{"as_of":"2026-08-08T21:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:41737c694f1485c2d330f3e68517acc6e3a0435e7af5af3af1744a1de9166753","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":"2026-08-01T20:38:33.102553Z","state":"measured"},{"denominator":61,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":61,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.16562/citation-record","integrity":"/paper/2607.16562/integrity","json":"/paper/2607.16562/citation-record.json","paper":"/paper/2607.16562"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T20:38:26.971351Z","title":"Multi-objective isac for low-altitude economy based on multi-task deep reinforcement learning with mixture of experts,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:26.971351Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:91d7b9e74e602088acf77226b5a84c107852933c9facfbb4893f5b34c1e8b611","observation_id":"79fa04e9-01c2-4263-b83b-a8f82f830884","resolution":{"observed_at":"2026-08-01T20:38:26.971351Z","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":"2026-08-01T20:38:27.029566Z","title":"Edge computing: Vision and challenges,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:27.029566Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:aa7b3d3ef55347d89bcf886325e12d9cf8a59a4404549f1761ea0903f35edd1e","observation_id":"20ad0007-9d6b-42de-ba6f-42a2569901e5","resolution":{"observed_at":"2026-08-01T20:38:27.029566Z","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":"2026-08-01T20:38:27.138517Z","title":"A comprehensive survey of mixture-of-experts: Algorithms, theory, and applications,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:27.138517Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:3d1b0c212e988c091b3664355b4720b0a2d996cb21a6d497466a08e4e1801f82","observation_id":"6f36f8a0-d2f2-418e-8709-7df8e9312e9e","resolution":{"observed_at":"2026-08-01T20:38:27.138517Z","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":"2026-08-01T20:38:27.266480Z","title":"Scaling vision with sparse mixture of experts,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:27.266480Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:80b0efd4a9f1996b28998240c3c446deb7c13ce163784a2d3fbec0909c004f71","observation_id":"3870ea3a-1bd0-4f43-9361-9b9afeb400da","resolution":{"observed_at":"2026-08-01T20:38:27.266480Z","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":"2026-08-01T20:38:27.322897Z","title":"Wdmoe: Wireless distributed large language models with mixture of experts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:27.322897Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:dfcb3ef35eff9eb9ab51951758c3a6bc3890fbf4d317e0a7f475040587f6e8d6","observation_id":"ed9527b9-6159-4bf4-aa9b-46423c4ffcef","resolution":{"observed_at":"2026-08-01T20:38:27.322897Z","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":"2026-08-01T20:38:27.438568Z","title":"Mixture-of-experts for distributed edge computing with channel-aware gating function,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:27.438568Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:96215217a6076b2383ba399f3f800bba217fedfe14fb5b10e1cf1430575f0b6d","observation_id":"16017816-8969-4ba1-9a00-1b5037efceab","resolution":{"observed_at":"2026-08-01T20:38:27.438568Z","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":"2026-08-01T20:38:27.536189Z","title":"A unified distributed algorithm for hybrid near-far field activity detection in cell- free massive mimo,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:27.536189Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:18026935036ee3bce65e3d033fdfac35fdecf89a33abd5d5410e6cba20c96be3","observation_id":"9357c341-bc81-4f01-adb6-e4597d95d3de","resolution":{"observed_at":"2026-08-01T20:38:27.536189Z","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":"2026-08-01T20:38:27.615607Z","title":"Broadband analog aggregation for low-latency federated edge learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:27.615607Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:553823e13b53f62cfbf8be85442f604e10dcc82ff1649837912584a047ae1a02","observation_id":"e229d338-5bd3-4fd9-bb65-2af99fac9b56","resolution":{"observed_at":"2026-08-01T20:38:27.615607Z","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":"2026-08-01T20:38:27.756183Z","title":"Machine learning at the wireless edge: Distributed stochastic gradient descent