{"as_of":"2026-08-08T04:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:7d54aeb522db82b9f8647390ec340b832ecfbd5813652a5bf8ae1153792606af","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:52:06.085397Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:52:05.987755Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-07T10:52:06.137780Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"cited_work":{"arxiv_id":"2506.04071","doi":null,"metadata_source":"pith","pith_arxiv_id":"2506.04071","snapshot_observed_at":"2026-08-07T10:52:06.137780Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","venue":"cs.LG","work_id":"8f1f0d7e-e97f-401b-963f-ee11619f753e","year":2025},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:05.987755Z"},"links":{"cited_paper":"/paper/2506.04071","citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:2151e56608be99fba4291dd0ac2bb436e4f04e3b3545893589f82b1c68408ba3","observation_id":"b943468c-2088-4c7a-adae-310a1f190669","resolution":{"observed_at":"2026-08-07T10:52:06.143404Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.04071/citation-record","integrity":"/paper/2506.04071/integrity","json":"/paper/2506.04071/citation-record.json","paper":"/paper/2506.04071"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.434152Z","title":null,"venue":null,"work_id":"0426ed54-f4d9-4d5d-93f4-ad7436f7790e","year":null},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:05.983958Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:ede829ac59de9802125cbae763721f7522e177cdb813a7dc2a055a106d657a7d","observation_id":"e0d233c5-4304-4148-8d18-80ec4eda25aa","resolution":{"observed_at":"2026-08-07T10:52:06.436815Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"cited_work":{"arxiv_id":"2506.04071","doi":null,"metadata_source":"pith","pith_arxiv_id":"2506.04071","snapshot_observed_at":"2026-08-07T10:52:06.137780Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","venue":"cs.LG","work_id":"8f1f0d7e-e97f-401b-963f-ee11619f753e","year":2025},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:05.987755Z"},"links":{"cited_paper":"/paper/2506.04071","citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:2151e56608be99fba4291dd0ac2bb436e4f04e3b3545893589f82b1c68408ba3","observation_id":"b943468c-2088-4c7a-adae-310a1f190669","resolution":{"observed_at":"2026-08-07T10:52:06.143404Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.424727Z","title":"Federated Learning The goal of federated learning (FL) is to train a single (global) model to make accurate predictions across all agents in a net- work","venue":null,"work_id":"4db33ad3-7a6e-4dd3-9257-a924ed41dd1a","year":null},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:05.991320Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:65b9bd02be39d29f4d1b1ab9c57ed1358572b2b6c018ef9dd84cd3d7d53b4f1b","observation_id":"d6d0530c-95d3-49d9-853a-ca6a78c5b487","resolution":{"observed_at":"2026-08-07T10:52:06.428328Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.415832Z","title":"We achieve this distribution-alignment goal by generating a tar- get space to which we project all local data","venue":null,"work_id":"060f98ea-90f9-48d1-afeb-e8d6cf0ca3a0","year":null},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:05.994629Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:98a957a0d3cbdee46a7b32eb00895ba04aac671f1b34645281fbb0b326146c22","observation_id":"ea30399c-6843-40ab-ac22-21de215f1386","resolution":{"observed_at":"2026-08-07T10:52:06.418904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.406508Z","title":"To demonstrate the advantages of using our preprocessing step, we require a learning algorithm","venue":null,"work_id":"d832a83d-a485-429a-b2fe-8004ef69dc5b","year":null},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:05.997779Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:a7c9a998a88fc949807dcae44cb4d2c2a7143b0bf79d90df760b01f709586339","observation_id":"68c2f215-12f5-40ff-b98d-770084edd363","resolution":{"observed_at":"2026-08-07T10:52:06.409424Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.397770Z","title":"Comm. Rounds","venue":null,"work_id":"3898beff-907e-4d86-952f-9230c2dcbe09","year":null},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.000776Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:22c84f79b226791c0818293990d8af4c650e0abfc1ca6e6f0a0c4e22615c4cf6","observation_id":"945f05bb-6fbe-408d-b9d5-15392e902119","resolution":{"observed_at":"2026-08-07T10:52:06.400510Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.388972Z","title":null,"venue":null,"work_id":"1b987d6f-920d-43c6-b350-1f05e897441c","year":null},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.003899Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:7e20b6502a9f207e1f9a55a2f4d212bf8020932b29b2d0fad6791d4a723ad154","observation_id":"1d7a2b47-eb57-49eb-88a2-4a5a06df6162","resolution":{"observed_at":"2026-08-07T10:52:06.392054Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.342588Z","title":"We