{"as_of":"2026-08-16T00:00:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7e0d476a1cbde83ebd1f5119dfddc1b2179320fc21d04cbd8943370ae4830a6b","coverage":[{"denominator":202,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T00:38:28.578015Z","state":"measured"},{"denominator":100,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":100,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-15T06:32:42.880941+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/2608.10016/citation-record","integrity":"/paper/2608.10016/integrity","json":"/paper/2608.10016/citation-record.json","paper":"/paper/2608.10016"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:38:25.129230Z","title":"Absil, Robert Mahony, and Rodolphe Sepulchre","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.129230Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:6b22adccd90fd054df45dfc2c8a47f15d17bfcedc1e70f30c148b2c813ad334f","observation_id":"da6be401-1097-4d66-9532-c85915b5e820","resolution":{"observed_at":"2026-08-12T00:38:25.129230Z","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":"2026.36768","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:38:32.019079Z","title":"Communication-efficient and robust multi-modal federated learning via latent-space consensus","venue":null,"work_id":"c01abbd2-604a-468b-be8e-9ea263a97c7c","year":2026},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.180942Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:c193e3ced9fa90f792e92c3dbde27b1a7c593b50d3ad18623d74b5189c9a8038","observation_id":"86c8f7ef-f542-429e-aa7e-6478fb54ef48","resolution":{"observed_at":"2026-08-12T00:38:32.093595Z","resolver_source":"raw_fallback","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:38:25.200643Z","title":"Bandeira, Amit Singer, and Daniel A","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.200643Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:e380f6e2a4fddef5b6da771dd0f7c7def7ee256ef57cb0e4c20168645c5b6c30","observation_id":"aa476218-c0ef-45d3-b1dd-d4fc5836c1ad","resolution":{"observed_at":"2026-08-12T00:38:25.200643Z","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":"2026-08-12T00:38:25.211040Z","title":"Semantic communications based on adaptive generative models and information bottleneck","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.211040Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:5f2156e6d339e3ba3396688b6fcd8415852b614ddcfb0b951602a9b7e9aa3b5f","observation_id":"337ddbe8-68da-4d8f-9731-b45b616e5e83","resolution":{"observed_at":"2026-08-12T00:38:25.211040Z","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":"2026-08-12T00:38:25.244931Z","title":"Sheaf neural networks with connection L aplacians","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.244931Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:7f49036257e862c3682431e48e0c9a2f97d6e7de57458c6198c23d1c5e264ac1","observation_id":"221203f1-0c82-47c8-a22e-8e452076466f","resolution":{"observed_at":"2026-08-12T00:38:25.244931Z","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":"2026-08-12T00:38:25.266509Z","title":"First-order methods in optimization","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.266509Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:3bc7b0ac8de5cb7cdb1952968a655b3edd278aae442fb6d44f80a203d3e4968c","observation_id":"f9cc0a38-74ef-4351-b29c-69ebfa73deb4","resolution":{"observed_at":"2026-08-12T00:38:25.266509Z","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":"2026-08-12T00:38:25.308593Z","title":"Bronstein","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.308593Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:53078fe3fba9e9afd20eac38d3eedd9d22d5172d326e7638fd06e2f4770d540b","observation_id":"35740fa8-1e70-44df-b90d-8670ec949819","resolution":{"observed_at":"2026-08-12T00:38:25.308593Z","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":"2026-08-12T00:38:25.407925Z","title":"Sheaf theory, volume 170","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.407925Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:8fcfc43660fc9cbb7e8297dfa70df629db594b71b65c394edd3b5efc42a02bec","observation_id":"d8c58362-aff6-409a-af79-d41be41922d8","resolution":{"observed_at":"2026-08-12T00:38:25.407925Z","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":"2026-08-12T00:38:25.465385Z","title":"Multimodal federated learning: A survey","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.465385Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:7d0dd7389ea082e72ad6a5bf8165a0464fef0716368b8efff997140bdb648bd6","observation_id":"3d91c47f-9f06-4a54-9a53-4d9fa2648a24","resolution":{"observed_at":"2026-08-12T00:38:25.465385Z","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":"2026-08-12T00:38:25.514757Z","title":"Ranking and sparsifying a connection graph","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.514757Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:21881c88d46665fb6f85acba24299e95c9b4e21cd3db927726eb7c80a9a959b5","observation_id":"1fbe6a9b-d8d6-4ffc-b230-ea3051d3ebbe","resolution":{"observed_at":"2026-08-12T00:38:25.514757Z","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":"2026-08-12T00:38:25.553528Z","title":"Exploiting shared representations for personalized federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.553528Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:ba4d31600d9fb3d21fd6da7cae3eb463de19452c404c94268885768e5e97aca6","observation_id":"7a71f8ee-1cfc-48f4-8a57-0a94d2efa981","resolution":{"observed_at":"2026-08-12T00:38:25.553528Z","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":"2026-08-12T00:38:25.578402Z","title":"Sheaves, cosheaves and applications","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.578402Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:b5d5cdc7aae81ed999e4cb3e405c31bd7be4bd728b4d10e2257ea79c65d52f96","observation_id":"a65a3f6b-71f1-44ed-a974-56528d39a1c6","resolution":{"observed_at":"2026-08-12T00:38:25.578402Z","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":"2026-08-12T00:38:25.600440Z","title":"Causal abstraction learning based on the semantic embedding