over-the-air,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:27.756183Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:6a97dc54bb8b2e42a699f05163eb63e6408ecdad4c76a38268902bae1f55be8c","observation_id":"0fa3182a-1787-427b-a139-d3430ff0e83b","resolution":{"observed_at":"2026-08-01T20:38:27.756183Z","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":"2026-08-01T20:38:27.884199Z","title":"Over-the-air computing for wire- less data aggregation in massive IoT,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:27.884199Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:2039c03f47883034bce28b41212a33bb31aa6d7a2e176973882314849d840324","observation_id":"41cc7d80-9d54-4533-91ad-8006184958a0","resolution":{"observed_at":"2026-08-01T20:38:27.884199Z","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":"2026-08-01T20:38:27.988550Z","title":"Computation-efficient federated prompt-tuning with vision-language foundation model compression over resource-constrained edge networks,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:27.988550Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:d2aeac8ac014c78f8701d9385e09866491d8e8e9c229d2833c1492015aad9d46","observation_id":"012c80f5-39e0-41a6-a70b-ff5a949e5f11","resolution":{"observed_at":"2026-08-01T20:38:27.988550Z","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":"2026-08-01T20:38:28.103792Z","title":"Fast ai model partition for split learning over edge networks,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:28.103792Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:60817ae97b90b0a0997317af8b1d5c7178f4cc2e0455bf467f3ff71bfdadb5ef","observation_id":"c3420b26-1468-4738-b31e-30ad7e822b67","resolution":{"observed_at":"2026-08-01T20:38:28.103792Z","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":"2026-08-01T20:38:28.207766Z","title":"Efficient layer-granularity unloading for llms in edge computing,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:28.207766Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:cfba9f3c41077f97fd2a5caa96d27f16b57e39da93983e6215c76e2219c8449f","observation_id":"d6a47436-8781-4e0d-8bb2-263956b8ed74","resolution":{"observed_at":"2026-08-01T20:38:28.207766Z","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":"2026-08-01T20:38:28.309683Z","title":"pfedlvm: A large vision model (lvm)-driven and latent feature-based personalized federated learning framework in autonomous driving,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:28.309683Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:f54ff561a5a7faebb5a5e1060086c4a10862a4b72dba7666600f8f9b5c9ba165","observation_id":"571e76ab-032d-4676-a7a0-3c2838691859","resolution":{"observed_at":"2026-08-01T20:38:28.309683Z","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":"2026-08-01T20:38:28.422874Z","title":"BottleNet: A deep learning architecture for intelligent mobile cloud computing services,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:28.422874Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:ae6964f589f8c43c922af4df686ab913ab3dd5a1c5572d079dc7fbf462e5482b","observation_id":"a1ac8660-341b-4d60-a746-d72dcc1ab15f","resolution":{"observed_at":"2026-08-01T20:38:28.422874Z","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":"2026-08-01T20:38:28.537301Z","title":"Split computing and early exiting for deep learning applications: Survey and research challenges,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:28.537301Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:836a06de5fd4fcadf261a50d1c36f8bf158e98f51c40a2b670c2695e01d6e247","observation_id":"bf89660b-300f-46de-b3aa-0c387e5967de","resolution":{"observed_at":"2026-08-01T20:38:28.537301Z","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":"2026-08-01T20:38:28.674801Z","title":"BranchyNet: Fast inference via early exiting from deep neural networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:28.674801Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:1a36e83ee5b5d3603e8d5821e3f3b6e445d169914fd35d963d0466d31ed3ccd8","observation_id":"bcc59dc1-04b7-489b-90bd-c81a0c5f0c88","resolution":{"observed_at":"2026-08-01T20:38:28.674801Z","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":"2026-08-01T20:38:28.820153Z","title":"Communication-computation trade-off in resource-constrained edge