accomplish this by projecting local data to a space that encodes all local data, in turn minimizing the distributional discrepancy between agents","venue":null,"work_id":"023178f5-0b9f-44e4-9e5d-80622cdd1745","year":null},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.019056Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:910f558b140530272218b997725e3e048053608486d687d6d3d3bff57af1b8e7","observation_id":"2d7158d9-bb32-40ae-928a-864c2a278bcb","resolution":{"observed_at":"2026-08-07T10:52:06.345722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.258153Z","title":"Collaborative op- timization and aggregation for decentralized domain generalization and adaptation,","venue":null,"work_id":"a657d296-85e3-43b0-8e63-5f2306ad9aa0","year":2021},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.045815Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:c47d40c36088c87909967398682d914818a66eafed960e0d22c066d878b42123","observation_id":"6697d553-a21a-4448-a773-e971b8d9cd2a","resolution":{"observed_at":"2026-08-07T10:52:06.261279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.360760Z","title":null,"venue":null,"work_id":"57077783-eaee-4608-ab70-1069543313a2","year":null},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.013132Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:1ada6c87fb63da31fa296d472223ef4d06b87b7ec360816fa04813f2db59d2cc","observation_id":"751bf1b8-5552-43cd-96f0-e37f26fe5c69","resolution":{"observed_at":"2026-08-07T10:52:06.363758Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.351812Z","title":"Therefore, we have O(M d2/ϵ2) for local barycenters and O(N d2/ϵ2) for the global barycenter","venue":null,"work_id":"68196639-4ec3-4334-96c8-22c47c6834d7","year":null},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.016093Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:2ecef855e2a37317dad807c3f2e2d562e583b6c1da821622fd75ffe2a8c6e821","observation_id":"a051c305-130f-48b5-a122-1c793cca432d","resolution":{"observed_at":"2026-08-07T10:52:06.354893Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.238745Z","title":"Clustered federated learning: Model-agnostic distributed multitask optimization under privacy con- straints,","venue":null,"work_id":"c33b32e7-9218-4ec0-9093-f74806fe5912","year":2020},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.056054Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:91539df51cbc0c47f6f1f494d03b6e5ae31865716b49a7f380a6b6ae5e82e764","observation_id":"f25da86b-be7e-45ae-b7fe-34ae16f3b02d","resolution":{"observed_at":"2026-08-07T10:52:06.242412Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.333547Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":"e1c8a9c8-b93f-42bf-a1ec-a4a0e80cf9fc","year":2017},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.022061Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:ad37d9eeb49401de6d05c2b1f5554faf73787a138597411a7c0c000c35796021","observation_id":"f5e5d2d9-723c-4a4d-9347-25612337e1a3","resolution":{"observed_at":"2026-08-07T10:52:06.336492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.324807Z","title":"Towards personalized federated learning,","venue":null,"work_id":"6002125e-6546-44bf-a668-820ca61793d6","year":2022},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.025113Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:bb384e8908795bab86a134f9fed620c59c1ab0cc7ca06ba44029d4dc1a84b9e3","observation_id":"f739e827-4977-44d6-b413-d2b60d38fa67","resolution":{"observed_at":"2026-08-07T10:52:06.327889Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.315398Z","title":"Federated learning: Challenges, methods, and future directions,","venue":null,"work_id":"1bca6760-a822-450f-b5fd-c3fdabddf816","year":2020},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.028168Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:991bfcd03520ff36848c11ec1500ec986dd6ba1b4fa9040ae0abd982efa06404","observation_id":"80fd8e3d-6b84-446e-8693-f252f787f85e","resolution":{"observed_at":"2026-08-07T10:52:06.318700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.306010Z","title":"Fedprof: Selective federated learning based on distri- butional representation profiling,","venue":null,"work_id":"5df2935f-62c8-4128-aa4b-5609dfc065ba","year":1942},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.031062Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:7e588cf3e01cff4bfd1deaea0d59c7121ef5414a3e509833c634561e696eae1d","observation_id":"06f7850a-7c16-4a6b-bf0f-dcaac907ff66","resolution":{"observed_at":"2026-08-07T10:52:06.309261Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.296604Z","title":"An optimal transport approach to personalized federated