{"as_of":"2026-08-14T19:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:95c6f527130ce90aa5708085e952e0e03dea84a20e6975ab83f1f6bc048d6d69","coverage":[{"denominator":49,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":49,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T05:51:35.206944Z","state":"measured"},{"denominator":51,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":51,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T09:17:04.893967Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T11:58:06.039986Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"cited_work":{"arxiv_id":"2603.18540","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2603.18540","snapshot_observed_at":"2026-08-04T03:26:38.495535Z","title":"Gapsl: A gradient-aligned parallel split learning on heterogeneous data","venue":null,"work_id":"5178339c-486e-4830-9208-42eccd0b7a17","year":2026},"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":10,"source":"pdf_text","source_observed_at":"2026-05-08T05:02:18.746700Z"},"links":{"cited_paper":"/paper/2603.18540","citing_paper":"/paper/2605.06027"},"observation_digest":"sha256:5cb5ea44e4dfbe21c3d045e6ba91275b0f90a021b3d6057d71d0a2a13f05a16d","observation_id":"ab603f52-2399-4bf8-83dd-c84a8e49a6cf","resolution":{"observed_at":"2026-08-04T03:26:38.495535Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"cited_work":{"arxiv_id":"2603.18540","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2603.18540","snapshot_observed_at":"2026-08-04T03:26:38.495535Z","title":"Gapsl: A gradient-aligned parallel split learning on heterogeneous data","venue":null,"work_id":"5178339c-486e-4830-9208-42eccd0b7a17","year":2026},"citing_paper":{"arxiv_id":"2606.11803","last_updated":"2026-06-10T08:35:31Z","snapshot_observed_at":"2026-08-13T09:07:13.092258Z","submitted_at":"2026-06-10T08:35:31Z","title":"SwarmSense-DNN: A Trustworthy and Decentralized Neural Framework for Proactive Anomaly Defense in Consumer IoT","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-27T09:17:04.893967Z"},"links":{"cited_paper":"/paper/2603.18540","citing_paper":"/paper/2606.11803"},"observation_digest":"sha256:df19eadbb101d4fbaf1e08a7c455de20d21ecef1f3cc8381796cd2fb931fb7c4","observation_id":"a7090875-2aca-474f-a200-4774c99731b7","resolution":{"observed_at":"2026-08-04T03:26:38.495535Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2603.18540/citation-record","integrity":"/paper/2603.18540/integrity","json":"/paper/2603.18540/citation-record.json","paper":"/paper/2603.18540"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.034229Z","title":"FedMobile: Enabling Knowledge Contribution-aware Multi-modal Federated Learning with Incomplete Modalities,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.034229Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:4d5e2ec6a099de52d8c4435ad2ad5a5615395fe7fbbc2da26386062ab0d49186","observation_id":"06482a07-4d10-45b5-b989-417dde0274a6","resolution":{"observed_at":"2026-08-04T05:51:35.034229Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2508.09085","last_updated":"2025-08-12T17:07:27Z","snapshot_observed_at":"2026-08-12T07:20:07.542418Z","submitted_at":"2025-08-12T17:07:27Z","title":"Dynamic Uncertainty-aware Multimodal Fusion for Outdoor Health Monitoring","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2508.09085","snapshot_observed_at":"2026-08-04T05:51:35.038721Z","title":"Dynamic Uncertainty-Aware Multimodal Fusion for Outdoor Health Monitoring,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.038721Z"},"links":{"cited_paper":"/paper/2508.09085","citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:3b45aa8b9c2b566a3dda3498e55dd8a6fa6fd0691cb434de098df8a9f998669a","observation_id":"a617e691-d180-4d00-9760-b1e80c316ba1","resolution":{"observed_at":"2026-08-04T05:51:35.038721Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.042957Z","title":"LLMs and IoT: A Comprehensive Survey on Large Language Models and the Internet of Things,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.042957Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:898f62e5f8ffbbcfaeb2ae4653288c27c872923e077d1540d7b3315306abd4dc","observation_id":"ec6bb66d-f8ed-4ea2-8daf-96207b37c515","resolution":{"observed_at":"2026-08-04T05:51:35.042957Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.046856Z","title":"Hfedmoe: Resource-Aware Heterogeneous Federated Learning with