inference,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:28.820153Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:b5ed7c5ea0f45155b51e87e1ecf2697eaa537e09652745f42fe88fca7f6a66ce","observation_id":"fec98010-cb4c-4e57-9dfa-6c6526434eb7","resolution":{"observed_at":"2026-08-01T20:38:28.820153Z","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":"2026-08-01T20:38:28.888424Z","title":"JointDNN: An efficient training and inference engine for intelligent mobile cloud com- puting services,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:28.888424Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:c436ff544afe417655c1b24f0b4e64fe6166b98fc808b95e6a6495b244cb77b5","observation_id":"c87c8072-1e84-4c6a-97c0-8f7ea2eac2f0","resolution":{"observed_at":"2026-08-01T20:38:28.888424Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.14352","last_updated":"2025-03-07T11:16:40Z","snapshot_observed_at":"2026-07-06T16:11:06.578398Z","submitted_at":"2023-08-28T06:56:08Z","title":"EdgeMoE: Empowering Sparse Large Language Models on Mobile Devices","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.14352","snapshot_observed_at":"2026-08-01T20:38:29.015403Z","title":"EdgeMoE: Fast on-device inference of moe-based large language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:29.015403Z"},"links":{"cited_paper":"/paper/2308.14352","citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:caab9462a324de003f7383dccfc8eb8cac5a31af5c1a5e04aebe31f92e5c9b4c","observation_id":"225048d6-3b1f-4300-819f-cff86c782f07","resolution":{"observed_at":"2026-08-01T20:38:29.015403Z","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":"2026-08-01T20:38:29.192896Z","title":"LLM-QAT: Data-free quantization aware training for large language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:29.192896Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:0cff015162abf053be814c1841de16e715cc31ba72137206801f1368955edb9b","observation_id":"064fc0e6-7816-4a14-9182-671eb5d33686","resolution":{"observed_at":"2026-08-01T20:38:29.192896Z","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":"2026-08-01T20:38:29.314371Z","title":"Understanding complex-valued transformer for modulation recognition,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:29.314371Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:793e1e98b65a5ad905dae78cb3eeb3dec988cc6f401af6b6312124a8324eb9eb","observation_id":"ca37dbeb-b552-4643-801e-f294ca2f96d7","resolution":{"observed_at":"2026-08-01T20:38:29.314371Z","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":"2026-08-01T20:38:29.380724Z","title":"LoRA: Low-rank adaptation of large language models,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:29.380724Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:9c706b9e8956db51e7dfc7f956a3824bb82331e32be63898e414a01b4b6166a9","observation_id":"85ec6962-15fc-4b8c-a24e-c4b07b63dd87","resolution":{"observed_at":"2026-08-01T20:38:29.380724Z","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":"2026-08-01T20:38:29.444289Z","title":"A federated rec- ommendation system framework based on variational autoencoder with mixture of experts,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:29.444289Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:22dd27ab11a2c54bb7b3b1fb817ad7df3575be31766c4ae58652cb476d78fd5e","observation_id":"64d5b3a5-b3e1-4e80-ab89-e1d770ba99b2","resolution":{"observed_at":"2026-08-01T20:38:29.444289Z","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":"2026-08-01T20:38:29.682415Z","title":"M 3vit: Mixture-of-experts vision transformer for efficient multi- task learning with model-accelerator co-design,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:29.682415Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:e4c88848dc19933d31dd78fce717759e64d06a36ca65ff0f0e02e5549c2b95d6","observation_id":"9d488fde-56fb-486f-b980-a11b2ede0242","resolution":{"observed_at":"2026-08-01T20:38:29.682415Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1701.06538","last_updated":"2017-01-23T18:10:00Z","snapshot_observed_at":"2026-07-06T05:27:13.416519Z","submitted_at":"2017-01-23T18:10:00Z","title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1701.06538","snapshot_observed_at":"2026-08-01T20:38:29.756369Z","title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:29.756369Z"},"links":{"cited_paper":"/paper/1701.06538","citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:c8ff8c1cd839c5c96a72cb74bfdc2b91623c935a36d583da51e5df858596ca8a","observation_id":"563d1bc7-0382-4714-a7e4-d0f4f8a74e30","resolution":{"observed_at":"2026-08-01T20:38:29.756369Z","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":"2026-08-01T20:38:29.815288Z","title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:29.815288Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:a88744c09655e01816a27e6a094bda56dd1f9f3d39b0e347bf6de8880e83478d","observation_id":"7b6e1595-d3db-46b9-96a4-9051b49a27b8","resolution":{"observed_at":"2026-08-01T20:38:29.815288Z","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":"2026-08-01T20:38:29.864362Z","title":"GShard: Scaling giant models with condi- tional computation and automatic sharding,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:29.864362Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:e58c3db12ad4d283734290749c23d2c72069c527e8a38e00b0629a0e3ac5d999","observation_id":"ff72f672-1acc-4e3a-af92-014bc2e299fd","resolution":{"observed_at":"2026-08-01T20:38:29.864362Z","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":"2026-08-01T20:38:29.930705Z","title":"GLaM: Efficient scaling of language models with mixture- of-experts,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:29.930705Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:f3f70d384514c8f0adf0e38520ac88e247fb61e26b87d37492321ab90da50a17","observation_id":"111f9527-c02e-43ea-8ceb-e9892e6fd8ed","resolution":{"observed_at":"2026-08-01T20:38:29.930705Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.04088","last_updated":"2024-01-08T18:47:34Z","snapshot_observed_at":"2026-08-08T06:16:25.839566Z","submitted_at":"2024-01-08T18:47:34Z","title":"Mixtral of Experts","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.04088","snapshot_observed_at":"2026-08-01T20:38:29.997555Z","title":"Mixtral of experts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:29.997555Z"},"links":{"cited_paper":"/paper/2401.04088","citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:c305dcfc389ca9839d00277ba49b2bd9ebf1787d1318ebab2444fb57324ee0c6","observation_id":"81547d53-203a-4ffd-a481-92107df200c3","resolution":{"observed_at":"2026-08-01T20:38:29.997555Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2401.06066","last_updated":"2024-01-11T17:31:42Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-01-11T17:31:42Z","title":"DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.06066","snapshot_observed_at":"2026-08-01T20:38:30.102836Z","title":"DeepSeekMoE: Towards ultimate expert specialization in mixture-of-experts language models,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:30.102836Z"},"links":{"cited_paper":"/paper/2401.06066","citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:2d1d7100853ccaa82fa5cb9c8b45b53f573737208ab93a5a5c018581d070aad8","observation_id":"3e89b41e-448d-41c3-a581-224440d6a555","resolution":{"observed_at":"2026-08-01T20:38:30.102836Z","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":"2026-08-01T20:38:30.155603Z","title":"BASE layers: Simplifying training of large, sparse models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:30.155603Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:905e47bb781d3bdf9f64230a32bc45004a8903899ad6b1ab14826dccd733d122","observation_id":"4ee5104e-5851-4d29-ac7d-2603414d7ea3","resolution":{"observed_at":"2026-08-01T20:38:30.155603Z","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":"2026-08-01T20:38:30.240057Z","title":"Mixture-of-experts with expert choice routing,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:30.240057Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:5a7cac09ce018f58d3f9378e69689582619f7f0b8352cd53658f8f2b6cece4a4","observation_id":"48de1893-1acc-460b-a60f-2fdda70ab20f","resolution":{"observed_at":"2026-08-01T20:38:30.240057Z","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":"2026-08-01T20:38:30.301348Z","title":"Tutel: Adaptive mixture-of-experts at scale,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:30.301348Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:7464b9791d073ec45c159cf95fd1bbef66b79382ee7f6cb555926ff6b63bb0b5","observation_id":"6533c717-955b-403a-8bf2-459fb6b12b7b","resolution":{"observed_at":"2026-08-01T20:38:30.301348Z","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":"2026-08-01T20:38:30.344247Z","title":"Theory of mixture-of-experts for mobile edge computing,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:30.344247Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:d5c115c8e9d258a25e1fd59585f4e70b2372364fc64d993de4ba99993d0d130a","observation_id":"988211b7-779c-4a21-b253-fedd8034c3b7","resolution":{"observed_at":"2026-08-01T20:38:30.344247Z","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":"2026-08-01T20:38:30.443264Z","title":"Accelerating