principle","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.600440Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:b45b3db3038133034c09db5d3e998d2bfc898c86807ab531acb236774f6d64a7","observation_id":"19526cd7-419d-4f7c-83de-65cd1ee9a2ed","resolution":{"observed_at":"2026-08-12T00:38:25.600440Z","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":"2026-08-12T00:38:25.620898Z","title":"Learning sheaf L aplacian optimizing restriction maps","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.620898Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:0eb4ad7e5e79d584ba28070d6a4b7ad600a457d246a1286f90273983500d1a27","observation_id":"ac6fb9ab-5c31-4fbf-b5c2-9ccb07d329e7","resolution":{"observed_at":"2026-08-12T00:38:25.620898Z","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":"2026-08-12T00:38:25.627136Z","title":"Learning the structure of connection graphs","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.627136Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:22f810afa27199e239ee1ea8912dfabca95247e27c2405c3911047424f983ab8","observation_id":"caea8c8a-8b23-4717-8136-70c25b24e280","resolution":{"observed_at":"2026-08-12T00:38:25.627136Z","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":"2026-08-12T00:38:25.700851Z","title":"HeteroFL : Computation and communication efficient federated learning for heterogeneous clients","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.700851Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:4018c7720e780cacbc134b26645c4ef3c4776d5e1c64760529d55aa55bbe5eea","observation_id":"437349e9-fb22-42f6-9545-d7e4da8f2e1a","resolution":{"observed_at":"2026-08-12T00:38:25.700851Z","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":"2026-08-12T00:38:25.758053Z","title":"A new look and convergence rate of federated multitask learning with L aplacian regularization","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.758053Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:b99f424bcefcfb5051a85b5a49345995a62bf89df845dec1cb8bae4c5ce73d01","observation_id":"ca60bc5d-eb3e-4851-875f-e2f6fd1ab039","resolution":{"observed_at":"2026-08-12T00:38:25.758053Z","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":"2026-08-12T00:38:25.833864Z","title":"Federated contrastive learning for decentralized unlabeled medical images","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.833864Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:be4c74960ac1b9d1551fffc03035b55f061ac97b97a26d85cdea654ebf9874b7","observation_id":"e1ccb8ae-6916-4421-99c0-2dd2355c502a","resolution":{"observed_at":"2026-08-12T00:38:25.833864Z","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":"2026-08-12T00:38:25.860523Z","title":"Arias, and Steven T","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.860523Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:7cf77d1c72c6f662b583cb8143e880a96f81a02ecec766742baa8efc50474ee7","observation_id":"d5251c20-e926-4ce2-993f-ed03cb574510","resolution":{"observed_at":"2026-08-12T00:38:25.860523Z","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":"2026-08-12T00:38:25.865509Z","title":"Regularized multi--task learning","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.865509Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:10c69352ffb8c6d22a5b30bff53d42cad293364e696ad4682c80708cd18bdaa3","observation_id":"d0e9198e-2ca0-4b95-b487-a1de9776600e","resolution":{"observed_at":"2026-08-12T00:38:25.865509Z","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":"2026-08-12T00:38:25.871097Z","title":"Learning multiple tasks with kernel methods","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.871097Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:b15a08c98d67738c1c8dd7c7d26132b0963f18e5e301e8edee57abdffd3a0444","observation_id":"b336a8cc-f00d-4368-93e7-dce8e4b2823a","resolution":{"observed_at":"2026-08-12T00:38:25.871097Z","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":"2026-08-12T00:38:25.875721Z","title":"Dynamic relative representations for goal-oriented semantic communications","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.875721Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:1d01f462da67768f113aaf02aa90eb0b20b5fa37f362589ab432f03f42126d0f","observation_id":"5ec0fb82-a373-4791-8634-b10175751446","resolution":{"observed_at":"2026-08-12T00:38:25.875721Z","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":"2026-08-12T00:38:25.882679Z","title":"Frame-based zero-shot semantic channel equalization for AI -native communications","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.882679Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:20f528a9bd084a67fb29a0263f4f85d4926f127fa65e5adc2de037948ac0eb06","observation_id":"edfb46f1-0451-41e3-bee7-f7b542e31dda","resolution":{"observed_at":"2026-08-12T00:38:25.882679Z","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":"2026-08-12T00:38:25.889858Z","title":"Model inversion attacks that exploit confidence information and basic countermeasures","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.889858Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:92307885cff296c9372db608344a935301b185e6c24a6f284e983332f9875298","observation_id":"991295a9-ebc4-4d43-ad17-9ae6b66144da","resolution":{"observed_at":"2026-08-12T00:38:25.889858Z","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":"2026-08-12T00:38:25.895214Z","title":"Sheaf A lign: A sheaf-theoretic framework for decentralized multimodal alignment","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.895214Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:1b0c3ef59ca12f15098577445513857368a03e297431f4ad661c453c47550808","observation_id":"c153e114-0de7-4ead-a8f1-6e0db1f87f3e","resolution":{"observed_at":"2026-08-12T00:38:25.895214Z","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":"2026-08-12T00:38:25.900003Z","title":"Learning network sheaves for AI -native semantic communication","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.900003Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:3be0a8a4e8a96aec31125cb90a93ad018c9cadd2b71e290058a1848e2435392d","observation_id":"250bb8cb-33da-46da-b1e5-5eb70c273ac9","resolution":{"observed_at":"2026-08-12T00:38:25.900003Z","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":"2026-08-12T00:38:25.950203Z","title":"Beyond