learning,","venue":null,"work_id":"7f847033-49ce-4279-a9d5-de175c53a3ac","year":2022},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.033940Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:69940d347d856c042e5d022033e619c0e6dff17fd1c108fd1857754cef9b6547","observation_id":"5b65007e-a13a-4138-a9d0-8c1f544bdd77","resolution":{"observed_at":"2026-08-07T10:52:06.299529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.286888Z","title":"Regularized discrete optimal transport,","venue":null,"work_id":"818c8c82-c38a-4cae-b4ef-4fe6bb407735","year":2014},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.037098Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:11444a608ea2934b1c252341a05e02a68d31b3868c4fd8b1c7616fc1cbb31435","observation_id":"b27be5b4-63bb-48fe-86a3-e30ce1b82f60","resolution":{"observed_at":"2026-08-07T10:52:06.290010Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.277693Z","title":"Generalizing to unseen domains: A survey on domain generalization,","venue":null,"work_id":"3fa425c2-d838-421f-8ce9-49c1d2b9a28d","year":2022},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.039908Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:954cb55079e7fb5bc99be03168ff6df12f9d0099c92ee54f7b659d901025c16d","observation_id":"284b1624-462f-4b34-8ab8-ab82c7d50799","resolution":{"observed_at":"2026-08-07T10:52:06.280742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.267897Z","title":"Fedhealth: A federated transfer learning framework for wearable healthcare,","venue":null,"work_id":"44a4437d-829f-4a34-98ac-9c09e5231585","year":2020},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.042778Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:e9522e4d71cb23fed7e0f2d47d3499348c663de1902bb1c6283878d1c14c3e73","observation_id":"fe0ece62-ebec-41be-a5dc-62f9dc6ccd75","resolution":{"observed_at":"2026-08-07T10:52:06.271117Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.370594Z","title":null,"venue":null,"work_id":"00fc44b3-e65e-48ec-9b44-e989680965e5","year":null},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.010239Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:c70e8f96a5adef2674e2b3aba59c5a7ec943bd868b4ea189e163151cded49398","observation_id":"ba9c6035-f508-4315-8e9f-abd65e0c3a32","resolution":{"observed_at":"2026-08-07T10:52:06.373459Z","resolver_source":"raw_fallback","status":"parse_uncertain"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.379408Z","title":"Given n samples of dimension d and reg- ularization parameter ϵ, we have a complexity of O(nd2/ϵ2)","venue":null,"work_id":"dfe2732c-8298-48de-9454-b1285c1ae09b","year":null},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.007309Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:9858afd2f8c1be25325d19fa2fc2bc4b7aff908bac817b69ed4fd5701849625a","observation_id":"c2800948-9cc1-4efc-9784-b00a08d016ee","resolution":{"observed_at":"2026-08-07T10:52:06.383091Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2111.10487","last_updated":"2023-01-07T04:15:38Z","snapshot_observed_at":"2026-07-06T12:10:24.153958Z","submitted_at":"2021-11-20T01:02:36Z","title":"Federated Learning with Domain Generalization","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.10487","snapshot_observed_at":"2026-08-07T10:52:06.048858Z","title":"Federated learning with domain gen- eralization,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.048858Z"},"links":{"cited_paper":"/paper/2111.10487","citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:bc87b297e77d7b0f13adb9ebcc0b23c91c5a734932fd2f46122c2bd5b16dc48c","observation_id":"673ba6e1-dd3b-4d27-88b2-f60f0fbc40a5","resolution":{"observed_at":"2026-08-07T10:52:06.048858Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.248804Z","title":"Learning to generate novel domains for domain generalization,","venue":null,"work_id":"75286fff-e797-41aa-99b7-04fa2fddffd7","year":2020},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.052946Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:dcebd07cb8469e18a3a924b5d0938292fb37ed4d5f1069d54c17e68aea59b3f5","observation_id":"fc66689c-ff95-4573-b3a2-e76f54e4ff5f","resolution":{"observed_at":"2026-08-07T10:52:06.252160Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.229418Z","title":"Federated visual classification with real-world data dis- tribution,","venue":null,"work_id":"b0338613-98a5-4063-9ae2-93d576793e05","year":2020},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.059197Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:1902cac238cada60f8b81cfd26d36203a65439680b846bcd8701d8727cc2bf1e","observation_id":"cce86920-8cfe-4190-9459-0c04a988cfd2","resolution":{"observed_at":"2026-08-07T10:52:06.232582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.219818Z","title":"Personalized federated learning with theoretical guar- antees: A model-agnostic meta-learning approach,","venue":null,"work_id":"6302f536-ad54-4a24-b684-a7d372af8d60","year":2020},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.061738Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:b9ff075b3af9ea79c0faaf89019e088d5a5cd813dbbeff7abc180e3e0a15c491","observation_id":"3f47db98-3bc1-4819-8d98-a27a3bf72e24","resolution":{"observed_at":"2026-08-07T10:52:06.223026Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.210669Z","title":"M ´emoire sur la th´eorie des d´eblais et des remblais,","venue":null,"work_id":"f9b8af33-7ef0-4526-bb71-267232200191","year":null},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.064460Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:7609afd678737d7ea84109a87dd0be9a77cb85c0758a2c6501d48e1cbb9bd1a4","observation_id":"57726d5b-5183-48a0-9b83-db3b5e8095a6","resolution":{"observed_at":"2026-08-07T10:52:06.213581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.201278Z","title":"Fast computation of wasserstein barycenters,","venue":null,"work_id":"4e60f8bd-08e1-4ea6-bb36-4e47abc7a412","year":2014},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.067154Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:d7d078e725f92cfc4a7aeb292261b4df08f70574bdc0e6bd1b745da1a341e6bf","observation_id":"0cfe1d15-4fd2-4b5f-a43b-8fcbd6fffeb6","resolution":{"observed_at":"2026-08-07T10:52:06.204392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.190943Z","title":"Sinkhorn distances: Lightspeed compu- tation of optimal transport,","venue":null,"work_id":"358d0fb5-b2b2-4e81-9726-7949b9f500f5","year":2013},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.070748Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:486965d8f51401a7877bb7bfdce49344b776462988e35934c16532312db62f66","observation_id":"5a37cab9-5b1f-4a73-9c73-533ca63382e0","resolution":{"observed_at":"2026-08-07T10:52:06.194460Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.180768Z","title":"Iterative bregman pro- jections for regularized transportation problems,","venue":null,"work_id":"333d5759-341a-4803-82a3-1af48b27c3c1","year":2015},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.073590Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:e58eb635e63791e8a68a415d9c355c677d75104a7d88d1a864f42dd87c8219fe","observation_id":"7609d66b-761f-49c7-970e-5f471b88962a","resolution":{"observed_at":"2026-08-07T10:52:06.183867Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.170626Z","title":"Model- contrastive federated learning,","venue":null,"work_id":"7a0fc413-d0f0-442a-b29a-84a2ea306d23","year":2021},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.076395Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:89931c2ceadd08763b5f54ec2c381d67b136c3fae3078c2c95c0f9337a87aee8","observation_id":"c9cf2055-f445-46bd-ab3f-6107e4bac110","resolution":{"observed_at":"2026-08-07T10:52:06.174112Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.06440","last_updated":"2020-02-15T20:09:24Z","snapshot_observed_at":"2026-08-06T14:46:34.371139Z","submitted_at":"2020-02-15T20:09:24Z","title":"Federated Learning with Matched Averaging","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.06440","snapshot_observed_at":"2026-08-07T10:52:06.079292Z","title":"Feder- ated learning with matched averaging,","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.079292Z"},"links":{"cited_paper":"/paper/2002.06440","citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:bec3db2d87d1e864932be7ed7d2fec68f3db0771ea336a2f7af34a4b7ee8b3c3","observation_id":"bfd2b3b9-7e97-44a7-9bb2-e82c5205d7bb","resolution":{"observed_at":"2026-08-07T10:52:06.079292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.160411Z","title":"No fear of heterogeneity: Classifier calibration for federated learning with non-iid data,","venue":null,"work_id":"f739a288-ea86-41b8-bd19-71b567a495fe","year":2021},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.082546Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:8451ea32137b1f6b779260a7a4cf2d74c15bbd56a5c1a2aa7b42b709481fa2f9","observation_id":"0bb0a9bc-777b-437b-9420-293b94d865e5","resolution":{"observed_at":"2026-08-07T10:52:06.163735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:52:06.150631Z","title":"On the complexity of approximating wasser- stein barycenters,","venue":null,"work_id":"1f112571-10cc-446c-994e-96230434cf00","year":2019},"citing_paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T10:52:06.085397Z"},"links":{"citing_paper":"/paper/2506.04071"},"observation_digest":"sha256:6929ab96d7b6da995af789a2beb3ef7edd86c5090b85a9e3bf324340398b980b","observation_id":"4ecdcf03-5d1d-4d80-ac3b-df4b1e4fb8a2","resolution":{"observed_at":"2026-08-07T10:52:06.153948Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.04071","last_updated":"2025-06-04T15:35:55Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T17:12:33.347275Z","submitted_at":"2025-06-04T15:35:55Z","title":"Optimal Transport-based Domain Alignment as a Preprocessing Step for Federated Learning"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":2,"unresolved":4,"verified_exact":1,"verified_fuzzy":27},"total_outbound_references":34},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 34 of 34 outbound references and 1 inbound Pith citation observation for arXiv:2506.04071."}