distributed MoE training and inference with Lina,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:30.443264Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:a6bd4501b9c05fc7b0b33fcf435e31316c610db7879514f92ddbb997ee49c4e2","observation_id":"26364b42-044f-42f6-ae30-1c07d4a51392","resolution":{"observed_at":"2026-08-01T20:38:30.443264Z","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":"2026-08-01T20:38:30.488511Z","title":"Computation over multiple-access channels,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:30.488511Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:b3b481c8dc542b7a01faf187c3cc0720bd3d578f2d28670a91adec42f1c33d57","observation_id":"018416c3-684a-4ba8-805a-fad194ff5273","resolution":{"observed_at":"2026-08-01T20:38:30.488511Z","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":"2026-08-01T20:38:30.543243Z","title":"Fast-convergent and communication-alleviated heterogeneous hierar- chical federated learning in autonomous driving,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:30.543243Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:73e63941fecc1100f3a260119aa4025aca29ae134dbef2f596af94bf4e5a08cc","observation_id":"376224d6-503f-475c-840c-cf298612b937","resolution":{"observed_at":"2026-08-01T20:38:30.543243Z","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":"2026-08-01T20:38:30.590797Z","title":"Communication resources constrained hierarchical federated learning for end-to-end autonomous driving,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:30.590797Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:5bae305426499e34a084549978f65ef99da494d2a72e2d410b56a485e4a273f3","observation_id":"80b72226-4a90-4b76-9ba3-79f20734859b","resolution":{"observed_at":"2026-08-01T20:38:30.590797Z","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":"2026-08-01T20:38:30.660790Z","title":"Fedrc: A rapid-converged hierarchical federated learning framework in street scene semantic understanding,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:30.660790Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:1ab8d4c9fa0b754a68f4d0914bbd1e65e7e2be875a12bae6d7fd466528a04480","observation_id":"e53397f4-e277-4f2b-a77c-8a84088eea64","resolution":{"observed_at":"2026-08-01T20:38:30.660790Z","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":"2026-08-01T20:38:30.761629Z","title":"Fedema: Federated exponential moving averaging with negative entropy regularizer in autonomous driving,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:30.761629Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:06542502b6a0b03c7f6e055ab6675c4676f8c0def7390c60c6cdedfb7668fed2","observation_id":"26b44da5-060b-417d-87ad-5a5f16a76b0e","resolution":{"observed_at":"2026-08-01T20:38:30.761629Z","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":"2026-08-01T20:38:30.929966Z","title":"Machine learning at the wireless edge: Distributed stochastic gradient descent over-the-air,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:30.929966Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:31ed400d67a41d283837dbd0c930fcdc9979698602285eb95a48ee50d66abfa8","observation_id":"0ef9d35e-5486-4c61-9b6f-7a029b35546b","resolution":{"observed_at":"2026-08-01T20:38:30.929966Z","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":"2026-08-01T20:38:31.028020Z","title":"Federated learning via over- the-air computation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:31.028020Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:48025e5e6f125d69cc0672fce70c914f0b47dfee55ceb0d8dc09d7a4a176368f","observation_id":"d8776319-85fe-43a8-ba27-614af785bbdf","resolution":{"observed_at":"2026-08-01T20:38:31.028020Z","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":"2026-08-01T20:38:31.153830Z","title":"Optimized power control design for over-the-air federated edge learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:31.153830Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:d8cd65cdf2cb691f65b8c047e2f583216dec2f4cf8404d4e5f12ca9ced18bcf7","observation_id":"57623cdc-f394-46bc-afb7-c574a21698bb","resolution":{"observed_at":"2026-08-01T20:38:31.153830Z","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":"2026-08-01T20:38:31.383404Z","title":"StableMoE: Stable routing strategy for mixture