transmitting bits: Context, semantics, and task-oriented communications","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:25.950203Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:220fa0723e04e2ed09090b4ccac4aac16949c5fe8adab70e4abd6cf5f4c018fc","observation_id":"5c2a1d68-361c-4cb9-aa42-cb7b52590525","resolution":{"observed_at":"2026-08-12T00:38:25.950203Z","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":"2026-08-12T00:38:26.040020Z","title":"Fedx: Unsupervised federated learning with cross knowledge distillation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.040020Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:587bd73258982205b4f568bb648b252bd0927396ce260743858b7c5ae2d1dda7","observation_id":"2a1130b2-ff13-4e89-aeaa-69512090a570","resolution":{"observed_at":"2026-08-12T00:38:26.040020Z","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":"2026-08-12T00:38:26.129825Z","title":"Toward a spectral theory of cellular sheaves","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.129825Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:d3de3cc1474e5b87eae707cde6e27b02848fb2b6141e21b4ea3759cfa5af4780","observation_id":"6ca7bdb2-ac91-45dd-8c3b-509d765ed34e","resolution":{"observed_at":"2026-08-12T00:38:26.129825Z","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":"2026-08-12T00:38:26.150121Z","title":"u ttebr \\","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.150121Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:148a3b82659fa4ae761d92152bd86e8b864c43e5673ea5561187e84641ecfe9e","observation_id":"49b464bc-d978-49b3-8b53-933a07efdfb3","resolution":{"observed_at":"2026-08-12T00:38:26.150121Z","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":"2026-08-12T00:38:26.173781Z","title":"Tackling feature and sample heterogeneity in decentralized multi-task learning: A sheaf-theoretic approach","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.173781Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:f97eb2ddbdb3c908cc0239728fa31f49c69dd7a0d7d299a99c0595ebe9904998","observation_id":"f51ae61d-e143-4e29-9826-7920fa87b77c","resolution":{"observed_at":"2026-08-12T00:38:26.173781Z","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":"2026-08-12T00:38:26.179576Z","title":"Clustered multi-task learning: A convex formulation","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.179576Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:21806bfa97908220cba81988ee001fbed4f7d38d9fb52bfcb20f51582430c10e","observation_id":"37f7bb41-bca5-4689-9269-652cbe61fb14","resolution":{"observed_at":"2026-08-12T00:38:26.179576Z","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":"2026-08-12T00:38:26.184834Z","title":"Communication-efficient distributed dual coordinate ascent","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.184834Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:2eac9dd47df1da1992bb98a2854f03aba37be4ee342fc5bb96237691774671b3","observation_id":"63e93283-dca4-4aa5-ba25-cfe7ffe1b782","resolution":{"observed_at":"2026-08-12T00:38:26.184834Z","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":"2026-08-12T00:38:26.190333Z","title":"Mcmahan, et al","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.190333Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:6c481301a30e1322262178fa3ce13c6f57ea057467a64131a9c6519dcd1854df","observation_id":"ccc13243-0b7d-474a-b9f7-0e0d32ddcf7d","resolution":{"observed_at":"2026-08-12T00:38:26.190333Z","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":"2026-08-12T00:38:26.256922Z","title":"SCAFFOLD : Stochastic controlled averaging for federated learning","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.256922Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:975fa4b1e0f3741cdea82f96d3777ff9cc8c6c9139c9123729b59811bf8c1ee5","observation_id":"b8f3ce81-828a-4a94-a383-1ee496d6af1d","resolution":{"observed_at":"2026-08-12T00:38:26.256922Z","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":"2026-08-12T00:38:26.327278Z","title":"Optimal whitening and decorrelation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.327278Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:2aec2149569d3df9e67f42b2b84b09132252e251e9b04eae087d15a3269f8670","observation_id":"12494ef2-87cd-40aa-ae28-dbacd046dc36","resolution":{"observed_at":"2026-08-12T00:38:26.327278Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2008.03371","last_updated":"2020-08-07T20:45:12Z","snapshot_observed_at":"2026-08-14T20:23:06.504001Z","submitted_at":"2020-08-07T20:45:12Z","title":"LotteryFL: Personalized and Communication-Efficient Federated Learning with Lottery Ticket Hypothesis on Non-IID Datasets","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2008.03371","snapshot_observed_at":"2026-08-12T00:38:26.332516Z","title":"Lottery FL : Personalized and communication-efficient federated learning with lottery ticket hypothesis on non-iid datasets","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.332516Z"},"links":{"cited_paper":"/paper/2008.03371","citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:411755a85119e124856560eb5d18ed97aa767641987b8fed2c927793296624c1","observation_id":"fd626a06-2f10-479a-a8d6-4443ddb4a365","resolution":{"observed_at":"2026-08-12T00:38:26.332516Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2206.05668","last_updated":"2022-06-12T05:41:23Z","snapshot_observed_at":"2026-08-13T15:25:26.703674Z","submitted_at":"2022-06-12T05:41:23Z","title":"Federated Learning on Riemannian Manifolds","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.05668","snapshot_observed_at":"2026-08-12T00:38:26.337632Z","title":"Federated learning on R iemannian manifolds","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.337632Z"},"links":{"cited_paper":"/paper/2206.05668","citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:03579bc3e61301763d4a320d1d7ed9fa275deaf73160fbf5ba3ef5cdcb8cd888","observation_id":"b5d32e35-25a4-474c-8027-2cca7345e4a2","resolution":{"observed_at":"2026-08-12T00:38:26.337632Z","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":"2026-08-12T00:38:26.347592Z","title":"Model-contrastive