{"as_of":"2026-08-22T06:43:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a2047af523a44901dbebd6a94d2d5c549178be56cd9c18741afae0a8e6cd277b","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T10:50:59.447686Z","state":"measured"},{"denominator":46,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":46,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-22T06:32:14.747728+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/2507.23461/citation-record","integrity":"/paper/2507.23461/integrity","json":"/paper/2507.23461/citation-record.json","paper":"/paper/2507.23461"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T10:51:00.348581Z","title":"Federated learning for iot devices with domain generalization,","venue":null,"work_id":"3d1b2085-edab-4381-ae20-88e3e8a420ea","year":2023},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.222407Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:bf87d4c10007e1bbdbeb94519d7aec2c3f58197670221dce124fb57ff3669777","observation_id":"84072829-1952-4e5b-9525-cce8711d757a","resolution":{"observed_at":"2026-08-06T10:51:00.354852Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:51:00.329713Z","title":"Communication-efficient federated learning for wireless edge intelligence in iot,","venue":null,"work_id":"ae3f32f3-c683-45dd-a2a0-c14df7cb73fe","year":2020},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.227235Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:5a697286eb2ca88e0d2b703ef4a4ff6842619629d8d94c7d11543bd0e2066a4c","observation_id":"4211d081-2e19-4e28-bfad-b82fde8090d9","resolution":{"observed_at":"2026-08-06T10:51:00.335701Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:51:00.310604Z","title":"Edge intelligence: The confluence of edge computing and artificial intelligence,","venue":null,"work_id":"463187e2-7dc7-470f-bc10-0cf8804beb94","year":2020},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.232081Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:ac0f5ded151be4609889b3f8750d78f76973bf43e41d3af7be492c8c7a29d0a7","observation_id":"81ac2915-0d1a-4b98-a171-e61cdf178bbe","resolution":{"observed_at":"2026-08-06T10:51:00.316120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:51:00.281411Z","title":"Wireless edge computing with latency and reliability guarantees,","venue":null,"work_id":"0e94d9d7-e238-4ee4-825c-91cdca1eb615","year":2019},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.238634Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:34d4921e9559485c45aa9e3fcf6768512bd95576dfaa19231b66a9338c650b79","observation_id":"bf15a92f-50b0-48e6-ad33-f582ffaf08bb","resolution":{"observed_at":"2026-08-06T10:51:00.296775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:51:00.262326Z","title":"Decentralized edge intelligence: A dynamic resource allocation framework for hierarchical federated learning,","venue":null,"work_id":"bba86539-2b77-4fd5-b1de-f0f58697b7db","year":2022},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.244310Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:95c0eddfcaaaf116467947ae87220b1b02ab356cba5d46a4b73860c39270079f","observation_id":"9d7fa7f5-3aed-4127-ad09-ce523af5242b","resolution":{"observed_at":"2026-08-06T10:51:00.267726Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:51:00.241325Z","title":"Communication-efficient learning of deep networks from decentralized data,","venue":null,"work_id":"4bb78466-ac91-4eac-8eda-43febc48031d","year":2017},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.250011Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:7a3c8f491e45cc3d191635195b25c8a393eb669286aa46e8698823ceb1469f08","observation_id":"902c19ee-eb4f-4795-ad8e-2ecf4cf384d4","resolution":{"observed_at":"2026-08-06T10:51:00.248267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.255440Z","title":"Federated learning: Challenges, methods, and future directions,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.255440Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:6d4fc8240d291fe470eecf4a5a3edccf739cf6276362a67e7a72545360079f00","observation_id":"20f0bccc-8ee3-48de-97f8-8b0945bd479f","resolution":{"observed_at":"2026-08-06T10:50:59.255440Z","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":"2026-08-06T10:51:00.206290Z","title":"Federated optimization in heterogeneous networks,","venue":null,"work_id":"0aa6f09a-2998-45fa-ae50-ec6e6e4227a4","year":2020},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.259836Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:a39ea70bb656d7fe1416bc644f94ea29e6990ad13c92c1ecce844a75a8748694","observation_id":"ee1e062d-9cca-48af-b3f4-0a523e2f9521","resolution":{"observed_at":"2026-08-06T10:51:00.213783Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:51:00.185827Z","title":"Scaffold: Stochastic