of experts,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:31.383404Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:5aabe440deb53b0facd14b21bff6e0b09e77b551e937820a5d6b6430bf4a8d01","observation_id":"26298a8b-fee0-4778-8a14-10153cdc26f5","resolution":{"observed_at":"2026-08-01T20:38:31.383404Z","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":"2026-08-01T20:38:31.511667Z","title":"Hash layers for large sparse models,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:31.511667Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:2637cf0a0ecd68e24e2f71526c69591a81251cd544b7e92fa98642c56ef5db45","observation_id":"e0cc986b-1e6a-4da1-8f10-21c5b06b35d4","resolution":{"observed_at":"2026-08-01T20:38:31.511667Z","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":"2026-08-01T20:38:31.667537Z","title":"The cityscapes dataset for semantic urban scene understanding,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:31.667537Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:1c08a025b9d182f7951a10762498e11b5ff225eed956c220e9d21dabf786f7e1","observation_id":"9bed7bd1-5926-484e-8788-2fe40fa5c70a","resolution":{"observed_at":"2026-08-01T20:38:31.667537Z","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":"2026-08-01T20:38:31.776513Z","title":"Segmentation and recognition using structure from motion point clouds,","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:31.776513Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:b5515ec36b5e87de0aeafc8732d64c4e83cea4d5cecdca7bb0a6db8677a22902","observation_id":"bdbd450f-a4a3-43d5-9fc7-8fa8ca89084c","resolution":{"observed_at":"2026-08-01T20:38:31.776513Z","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":"2026-08-01T20:38:31.847757Z","title":"The apolloscape open dataset for autonomous driving and its application,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:31.847757Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:2cd007b7b4cc933df2a94bc8f71612942238cff986fbbd9d8b7edf90668b0e70","observation_id":"d2ce6773-0d0c-42c8-b715-ab4190628d6c","resolution":{"observed_at":"2026-08-01T20:38:31.847757Z","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":"2026-08-01T20:38:31.943541Z","title":"Carla: An open urban driving simulator,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:31.943541Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:3cec3345b888a215fb50ab745b6d2d9dacf0b297927cb90e2db43737c5c466d9","observation_id":"5140ac19-4216-4a00-a392-739c1a91d499","resolution":{"observed_at":"2026-08-01T20:38:31.943541Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-08-01T20:38:32.099007Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale,","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:32.099007Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:8f8fc52b72ed98fb2d8b2d9cb37154515ad34abed2bac075967b89487a417087","observation_id":"8164e373-c86f-4a06-809a-dd69ffee7f10","resolution":{"observed_at":"2026-08-01T20:38:32.099007Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1706.05587","last_updated":"2017-12-05T18:06:21Z","snapshot_observed_at":"2026-08-07T13:44:53.690521Z","submitted_at":"2017-06-17T22:48:57Z","title":"Rethinking Atrous Convolution for Semantic Image Segmentation","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1706.05587","snapshot_observed_at":"2026-08-01T20:38:32.153357Z","title":"Rethinking atrous convolution for semantic image segmentation,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:32.153357Z"},"links":{"cited_paper":"/paper/1706.05587","citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:bad08054bf530c34f1db37500d40addf779ae978861c51bdfec3ae76fce297ca","observation_id":"58cc84fe-63f5-4532-a925-81698dc18c33","resolution":{"observed_at":"2026-08-01T20:38:32.153357Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.14131","last_updated":"2025-03-05T17:05:55Z","snapshot_observed_at":"2026-08-06T13:31:21.120277Z","submitted_at":"2024-05-23T03:11:07Z","title":"Statistical Advantages of Perturbing Cosine Router in Mixture of Experts","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.14131","snapshot_observed_at":"2026-08-01T20:38:32.196027Z","title":"Statistical advantages of perturbing cosine router in sparse mixture of