federated learning","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.347592Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:f7448d55d01a694835ff4cc40a7a3d34e68ff0a8018565c90d6c3713ac7f0530","observation_id":"0fd6fa42-ce12-40fd-b8ee-211b304acab3","resolution":{"observed_at":"2026-08-12T00:38:26.347592Z","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":"2026-08-12T00:38:26.352792Z","title":"Federated optimization in heterogeneous networks","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.352792Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:203a7ac6a3b63c8ef2ee458d498f3854b32896addd141ee62b347aae6af0e1b5","observation_id":"a54fa529-053d-41fe-b497-b2159ce41d65","resolution":{"observed_at":"2026-08-12T00:38:26.352792Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.01523","last_updated":"2020-07-14T08:12:35Z","snapshot_observed_at":"2026-08-14T23:16:03.815025Z","submitted_at":"2020-01-06T12:40:21Z","title":"Think Locally, Act Globally: Federated Learning with Local and Global Representations","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2001.01523","snapshot_observed_at":"2026-08-12T00:38:26.358315Z","title":"Think locally, act globally: F ederated learning with local and global representations","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.358315Z"},"links":{"cited_paper":"/paper/2001.01523","citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:38f217d452f7ffd78c99c265d59127270e827802b3d0eb43adfad1e7af883c17","observation_id":"8a04f1c8-a548-497c-9ba5-39d5657fd3d2","resolution":{"observed_at":"2026-08-12T00:38:26.358315Z","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":"2026-08-12T00:38:26.364166Z","title":"Adding vs","venue":null,"work_id":null,"year":1973},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.364166Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:6978f1cf73283a5a1353a321a3eb5446fd6618911ab3b4d34bb2229e05cbcd35","observation_id":"074ced25-9aa6-41da-b6ac-619fb4814794","resolution":{"observed_at":"2026-08-12T00:38:26.364166Z","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":"2026-08-12T00:38:26.369666Z","title":"Personalized federated learning via feature distribution adaptation","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.369666Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:5bf33fa458f92dc9e5debc332fa4cbd409c5fd4344d147db9f837610f33d7632","observation_id":"06df3dc9-d998-4a9a-ada3-19527b40d7b8","resolution":{"observed_at":"2026-08-12T00:38:26.369666Z","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":"2026-08-12T00:38:26.407027Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.407027Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:449bd2f44b5631fa9b2cda6720e38370047f12c00a282d2192ad8c22e03ec189","observation_id":"3c980c91-82d0-4a13-93d7-d410b99ba2f7","resolution":{"observed_at":"2026-08-12T00:38:26.407027Z","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":"2026-08-12T00:38:26.520291Z","title":"Exploiting unintended feature leakage in collaborative learning","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.520291Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:606855b2581214224818d968ad3dff5deb56572830ca0d33f75dd248b463d1e6","observation_id":"8a0ed6ce-b929-4339-b968-845c2527ac39","resolution":{"observed_at":"2026-08-12T00:38:26.520291Z","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":"2026-08-12T00:38:26.560048Z","title":"Contrastive and non-contrastive strategies for federated self-supervised representation learning and deep clustering","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.560048Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:65ca4f3a9e6b810ae08979f4655a71dfc32ea70d7df9d2c6be7757c06db015a7","observation_id":"940febb3-16ea-499c-82e4-4aca92156f63","resolution":{"observed_at":"2026-08-12T00:38:26.560048Z","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":"2026-08-12T00:38:26.594756Z","title":"Relative representations enable zero-shot latent space communication","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.594756Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:837ec38d4b21cadfd93ccfab567c358929dfb66780eb81fa40176e0fef128ff3","observation_id":"1f3f68e2-74ea-429e-b3e1-3759663360eb","resolution":{"observed_at":"2026-08-12T00:38:26.594756Z","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":"2026-08-12T00:38:26.600582Z","title":"Introductory Lectures on Convex Optimization: A Basic Course, volume 87 of Applied Optimization","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.600582Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:ff92d492ff1bcc3d646f37c5499677fdb9c422c4deb6b6b016e048b53d89fa0f","observation_id":"5d955ea4-8cff-48e1-a45f-2c2f1ea15206","resolution":{"observed_at":"2026-08-12T00:38:26.600582Z","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":"2026-08-12T00:38:26.708001Z","title":"Latent space alignment for AI -native mimo semantic communications","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.708001Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:f4ec98bee728d75e8e90194e66f10c960e3f665553be93cc1f0a0acb1b214ce6","observation_id":"f459255a-2690-4eff-94ae-8cea25d90e6c","resolution":{"observed_at":"2026-08-12T00:38:26.708001Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.09485","last_updated":"2026-05-10T11:42:36Z","snapshot_observed_at":"2026-08-13T14:21:58.231767Z","submitted_at":"2026-05-10T11:42:36Z","title":"SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations","version":1},"cited_work":{"arxiv_id":"2605.09485","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.09485","snapshot_observed_at":"2026-08-12T00:38:31.764918Z","title":"SEMASIA: A Large-Scale Dataset of Semantically Structured Latent