Mixture-of-Experts,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.046856Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:d203ae5e06d73a38343f9e7e8ae445137c9ef005b552c6fe0863ee2dcf0d65fd","observation_id":"46860495-ffe3-42c8-8899-afc4ea6d5544","resolution":{"observed_at":"2026-08-04T05:51:35.046856Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.050531Z","title":"Unleashing the Power of Continual Learning on Non-centralized Devices: A Survey,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.050531Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:9895a06a5ea0d2ff5dedd35695a0280b76d7eba5ab329612ae01dee0a4e2ffd5","observation_id":"20ec99f7-2f71-4a9a-81a0-376190e11387","resolution":{"observed_at":"2026-08-04T05:51:35.050531Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.054242Z","title":"Centralized and Federated Learning for Predictive VNF Autoscaling in Multi-domain 5G Networks and Beyond,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.054242Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:a57ca62e859f6fac9b02298ee9c489a270de9b95793dad963da93a3fbf048b85","observation_id":"be61621c-01a3-44ab-b2da-641a049d45a6","resolution":{"observed_at":"2026-08-04T05:51:35.054242Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.058409Z","title":"Social-aware Federated Learning: Challenges and Opportunities in Collaborative Data Training,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.058409Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:86cfb0b3b889c5aeb382fa771e99d7a4763a509f6d2db90b217e78020a22a205","observation_id":"324ac001-ab2d-4096-9b7f-f8c76e0e17ff","resolution":{"observed_at":"2026-08-04T05:51:35.058409Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.062008Z","title":"Automated Federated Pipeline for Parameter-efficient Fine-tuning of Large Language Models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.062008Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:ec096fa37bb4a6d138fbee8c4d03db7526d40cde9df324324a15a306f3697fac","observation_id":"aca5f0e5-e735-4fce-b39f-740f6157c234","resolution":{"observed_at":"2026-08-04T05:51:35.062008Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.065429Z","title":"Amount of Data Created, Consumed, and Stored 2010-2023, with Forecasts to 2028,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.065429Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:0ff484f358320fc35ead1260c92a35a76aef036db7bb6c97f216cdc2aac3cd3f","observation_id":"4a123d27-edd0-4470-8e96-85dc8b45370d","resolution":{"observed_at":"2026-08-04T05:51:35.065429Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.068959Z","title":"Optimizing Parameter Mixing Under Constrained Communications in Parallel Federated Learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.068959Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:6314039b4c492888d7e3f2dd316a9e5b7932ca36db59c74836db4b458a09346c","observation_id":"4d011092-7507-4914-95c5-b5cb474b99b3","resolution":{"observed_at":"2026-08-04T05:51:35.068959Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.072534Z","title":"Actions at the Edge: Jointly Optimizing the Resources in Multi-access Edge Computing,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.072534Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:9298347ef3819776ebbbde34fa806bbde8b20bb71e9b687f6aac7a0bf1a18808","observation_id":"58c0e176-6409-479c-910b-d9f4ef0a5ce1","resolution":{"observed_at":"2026-08-04T05:51:35.072534Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.076346Z","title":"Communication-efficient Learning of Deep Networks From Decentralized Data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.076346Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:6d9a9d048360187401a1e1c66cd2a6cd7e1d4f723c75d9e685f3be9d9ecda98a","observation_id":"41f3c745-d304-46b5-a5dc-d7829df8018c","resolution":{"observed_at":"2026-08-04T05:51:35.076346Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1610.05492","snapshot_observed_at":"2026-08-04T05:51:35.079665Z","title":"Federated Learning: Strategies for Improving Communication Efficiency,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.079665Z"},"links":{"cited_paper":"/paper/1610.05492","citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:46405cf904e709774eda32ac8a0518b347d5517042545e6bd5431df902b0aac8","observation_id":"2d59688b-69dd-444e-b77c-0343c87ed8fa","resolution":{"observed_at":"2026-08-04T05:51:35.079665Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.083394Z","title":"Accelerating Federated Learning with Model Segmentation for Edge