experts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:32.196027Z"},"links":{"cited_paper":"/paper/2405.14131","citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:174ef24729fd9fffa385890229918c93d7a83e243de04ebc60ac75bfd8102bda","observation_id":"1357b3e8-0d09-4713-b771-36c0f545a6fa","resolution":{"observed_at":"2026-08-01T20:38:32.196027Z","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":"2026-08-01T20:38:32.286390Z","title":"From sparse to soft mixtures of experts,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:32.286390Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:2dd5a5106281cc5e125fedcb2150211b40890a4ec6a28a680f35d2ddcf314efd","observation_id":"5252944a-4c8b-4031-baa7-1d201f9787d0","resolution":{"observed_at":"2026-08-01T20:38:32.286390Z","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":"2026-08-01T20:38:32.401610Z","title":"Bisenet v2: Bilateral network with guided aggregation for real-time semantic segmentation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:32.401610Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:863aa6e0669547c0f7132bfc5b273cc92ed86eef8b3e40d9b955658163f60342","observation_id":"ffbe60bc-048e-4257-8bce-25541519d241","resolution":{"observed_at":"2026-08-01T20:38:32.401610Z","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":"2026-08-01T20:38:32.474440Z","title":"Segnet: A deep con- volutional encoder-decoder architecture for image segmentation,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:32.474440Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:e821f2994aff6fee41fe8a07429a11cb85aaf3815ca6368c08aca26a8746b314","observation_id":"ec985abd-ee3c-43cf-ae01-b57e54fa3c8d","resolution":{"observed_at":"2026-08-01T20:38:32.474440Z","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":"2026-08-01T20:38:32.628693Z","title":"Segformer: Simple and efficient design for semantic segmentation with transformers,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:32.628693Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:fe97cad5f0a2a491bc0d964e483440604f45889453a456bac24127395c8f00d1","observation_id":"9ad9caa7-36b3-4329-bf14-b47e480dea29","resolution":{"observed_at":"2026-08-01T20:38:32.628693Z","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":"2026-08-01T20:38:32.680945Z","title":"Attanet: Attention-augmented network for fast and accurate scene parsing,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:32.680945Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:a3c51c68694e165ef457418aa832839525a7bb758e9d7951eb536a0bca20af94","observation_id":"dd939b25-6282-4bcb-9c1c-48e31c7eb20a","resolution":{"observed_at":"2026-08-01T20:38:32.680945Z","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":"2026-08-01T20:38:32.820412Z","title":"Domain adaptive and general- izable network architectures and training strategies for semantic image segmentation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:32.820412Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:ad8cdb2815743c4359114dbc6a1e03bde8b5991c29649943e462c405ca12bd1a","observation_id":"1d23fa5e-4452-40de-9e38-cba7b9e4abd5","resolution":{"observed_at":"2026-08-01T20:38:32.820412Z","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":"2026-08-01T20:38:32.957905Z","title":"Topformer: Token pyramid transformer for mobile semantic segmentation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:32.957905Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:2298994c4ad2b25b1a918438afff992158fa4bd83167fc54df273483779c5ea6","observation_id":"26b3c558-43f2-4444-a72c-354fba9f4d86","resolution":{"observed_at":"2026-08-01T20:38:32.957905Z","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":"2026-08-01T20:38:33.102553Z","title":"Seaformer: Squeeze- enhanced axial transformer for mobile semantic segmentation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-01T20:38:33.102553Z"},"links":{"citing_paper":"/paper/2607.16562"},"observation_digest":"sha256:048e43ea3bab346d2c2add9ef75246400a743f76bede445ea5f5fcfe6bb3bb4e","observation_id":"ca6a7559-f66a-4d65-87d9-b1ccb3cc8201","resolution":{"observed_at":"2026-08-01T20:38:33.102553Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.16562","last_updated":"2026-07-18T00:20:43Z","latest_version":1,"primary_category":"cs.DC","snapshot_observed_at":"2026-08-08T21:14:42.217646Z","submitted_at":"2026-07-18T00:20:43Z","title":"AirMoE: Statistic-Augmented Over-the-Air MoE for Collaborative Intelligence"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":61,"verified_exact":0,"verified_fuzzy":0},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 0 inbound Pith citation observations for arXiv:2607.16562."}