Representations","venue":"cs.LG","work_id":"0ad4149e-1026-47b2-bba5-6c1eb8364e40","year":2026},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.801095Z"},"links":{"cited_paper":"/paper/2605.09485","citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:671051ae6dd60e946472b87bfd1da05feb9e7621df59dfeaada753ce622fd2bd","observation_id":"6ba2f52e-fc60-4bbd-83fb-7d3cde4d0b88","resolution":{"observed_at":"2026-08-12T00:38:31.826945Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-12T00:38:26.864283Z","title":"A convergence theorem for non negative almost supermartingales and some applications","venue":null,"work_id":null,"year":1971},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.864283Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:4499d810fcdb084cb3d4ab30be4e6b4f86b1b2e4efde71a7eb1613bd442a2a6e","observation_id":"000743a4-83ae-4dcb-8cc9-77a815076d4d","resolution":{"observed_at":"2026-08-12T00:38:26.864283Z","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":"2026-08-12T00:38:26.906468Z","title":"A framework for parallel and distributed training of neural networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.906468Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:0946c67f21790d0f53ab2ac03dc1c7c44434cd3d384a61e4668540e4879ca6dd","observation_id":"9d172392-a6f9-4e95-ba47-45b4668bc4d3","resolution":{"observed_at":"2026-08-12T00:38:26.906468Z","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":"2026-08-12T00:38:26.912481Z","title":"Sch \\\"o nemann","venue":null,"work_id":null,"year":1966},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.912481Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:fddc5bab5947e57a2f2791641966f73235dde346478496b25e0f931d2d1ae810","observation_id":"ac8eaf8a-ecea-4fa7-b7df-0359bf7ccde3","resolution":{"observed_at":"2026-08-12T00:38:26.912481Z","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":"2026-08-12T00:38:26.918291Z","title":"Khalil, and Hongliang Li","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.918291Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:58cd3d71ef30fae6198198a6c57a1534c2a0fd8ac73163e8796b8d3dc467a5e5","observation_id":"0d4d6192-23be-4b86-8b5f-1fa42ef15156","resolution":{"observed_at":"2026-08-12T00:38:26.918291Z","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":"2026-08-12T00:38:26.924366Z","title":"Membership inference attacks against machine learning models","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.924366Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:7a914dd7e0c55f9cc7889d0154142f499e4e7c84a8dd464950f0b306499acc28","observation_id":"7aa818e0-9087-4c05-a7b7-06ff1b79b4c4","resolution":{"observed_at":"2026-08-12T00:38:26.924366Z","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":"2026-08-12T00:38:26.929916Z","title":"Angular synchronization by eigenvectors and semidefinite programming","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.929916Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:d753f775c031ae13523b545200c932739ccfe39e56ee52cbccf27cf4a9710820","observation_id":"52092997-c1bd-47ec-8114-f439d5dfd349","resolution":{"observed_at":"2026-08-12T00:38:26.929916Z","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":"2026-08-12T00:38:26.977109Z","title":"Vector diffusion maps and the connection L aplacian","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:26.977109Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:97de93cb9dce575514f50c45da47bdc84517bedc2fd19f3e1d740bf5af538c00","observation_id":"6a0f9588-c086-4b46-bcd7-28ebaf4869ce","resolution":{"observed_at":"2026-08-12T00:38:26.977109Z","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":"2026-08-12T00:38:27.062778Z","title":"Federated multi-task learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.062778Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:0d79a37f4ae378af0d4962c6e272de8ba99a0cdcd7ed9b5b83e6b5f9d886e187","observation_id":"4cf5b7cf-0f59-43b5-af1e-35162a044357","resolution":{"observed_at":"2026-08-12T00:38:27.062778Z","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":"2026-08-12T00:38:27.153993Z","title":"Goal-oriented and semantic communication in 6G AI -native networks: The 6G-GOALS approach","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.153993Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:3cfc946be562f001d136230244bfb7c46ef1f04912eab52b76d4cba091685c83","observation_id":"b1b9b5db-f46f-448c-9c94-e800610e1f85","resolution":{"observed_at":"2026-08-12T00:38:27.153993Z","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":"2026-08-12T00:38:27.190661Z","title":"Fedproto: Federated prototype learning across heterogeneous clients","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.190661Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:f6ecf2c8c5ee04cddf0fbb95a5d705be7aa2c22574f7a2cc95c934cd5243ba40","observation_id":"940c8b86-b7dc-4be4-9d47-cade623aaaa8","resolution":{"observed_at":"2026-08-12T00:38:27.190661Z","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":"2026-08-12T00:38:27.196131Z","title":"Distributed methods for synchronization of orthogonal matrices over graphs","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.196131Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:d13118a22832b6fcbc6468e96b5e4a53f574e998ad94143f94d4d13c6557a77d","observation_id":"4c7ffe35-88e5-45e4-9b75-cd2fbe7e221c","resolution":{"observed_at":"2026-08-12T00:38:27.196131Z","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":"2026-08-12T00:38:27.203623Z","title":"Fedntproto: A prototype-based approach for personalized federated learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.203623Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:901549bda40385e1866a4632200682fba2863ba7b7f2995f3afd2160730c3897","observation_id":"860750ed-8189-49e6-b945-19bd73db210f","resolution":{"observed_at":"2026-08-12T00:38:27.203623Z","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":"2026-08-12T00:38:27.244079Z","title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.244079Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:abef2591e946ab00bbc4a45805bfa50f2ecf706c1fcb134f8a2b4d2902b006cc","observation_id":"d1cda90c-0251-4fd9-9f3a-b0c0fed27798","resolution":{"observed_at":"2026-08-12T00:38:27.244079Z","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":"2026-08-12T00:38:27.325723Z","title":"Federated