Networks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.083394Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:980df08cd07f6986b08c7ed7fe835117d398bf35c832d06981f022a5b80f6316","observation_id":"3b99140c-a18b-410c-869d-4764a2a8e572","resolution":{"observed_at":"2026-08-04T05:51:35.083394Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.086691Z","title":"Optimizing Personalized Federated Learning through Adaptive Layer-Wise Learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.086691Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:bc987fc8a986df2d3c711cf8e5878fff6f889e026418ae463aadd86f2a8f7854","observation_id":"2f80e888-64d1-4508-aa2b-26a2d8281aad","resolution":{"observed_at":"2026-08-04T05:51:35.086691Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.090045Z","title":"Trust Management of Tiny Federated Learning in Internet of Unmanned Aerial Vehicles,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.090045Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:a2c68bd77798c3bc1adfc1068a9981973f623ed1334b894db8bfaa13d42338cd","observation_id":"af7cce26-67a5-49b7-a595-295cebe72f96","resolution":{"observed_at":"2026-08-04T05:51:35.090045Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.02795","last_updated":"2025-05-05T17:09:19Z","snapshot_observed_at":"2026-08-14T01:34:31.494084Z","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":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.02795","snapshot_observed_at":"2026-08-04T05:51:35.093371Z","title":"HSplitLoRA: A Heterogeneous Split Parameter- Efficient Fine-Tuning Framework for Large Language Models,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.093371Z"},"links":{"cited_paper":"/paper/2505.02795","citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:9a374640dafaf226d889fdf7dcfd68444cf079f8ea1f7714f52a6bcdab3245bb","observation_id":"1706cc11-de11-4fcc-9502-5c2b14a9440a","resolution":{"observed_at":"2026-08-04T05:51:35.093371Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.096993Z","title":"Split learning over Wireless Networks: Parallel Design and Resource Management,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.096993Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:bb0c4cedfa17aa45ecf70179473fbac1c47e261ee5b01845409d21442515905e","observation_id":"335eace6-ffda-44b7-ad2c-d43920547877","resolution":{"observed_at":"2026-08-04T05:51:35.096993Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-04T05:51:35.100407Z","title":"Gemini: A Family of Highly Capable Multimodal Models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.100407Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:a49aae7d89d73c8b2faf5efa55416316c0e3be8ade66405f0b4f3ad9bd296f48","observation_id":"eb3773e6-c299-41f3-be90-66e77966e5e2","resolution":{"observed_at":"2026-08-04T05:51:35.100407Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.104043Z","title":"HASFL: Heterogeneity- aware Split Federated Learning over Edge Computing Systems,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.104043Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:5080bd2cb9a78aa3d057126f49c330550b51ff200f744ea88e8f14d52c7fa227","observation_id":"14a64b17-245e-457e-9606-a6f3e835cb0d","resolution":{"observed_at":"2026-08-04T05:51:35.104043Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.107614Z","title":"Splitfed: When Federated Learning Meets Split Learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.107614Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:cdb5664702c1d2d22120ece039cb27ce57b325867a685a7f143ee5d97ef8fb4a","observation_id":"5e76bea7-ebe8-40ee-a58b-093af3f65e35","resolution":{"observed_at":"2026-08-04T05:51:35.107614Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.110948Z","title":"Unleashing the Tiger: Inference Attacks on Split Learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.110948Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:59908fabef4e53d37c4209c0a9c9a347f6fe952b333cf1ca9c71e8d8a8476118","observation_id":"9c522793-dc2b-4660-b62f-582a9834a611","resolution":{"observed_at":"2026-08-04T05:51:35.110948Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.114287Z","title":"Efficient Parallel Split Learning over Resource-constrained Wireless Edge Networks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.114287Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:6057f5e63d9a31622a0a4f7302ef2f257a1d1dd5f305531170043a71be9651d0","observation_id":"dcec8f1d-8acd-40eb-a2b4-1b33ed26c34c","resolution":{"observed_at":"2026-08-04T05:51:35.114287Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.117646Z","title":"NSC-SL: A Bandwidth-Aware Neural Subspace Compression for Communication-Efficient Split Learning,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.117646Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:8fac395e017dfd011188592df46986f6d331a64eec7f971abd91fbf7cf7aab2e","observation_id":"c8ff5dc4-37eb-4a37-8890-a99a5069c267","resolution":{"observed_at":"2026-08-04T05:51:35.117646Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.121215Z","title":"ESL-LEO: An Efficient Split Learning Framework over LEO Satellite Networks,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.121215Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:0ac0e5404f92a7eb92687492de99090e20c9cc7a2387d9937de1626836d3bfd4","observation_id":"a9948f85-39cd-4e26-8f05-333f6149ae5e","resolution":{"observed_at":"2026-08-04T05:51:35.121215Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.06107","last_updated":"2022-12-12T18:29:40Z","snapshot_observed_at":"2026-08-13T16:33:01.710347Z","submitted_at":"2022-12-12T18:29:40Z","title":"A Bargaining Game for Personalized, Energy Efficient Split Learning over Wireless Networks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.06107","snapshot_observed_at":"2026-08-04T05:51:35.124731Z","title":"A Bargaining Game for Personalized, Energy Efficient Split Learning over Wireless Networks,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.124731Z"},"links":{"cited_paper":"/paper/2212.06107","citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:994e3bf4e4447b15d37f780339fa86a92fe66d5b32b1bf686b26d11c4573c654","observation_id":"3bf8587e-c54a-44a4-980c-8f3fad7e1f46","resolution":{"observed_at":"2026-08-04T05:51:35.124731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.09246","last_updated":"2021-09-19T22:57:23Z","snapshot_observed_at":"2026-08-10T16:47:47.760394Z","submitted_at":"2021-09-19T22:57:23Z","title":"Splitfed learning without client-side synchronization: Analyzing client-side split network portion size to overall performance","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.09246","snapshot_observed_at":"2026-08-04T05:51:35.128499Z","title":"Splitfed Learning Without Client-side Synchronization: Analyzing Client- side Split Network Portion Size to Overall Performance,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.128499Z"},"links":{"cited_paper":"/paper/2109.09246","citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:1e46e9eb0713f330fa8ea8ac9a7ce3fe605989a3dc410c4cc4ac3ef7d85dc6d2","observation_id":"a037f134-6f4a-4b68-9b75-49880e536333","resolution":{"observed_at":"2026-08-04T05:51:35.128499Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.132456Z","title":"Split Learning in 6G Edge Networks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.132456Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:046b923a57608d1e11128915a3def236ee8f8225024611eaea89c256a58c8531","observation_id":"f49d3d7e-5248-4eb4-b236-fa47fe55d6c2","resolution":{"observed_at":"2026-08-04T05:51:35.132456Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.136144Z","title":"Towards Collaborative Fairness in Federated Learning Under Imbalanced Covariate Shift,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.136144Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:2bc14eefb782ae697b6edff5c80e44536bfa82aa233928e00a516da3b7ebef0e","observation_id":"ccea7dbc-c560-4544-bd0d-14e1eadb6a7e","resolution":{"observed_at":"2026-08-04T05:51:35.136144Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.139606Z","title":"FedCiR: Client-invariant Representation Learning for Federated Non-IID Features,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.139606Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:5634c4a3344ea020b5d5d605437e50fe099e6e5cde7abbdf6fd99e9633967383","observation_id":"5e7b6514-ff4a-42d5-8d0c-2306b9682450","resolution":{"observed_at":"2026-08-04T05:51:35.139606Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.143057Z","title":"FedASA: A Personalized Federated Learning with Adaptive Model Aggregation for Heterogeneous Mobile Edge Computing,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.143057Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:86572437732880301963fd01216c23aff0cb6784a88daa12cc5e843e8ba6475f","observation_id":"5f487b45-d7e0-4dc9-91d0-5433a8e865a7","resolution":{"observed_at":"2026-08-04T05:51:35.143057Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.146755Z","title":"Very Deep Convolutional Networks for Large-scale