81a2-4ec2fc38124a","resolution":{"observed_at":"2026-05-18T15:26:34.475579Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"On the conver- gence of fedavg on Non-IID data","venue":null,"work_id":"3a94e89d-2e8a-4b3c-bfa8-6a7f1e8a89e0","year":2020},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:09e2d9b4ff0a8082ae35c242cc8cc60f0f86203908b53222084ad55454a8462d","observation_id":"5f6896ab-361e-445b-ae23-0e187606b14f","resolution":{"observed_at":"2026-05-18T15:26:34.434669Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Achieving linear speedup with partial worker participation in non-iid federated learning","venue":null,"work_id":"d8080e49-a44d-446f-a39d-efff6c02600e","year":2021},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:2db98f1910776f04b150c7fe9d61ca0883021d0d6cde75a2509b8b9ec738d766","observation_id":"cbec7a1a-382a-4027-80fa-0a5de3c1c225","resolution":{"observed_at":"2026-05-18T15:26:34.478712Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Resource constrained vehicular edge federated learning with highly mobile connected vehicles","venue":null,"work_id":"c8513f75-1acb-44dd-ada9-0e99a538f2a1","year":2023},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:33193d4024550072558e34ca7a9f7657d61e64b4b19e764590e16c8975344f2c","observation_id":"d8e5c454-e47e-4895-a5c7-4cd45a4004ba","resolution":{"observed_at":"2026-05-18T15:26:34.498379Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15166","last_updated":"2025-01-09T11:39:19Z","snapshot_observed_at":"2026-08-16T14:15:59.162403Z","submitted_at":"2024-02-23T07:59:23Z","title":"Convergence Analysis of Split Federated Learning on Heterogeneous Data","version":3},"cited_work":{"arxiv_id":"2402.15166","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.15166","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Convergence anal- ysis of split federated learning on heterogeneous data","venue":null,"work_id":"744fa578-a092-4dcc-8e13-17e3d5fa93be","year":2025},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"cited_paper":"/paper/2402.15166","citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:8f05856a2632775ae84ee31afdc757357224d3fe92cb9a5edb21a050075cad49","observation_id":"295f34fe-a6f5-4cbf-8a45-dd695a665244","resolution":{"observed_at":"2026-05-18T15:26:33.740762Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"On the convergence of local stochastic compositional gradient descent with momentum","venue":null,"work_id":"1906d826-9cdb-4a80-b9e1-509354c7a1f4","year":2022},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:7abb723b1bd3a1ef8fa832b238ca79c10599abaec24ef1290ad18cf90becdd59","observation_id":"4f4f3b8c-909a-4c14-8eef-127136cd4c81","resolution":{"observed_at":"2026-05-18T15:26:34.376865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.15601","last_updated":"2025-08-22T10:51:55Z","snapshot_observed_at":"2026-08-17T07:59:10.502866Z","submitted_at":"2025-07-21T13:24:38Z","title":"Optimal Batch-Size Control for Low-Latency Federated Learning with Device Heterogeneity","version":2},"cited_work":{"arxiv_id":"2507.15601","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.15601","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Optimal batch-size control for low-latency federated learning with device heterogeneity","venue":null,"work_id":"df56623d-0734-4644-a4d7-2f60fa1ed9aa","year":2025},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"cited_paper":"/paper/2507.15601","citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:a0be4b7811e8f537c36be7d818b6c3c05a69d4205846d49b71b3c84f60be17d6","observation_id":"b85938c2-440d-4ebc-a1dd-467dd5a1bb8e","resolution":{"observed_at":"2026-05-18T15:26:33.777262Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Adaptive heterogeneous client sampling for federated learning over wireless networks","venue":null,"work_id":"7ce35340-3bad-4de8-bca9-c2f34dc91e70","year":2024},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:aacfbf90ec9b62f16d533e07470418a0eaf39c8ad557ebe1c7a8312d9550a294","observation_id":"36dd018f-8414-4b63-a9bb-afc99f92d986","resolution":{"observed_at":"2026-05-18T15:26:34.366525Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"A bisection method for systems of nonlinear equations","venue":null,"work_id":"dccd1e19-bf1f-484f-a355-662407bf8fc2","year":1984},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:ba38fad55e4a03cb6c52dd9bcd9c880b2c8f4923d3b3bdc76955f0cf2a979866","observation_id":"5852b79f-b04b-4bfb-bdc8-81635d70ba45","resolution":{"observed_at":"2026-05-18T15:26:34.488590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1702.05373","last_updated":"2017-03-01T08:55:36Z","snapshot_observed_at":"2026-08-15T04:39:39.680366Z","submitted_at":"2017-02-17T15:06:14Z","title":"EMNIST: an extension of MNIST to handwritten letters","version":2},"cited_work":{"arxiv_id":"1702.05373","doi":"10.48550/arxiv.1702.05373","metadata_source":"pith","pith_arxiv_id":"1702.05373","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"EMNIST: an extension of MNIST to handwritten letters","venue":"cs.CV","work_id":"86fc316d-b762-434e-8af4-868553442be7","year":2017},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"cited_paper":"/paper/1702.05373","citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:fe83b13455ea683533ba8c09a065395d7f62ffffeb265a59886cf2a11e0a0770","observation_id":"5ac8f303-341d-49c7-a570-e957a2d66c22","resolution":{"observed_at":"2026-05-18T15:26:33.799540Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-07-14T21:20:03.548926+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-14T21:20:03.548926+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Gradient-based learning applied to document recognition","venue":null,"work_id":"d7f7398f-48e6-4394-ac14-f9e4c9d2c6c3","year":1998},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:aa14954121703a8c85772037ad97a3d079259be1c09704fa5b91be1ab1af215b","observation_id":"0226d041-ce0a-4d18-83ae-140918e630e1","resolution":{"observed_at":"2026-05-18T15:26:34.343261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Deep residual learning for image recognition","venue":null,"work_id":"c731b213-c068-4cc9-868e-07e845046dbf","year":2016},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:54733f948b8023c7d79ce07cdb8195bddd079697115f9a495f25535a0d6dbf6d","observation_id":"5c52b4f9-e4a1-44ae-be25-7b85bf5e8ed1","resolution":{"observed_at":"2026-05-18T15:26:34.340555Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.05138","last_updated":"2025-04-21T18:13:21Z","snapshot_observed_at":"2026-08-19T10:25:47.000511Z","submitted_at":"2025-04-07T14:43:17Z","title":"Towards Optimal Heterogeneous Client Sampling in Multi-Model Federated Learning","version":3},"cited_work":{"arxiv_id":"2504.05138","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.05138","snapshot_observed_at":"2026-07-03T00:07:27.794690Z","title":"Towards optimal heterogeneous client sampling in multi-model feder- ated learning","venue":null,"work_id":"5eaed267-1766-407d-894c-52413b6f21a9","year":2025},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"cited_paper":"/paper/2504.05138","citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:40f1da20147463757d2bc934d70890c10fec75920bdd3716109aebbe60dd5d48","observation_id":"9b0da58f-9023-4447-af46-f9a9625901ba","resolution":{"observed_at":"2026-05-18T15:26:33.735807Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Adaptive federated learning in resource constrained edge com- puting systems","venue":null,"work_id":"3802cb1e-e885-44a3-aef5-1dd332b98763","year":2019},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:59e5d9c883f4691616259d96784a8f388e1e03fe1e107aa6f68a2f1b95febcc7","observation_id":"ab2851a4-f638-4cb4-9aec-15cda198ad4b","resolution":{"observed_at":"2026-05-18T15:26:34.352828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"DTS: A simulator to estimate the training time of distributed deep neural networks","venue":null,"work_id":"abe4e3f3-4248-4a0f-b940-b704db82b144","year":2023},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:0b9717232fca0cce5be93cff0718a1053707deab455fd03e0339cdf19b63362b","observation_id":"6c1bc0d3-aa5d-4988-a773-901180df2c09","resolution":{"observed_at":"2026-05-18T15:26:34.349492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-06-05T21:23:00.469572Z","title":"Modeling forecast errors for microgrid operation using Gaussian process regression","venue":null,"work_id":"5606eaf1-f71b-43dc-a800-0153064b4dec","year":2024},"citing_paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation","version":2},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-05-18T15:24:04.079011Z"},"links":{"citing_paper":"/paper/2509.17398"},"observation_digest":"sha256:86ac83abe4f96e3392bbde59d5ea46a3fdb96cbee7386d51adc164fa5ff2386a","observation_id":"64994bff-427f-4a02-9d8a-5565b9195554","resolution":{"observed_at":"2026-05-18T15:26:34.346155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.17398","last_updated":"2026-04-08T13:39:21Z","latest_version":2,"primary_category":"cs.NI","snapshot_observed_at":"2026-08-16T17:40:17.466000Z","submitted_at":"2025-09-22T06:57:46Z","title":"Optimizing Split Federated Learning with Unstable Client Participation"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":12,"verified_fuzzy":49},"total_outbound_references":61},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 1 inbound Pith citation observation for arXiv:2509.17398."}