unsupervised representation learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.325723Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:1adb2f4165fb76e08b849870d8213d051e5e7d61cf553b5d7fb995caecb0507e","observation_id":"526c0674-6270-4d45-b609-b1937db61a8c","resolution":{"observed_at":"2026-08-12T00:38:27.325723Z","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":"2026-08-12T00:38:27.402655Z","title":"Stochastic whitening batch normalization","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.402655Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:156fac5d6d169758168c6a4eb73b71a2af60aa20b5f932481c473daef59d90bd","observation_id":"6bc3a227-76da-4316-906e-dcb24318deeb","resolution":{"observed_at":"2026-08-12T00:38:27.402655Z","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":"2026-08-12T00:38:27.427878Z","title":"Learning sparse task relations in multi-task learning","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.427878Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:90e17d9ec688aebbcebb40b508d70016d41bf86969426f7939d5f99c7de7ce9e","observation_id":"c1436bd4-eb84-4922-a441-fa77a5a5d6f7","resolution":{"observed_at":"2026-08-12T00:38:27.427878Z","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":"2026-08-12T00:38:27.435271Z","title":"A convex formulation for learning task relationships in multi-task learning","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.435271Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:105feadd32d9d888988de3e6a438775308fbd3fbdd7c9f6a7ef7424952a20cc3","observation_id":"64697010-11c1-4f4b-b508-d88a70c34c54","resolution":{"observed_at":"2026-08-12T00:38:27.435271Z","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":"2026-08-12T00:38:27.441326Z","title":"Collaborative unsupervised visual representation learning from decentralized data","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.441326Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:64e1d73d150242f26dada907ea477a7eda77fe4877116e2442b773a3ad9bec86","observation_id":"0bb7fefe-a489-4723-aba6-bf807b226db0","resolution":{"observed_at":"2026-08-12T00:38:27.441326Z","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":"2026-08-12T00:38:27.447362Z","title":"Communication-Efficient Learning of Deep Networks from Decentralized Data , booktitle =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.447362Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:e577b006f27a9c34a44de2e6325b8939816e933a489190ad90e940beea8fc071","observation_id":"8b3835b4-a61b-420d-8e5c-15067fd26230","resolution":{"observed_at":"2026-08-12T00:38:27.447362Z","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":"2026-08-12T00:38:27.493429Z","title":"IEEE Communications Magazine , volume=","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.493429Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:76e0167e46a8e981cdc5f831fe222e56db07e4bf52e9638fd54f67a8f0fc3971","observation_id":"db184444-5f1a-4968-a926-1cb5daee5248","resolution":{"observed_at":"2026-08-12T00:38:27.493429Z","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":"2026-08-12T00:38:27.555955Z","title":"Proceedings of the Third Conference on Machine Learning and Systems (MLSys) , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.555955Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:6d528b03827611e79ea83637b07c04ff30028826dfd09b5c6b5e09d1b68d484b","observation_id":"5281675c-4d93-45c9-83e4-5b82f7d6cb9b","resolution":{"observed_at":"2026-08-12T00:38:27.555955Z","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":"2026-08-12T00:38:27.684807Z","title":"Optimizing Methods in Statistics , pages=","venue":null,"work_id":null,"year":1971},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.684807Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:031401334bf81ad7f4a70e9f0a4c0a862e4fbf5debf5df363c791f5750ff9ad6","observation_id":"13261314-c967-41b9-a61a-1313ce4bb203","resolution":{"observed_at":"2026-08-12T00:38:27.684807Z","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":"2026-08-12T00:38:27.696780Z","title":"ICML , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":75,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.696780Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:51042b745a4816af4d4cd47eaa06d92b1cb1b0a1dae8f821558a612cdfefe05d","observation_id":"23fbed42-d71d-464e-a528-71c3cd065f2a","resolution":{"observed_at":"2026-08-12T00:38:27.696780Z","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":"2026-08-12T00:38:27.704045Z","title":"CVPR , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":76,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.704045Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:38ba2b097b9d38dbef9b809687a86e70992b95b58027b6dc5a03d1ff0de7e2f8","observation_id":"4e878c56-1771-44cb-a012-00c5c10c83f8","resolution":{"observed_at":"2026-08-12T00:38:27.704045Z","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":"2026-08-12T00:38:27.709570Z","title":"CVPR , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":77,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.709570Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:3238f93bc87f0bbc438f6c456a1d13b503f9dc62c38b0609e9d800fc4ba76eca","observation_id":"4eb16cef-cf6b-4284-9db4-3ab49d1a77cb","resolution":{"observed_at":"2026-08-12T00:38:27.709570Z","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":"2026-08-12T00:38:27.751753Z","title":"ICML , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":78,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.751753Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:8a5bc9b2c6070c601fc69b7450c5bc45a118d90f44227e18b289a8699f154c54","observation_id":"225a6d00-9734-4dd1-bc37-e9c7db93b140","resolution":{"observed_at":"2026-08-12T00:38:27.751753Z","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":"2026-08-12T00:38:27.848517Z","title":"2020 , series =","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.848517Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:d7d74f3426e9fa6f1ca8fd0e6bacaa993e54e88a81f153bc23f73b3aecb55c18","observation_id":"a69e3df1-63cd-429f-b954-6079870656f7","resolution":{"observed_at":"2026-08-12T00:38:27.848517Z","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":"2026-08-12T00:38:27.912663Z","title":"Learning