Image Recognition,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.146755Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:e991a326c1dde122183af0cd40d8e33f101424683bf18f60cbe21e8cb53ef4c4","observation_id":"5449b80d-05fc-4f7d-83f2-b7882b66d682","resolution":{"observed_at":"2026-08-04T05:51:35.146755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.150253Z","title":"Learning Multiple Layers of Features From Tiny Images,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.150253Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:3f85d915959d8358ab7f740092283dbd172104d49ff5b65cd0f269235f4e78d6","observation_id":"5cc88647-816c-4162-a9db-91e81a6f999f","resolution":{"observed_at":"2026-08-04T05:51:35.150253Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.153671Z","title":"Faster Convergence on Heterogeneous Federated Edge Learning: An Adaptive Clustered Data Sharing Approach,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.153671Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:5377ace4a75080bd4f773475913ff49cbd6d45752bf54dca79067704d2e3da68","observation_id":"971c7c02-3c87-4117-8059-c8dcb78b5b7b","resolution":{"observed_at":"2026-08-04T05:51:35.153671Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.157106Z","title":"LEO-Split: A Semi-supervised Split Learning Framework over LEO Satellite Networks,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.157106Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:91878c190049f6d38b0164ecc6a2273efef2207ebedea83ada252441ad054d10","observation_id":"99717386-404d-42c1-9041-5f234d0eaf72","resolution":{"observed_at":"2026-08-04T05:51:35.157106Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.161091Z","title":"Multi-level Personalized Federated Learning on Heterogeneous and Long-tailed Data,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.161091Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:4d4b05b6b5b72e4f2e1f9acb464f5617382eb5c1bf7957174236b80eb9a74aff","observation_id":"e29bfccb-6376-439b-8e3e-21374aadb14b","resolution":{"observed_at":"2026-08-04T05:51:35.161091Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.164483Z","title":"AOCC-FL: Federated Learning with Aligned Overlapping via Calibrated Compensation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.164483Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:c6184d721e888cce04e56289db49347ea2fabc6abd0ce9fa1d1764a3e850daad","observation_id":"65686420-ef65-48e7-91b6-13deeed7c5d7","resolution":{"observed_at":"2026-08-04T05:51:35.164483Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.167887Z","title":"Profit Allocation for Federated Learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.167887Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:1b8978f6e7e9d2fa55e5b0551abaec1828d237ca9df828afba1745f2dc434144","observation_id":"249bc8b9-f61c-4ea3-9917-f7a7e39b2311","resolution":{"observed_at":"2026-08-04T05:51:35.167887Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.171346Z","title":"GOFL: An accurate and efficient federated learning framework based on gradient optimization in Heterogeneous IoT systems,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.171346Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:4281d2cf96796b26418b331937566ffa82bee818a3fea5ce1d5a9f7e0ac5aec8","observation_id":"c03842c0-6fb0-4aae-b695-921b94864b26","resolution":{"observed_at":"2026-08-04T05:51:35.171346Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.175090Z","title":"NVIDIA Jetson Embedded Systems Developer Kits and Mod- ules","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.175090Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:91df9ab1307306f1953bcff01c47e868f319e77ece8ca6dea14de0cb9ac2fe93","observation_id":"47c5986a-360f-408f-beaf-281aecf5ac29","resolution":{"observed_at":"2026-08-04T05:51:35.175090Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.178574Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.178574Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:abba76125ac2d146f5e71cffbaa784f534a083d23aacb29a501ce4c8e3607821","observation_id":"94e8af30-e3ed-42fa-bc2a-5876ab41478f","resolution":{"observed_at":"2026-08-04T05:51:35.178574Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00564","last_updated":"2018-12-03T05:43:20Z","snapshot_observed_at":"2026-08-14T17:49:43.940153Z","submitted_at":"2018-12-03T05:43:20Z","title":"Split learning for health: Distributed deep learning without sharing raw patient data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00564","snapshot_observed_at":"2026-08-04T05:51:35.181942Z","title":"Split Learning for Health: Distributed Deep Learning without Sharing Raw Patient Data,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.181942Z"},"links":{"cited_paper":"/paper/1812.00564","citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:039ba143de0016046b6d3d0fcb492a588588678758a266a4fcb1736cd41401c6","observation_id":"710c9888-2a9d-465e-a161-f37b86098f6c","resolution":{"observed_at":"2026-08-04T05:51:35.181942Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.05929","last_updated":"2021-12-11T08:33:25Z","snapshot_observed_at":"2026-08-13T17:17:45.751032Z","submitted_at":"2021-12-11T08:33:25Z","title":"Server-Side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.05929","snapshot_observed_at":"2026-08-04T05:51:35.185665Z","title":"Server-side Local Gradient Averaging and Learning Rate Acceleration for Scalable Split Learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.185665Z"},"links":{"cited_paper":"/paper/2112.05929","citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:c9ba04b00b05894cb87644599b4aaebc3d5a5fbd733409176734acf7b37961e3","observation_id":"4abfd08b-a7c8-4023-a706-1775e257a35e","resolution":{"observed_at":"2026-08-04T05:51:35.185665Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.189565Z","title":"Adaptsfl: Adaptive Split Federated Learning in Resource-constrained Edge Networks,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.189565Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:82e7c085505b012d6adb9db5aa2e690a6ad279f266a31c05d0537c447a4d99c0","observation_id":"91d9a870-d476-482e-88bd-453e7b8e960f","resolution":{"observed_at":"2026-08-04T05:51:35.189565Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.193010Z","title":"Hierarchical Split Federated Learning: Convergence Analysis and System Optimization,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.193010Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:1668837678da3978249293a4f4f453f691d913506c400f122eb0d4582b47f21b","observation_id":"75fe1666-f424-426d-8732-3ffabca3bbdb","resolution":{"observed_at":"2026-08-04T05:51:35.193010Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.196427Z","title":"FedAW A: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.196427Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:538af249de0ebe223810cb285d735392dc5d02c699375a2e9b6aa946ae101f14","observation_id":"4e9188da-2657-490f-90d5-0f9b128cd5cb","resolution":{"observed_at":"2026-08-04T05:51:35.196427Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.199980Z","title":"Scaffold: Stochastic Controlled Averaging for Federated Learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.199980Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:d006265b21601f200ff9dccf243a0a140a81d5f5a3a1a58e8c7ea7656936e684","observation_id":"47f59194-6ee6-462f-8bd6-9da0cc566fb8","resolution":{"observed_at":"2026-08-04T05:51:35.199980Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.203473Z","title":"Fedcache: A Knowledge Cache-driven Federated Learning Architecture for Personalized Edge Intelligence,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.203473Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:5aea00ad2605eef6d5a7674b27591a76e3d7ba58ce2934488e27a57845df114d","observation_id":"65100990-3ede-4c47-a462-99eb7878c3a2","resolution":{"observed_at":"2026-08-04T05:51:35.203473Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T05:51:35.206944Z","title":"Towards Personalized Federated Learning via Heterogeneous Model Reassembly,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-04T05:51:35.206944Z"},"links":{"citing_paper":"/paper/2603.18540"},"observation_digest":"sha256:2a07e6a42fc6fb5100ee4cd3ac9a728350afe72b41d41399e7001518115aca9d","observation_id":"29d1a487-46e6-49a1-8ff4-46a0c824ab19","resolution":{"observed_at":"2026-08-04T05:51:35.206944Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2603.18540","last_updated":"2026-08-03T17:37:39Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T09:20:55.859560Z","submitted_at":"2026-03-19T06:51:05Z","title":"GAPSL: A Gradient-Aligned Parallel Split Learning over Data-Heterogeneous Edge Computing Systems"},"reference_resolution":{"displayed":49,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":49,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":49},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 49 of 49 outbound references and 2 inbound Pith citation observations for arXiv:2603.18540."}