Sheaf","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":80,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.912663Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:0aae3e2295d96ed9c8b992eb35e2363f30e67a56dd915eb2735c50d7a545216f","observation_id":"faeb3081-f97f-417f-b2ac-426078014093","resolution":{"observed_at":"2026-08-12T00:38:27.912663Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.14198","last_updated":"2022-11-15T23:07:37Z","snapshot_observed_at":"2026-07-06T13:05:12.350238Z","submitted_at":"2022-04-29T16:29:01Z","title":"Flamingo: a Visual Language Model for Few-Shot Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.14198","snapshot_observed_at":"2026-08-12T00:38:27.930263Z","title":"arXiv preprint arXiv:2204.14198 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":81,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.930263Z"},"links":{"cited_paper":"/paper/2204.14198","citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:f495010c72c250e0d9c2c8e00b29a672a289ab5ccd0094f3724cbb7a399361be","observation_id":"db932e30-9d97-4f30-bb6f-7bf10380c47b","resolution":{"observed_at":"2026-08-12T00:38:27.930263Z","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":"2026-08-12T00:38:27.937702Z","title":null,"venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":82,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.937702Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:9ca07e8f3a2672af903167835cc5c1b89ee92e9525108545cf51efcafcef5b94","observation_id":"f3970ccd-6b43-47fb-9a4c-067b267af62f","resolution":{"observed_at":"2026-08-12T00:38:27.937702Z","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":"2026-08-12T00:38:27.943103Z","title":"and others , URL =","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":83,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.943103Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:0ff0d69524bdd110529d983e82f4ba48499fcd79a9e217501dfa076ade950d93","observation_id":"5ee8b6fd-ef69-4f23-bb9c-b09ef35fff2c","resolution":{"observed_at":"2026-08-12T00:38:27.943103Z","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":"2026-08-12T00:38:27.948339Z","title":"International Conference on Machine Learning , pages=","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":84,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.948339Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:da935e0bc9d69acccee7d0b8981148b1c6fb39105c1ec4f532738a0690d130cf","observation_id":"7a47d0cd-ee32-4605-90bb-aae424e6e96a","resolution":{"observed_at":"2026-08-12T00:38:27.948339Z","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":"2026-08-12T00:38:27.960358Z","title":"Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security (CCS) , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:27.960358Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:674425633681cd87fef273a3faee88647304c69b9238f95890c4bde86dcdb9de","observation_id":"8fc954f1-3ee7-439f-867f-2ace055b78bc","resolution":{"observed_at":"2026-08-12T00:38:27.960358Z","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":"2026-08-12T00:38:28.043167Z","title":"IEEE Symposium on Security and Privacy (S&P) , pages=","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":86,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.043167Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:537bbf498edc46c89fe1c1fe3c3ea947ecb90797b24381f63b4d70991e7688a3","observation_id":"75ad05e9-4060-4158-8f85-c3ff73d2cfe6","resolution":{"observed_at":"2026-08-12T00:38:28.043167Z","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":"2026-08-12T00:38:28.132516Z","title":"IEEE Symposium on Security and Privacy (S&P) , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":87,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.132516Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:b2d6bb979b757e4a5ac6007a9f9e4511d23ad3220504fcb5c2a85fb6d83a72a3","observation_id":"7ee55bd5-5919-431c-99a7-b8c533e34c9c","resolution":{"observed_at":"2026-08-12T00:38:28.132516Z","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":"2026-08-12T00:38:28.261597Z","title":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":88,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.261597Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:943c40e1e7e155007f62f029bbed47fb042492e5f6776121c36a73f86e2a5509","observation_id":"e30e2a0a-f51a-44fd-abee-12169d6178b2","resolution":{"observed_at":"2026-08-12T00:38:28.261597Z","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":"2026-08-12T00:38:28.289598Z","title":"1997 , publisher=","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":89,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.289598Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:e2858eb912dcf8e039e6555b2d25ac3dfa62674f5bdcf0403341bb0346cc17aa","observation_id":"1bfb0763-ffe9-4fce-a176-2b3a35ba028f","resolution":{"observed_at":"2026-08-12T00:38:28.289598Z","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":"2026-08-12T00:38:28.295487Z","title":"ICASSP 2026-2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) , pages=","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":90,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.295487Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:cb1d5c35e3d38d7c7f5f1bef90df624d17cbbd5f2ea3b00eddd604041923b852","observation_id":"a0227427-5090-451e-926c-2a3ae826cdb7","resolution":{"observed_at":"2026-08-12T00:38:28.295487Z","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":"2026-08-12T00:38:28.301207Z","title":"Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":91,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.301207Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:fb3fe4c0ddac7fa848b3dec98a0678730dabee4a26eefa45c67aaa08e0997058","observation_id":"d6c03773-7770-46c4-8bdb-5ef8b41dabf4","resolution":{"observed_at":"2026-08-12T00:38:28.301207Z","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":"2026-08-12T00:38:28.306435Z","title":"International Conference on Medical Image Computing and Computer-Assisted Intervention , pages=","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":92,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.306435Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:27b7bbf4817d7d2f2b7578c419fa901d77b4e7892adc25575d977a9809686d18","observation_id":"ac482ae1-3166-4f7c-866d-fb5f86495868","resolution":{"observed_at":"2026-08-12T00:38:28.306435Z","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":"2026-08-12T00:38:28.312683Z","title":"Proceedings of the Thirty-Sixth AAAI Conference on Artificial Intelligence (AAAI) , pages =","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":93,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.312683Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:7150d0e1ac6247c53d41b7ed90e8855195272decb239d18fa60f3cc5731db34d","observation_id":"6672debe-8065-40a1-99bf-1e84ea8c9e8c","resolution":{"observed_at":"2026-08-12T00:38:28.312683Z","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":"2026-08-12T00:38:28.327432Z","title":"Neural Sheaf Diffusion: A Topological Perspective on Heterophily and Oversmoothing in","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":94,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.327432Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:72edf5ece07dd25bd1f51b3305300ff59036ecff373944efdec5d563e4ab0005","observation_id":"36593656-778d-4548-9167-50b6b4bf8c9a","resolution":{"observed_at":"2026-08-12T00:38:28.327432Z","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":"2026-08-12T00:38:28.444578Z","title":"Journal of Applied and Computational Topology , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":95,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.444578Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:68434690d81ce6459982ccabc984fdba87492fb151e8facad850b088d237a0f7","observation_id":"ba088499-8b50-491e-8473-85f14eb82570","resolution":{"observed_at":"2026-08-12T00:38:28.444578Z","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":"2026-08-12T00:38:28.508787Z","title":null,"venue":null,"work_id":null,"year":1966},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":96,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.508787Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:dd5a31dd5b55fac956ad3c2320589079ed2bfd984068b9352ad67ca0e7211bcf","observation_id":"7cd9eaf6-0c89-47a7-9b71-afc621a4c207","resolution":{"observed_at":"2026-08-12T00:38:28.508787Z","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":"2026-08-12T00:38:28.537642Z","title":"Applied and Computational Harmonic Analysis , volume=","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":97,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.537642Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:7e95a6818f2dc0776356f443eb7d72de40bcc1c2c7107d64be958506ba98650d","observation_id":"73835bed-9f2e-47ee-a340-9e55ca976622","resolution":{"observed_at":"2026-08-12T00:38:28.537642Z","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":"2026-08-12T00:38:28.547191Z","title":"Vector Diffusion Maps and the Connection","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":98,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.547191Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:9efea3013d3473265c175b13ee221c2249122dace91d67de8ae6264a31bbf1c1","observation_id":"e26ad436-bc5e-4af9-81e4-b1dbefc7819c","resolution":{"observed_at":"2026-08-12T00:38:28.547191Z","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":"2026-08-12T00:38:28.561111Z","title":"Internet Mathematics , volume=","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":99,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.561111Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:c0bc1b7a1d9a3bf9c0835e497e1425ee08206fc77b85cf7db2f205ada77dd1c0","observation_id":"fda1d7b3-90c4-484f-9309-ce35c1adfb67","resolution":{"observed_at":"2026-08-12T00:38:28.561111Z","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":"2026-08-12T00:38:28.566913Z","title":"Forty-second International Conference on Machine Learning , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":100,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.566913Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:42588add910ebee706da8177c258fd671eed1d0e9752d486faa5535d4d6f06f0","observation_id":"eb67719d-297f-4e5a-a78d-9cd2d79c129d","resolution":{"observed_at":"2026-08-12T00:38:28.566913Z","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":"2026-08-12T00:38:28.572260Z","title":"2004 , series =","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":101,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.572260Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:34570f38604fb4763c25b9a43295a2f3195760782937a936c203312566a65221","observation_id":"f3a9a294-8786-4ca1-9bb6-4b5fad566f8f","resolution":{"observed_at":"2026-08-12T00:38:28.572260Z","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":"2026-08-12T00:38:28.578015Z","title":"2017 , publisher=","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning","version":1},"reference_index":102,"source":"arxiv_source","source_observed_at":"2026-08-12T00:38:28.578015Z"},"links":{"citing_paper":"/paper/2608.10016"},"observation_digest":"sha256:9c01cfcbd17c02f8ebf795385b62d52d41550c409a5d5a7ee897c7d3a34f0b5f","observation_id":"51b61a85-2dc2-4207-9cb1-fcab01bd25fa","resolution":{"observed_at":"2026-08-12T00:38:28.578015Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.10016","last_updated":"2026-08-08T16:38:34Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T23:09:56.808217Z","submitted_at":"2026-08-08T16:38:34Z","title":"Sheaf-Based Federated Representation Learning"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":98,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":202},"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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 100 of 202 outbound references and 0 inbound Pith citation observations for arXiv:2608.10016."}