controlled averaging for federated learning,","venue":null,"work_id":"75ca2eb2-f8d6-4374-a85a-ba9453621359","year":2020},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.264549Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:9caf739cb0263d0b037be953e299c0c85601e8c2ce69d307bc1f2b2d1268a8c5","observation_id":"3b80822f-b009-41b5-8849-b399b3f26a1b","resolution":{"observed_at":"2026-08-06T10:51:00.193709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:51:00.163060Z","title":"Simple baselines for human pose estimation and tracking,","venue":null,"work_id":"caf16d5f-231a-4652-be57-9189b5806350","year":2018},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.269773Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:98c67217f576ac8cfcd7690c23b6e2fd77bec769a27687ffbc431aac4ae63127","observation_id":"3de1fcb2-585c-45f9-b00d-93854aa14c4d","resolution":{"observed_at":"2026-08-06T10:51:00.168413Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:51:00.144506Z","title":"Vitpose: Simple vision transformer baselines for human pose estimation,","venue":null,"work_id":"4a31bcd4-0cd6-4dd4-b57a-5c2a06ce6e0d","year":2022},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.274508Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:b600a9cb862579e079af175245ce0d390d22d3aa2f039f0966bbfc1496453487","observation_id":"9581aaa2-5e48-445a-8724-8c049f595473","resolution":{"observed_at":"2026-08-06T10:51:00.150895Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:51:00.123711Z","title":"Deep high-resolution repre- sentation learning for human pose estimation,","venue":null,"work_id":"9f6b4ab5-15f1-4b8a-95bf-a63d7f8997b6","year":2019},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.279779Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:80868ef9038b78979e4d6eb0e4f6b3ea4f096510aa22c4f86335df80c2cdfe5a","observation_id":"c4db34d2-c445-45b6-aa52-98af48cb88a0","resolution":{"observed_at":"2026-08-06T10:51:00.131469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:51:00.099402Z","title":"Redefining non-iid data in federated learning for computer vision tasks: Migrating from labels to embeddings for task-specific data distributions,","venue":null,"work_id":"cd0cc875-5419-4f80-8153-974ecb91d632","year":2025},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.285389Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:d0a547c3383518620138259af08e403d4d1ed140bbd58937c5f10aa7f8f61aa6","observation_id":"70c6e142-0e83-4b58-a954-3572a0222a22","resolution":{"observed_at":"2026-08-06T10:51:00.108206Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-08-16T18:00:58.008096Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-06T10:50:59.290295Z","title":"Distilling the knowledge in a neural network,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.290295Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:2e62a1f8c54dd6bf32fb992da7f67a057b5d8dcccf8851032f6568ecc4e4c860","observation_id":"7c07f221-c9df-4ecd-9c53-4388920045c0","resolution":{"observed_at":"2026-08-06T10:50:59.290295Z","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":"2026-08-06T10:51:00.073134Z","title":"Self-distillation amplifies regularization in hilbert space,","venue":null,"work_id":"d6c735f3-9425-48a3-a91c-8743f35bc2bd","year":2020},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.295404Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:81a22c82f27b805bf44d17eb2a355ed060e1057cf0f9624f5ad90c361a72a8f5","observation_id":"9df53b79-6f34-46f7-aaca-63b63b731eb2","resolution":{"observed_at":"2026-08-06T10:51:00.081235Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:51:00.043432Z","title":"Revisiting knowledge distillation via label smoothing regularization,","venue":null,"work_id":"d8e9b816-5d67-492f-86ba-6abdf9719188","year":2020},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.300867Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:79af98ada29490f4503f7c90746114e020f63afb7e1ade1293d1bf7f461b8715","observation_id":"e26535b3-8d4b-4011-9761-59465c4ba6ff","resolution":{"observed_at":"2026-08-06T10:51:00.051798Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:51:00.023731Z","title":"Resformer: Scaling vits with multi-resolution training,","venue":null,"work_id":"491b807a-67de-4d30-bca3-ac6363a43fb2","year":2023},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.305397Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:bf1aba92419d7a9c2b6ccb876b914cc1963767a2de30f0660ff268ac998a6f84","observation_id":"07ae4827-a764-4bce-8a2c-dcc0837be56c","resolution":{"observed_at":"2026-08-06T10:51:00.030349Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.999907Z","title":"Tackling the ob- jective inconsistency problem in heterogeneous federated optimization,","venue":null,"work_id":"9a7c6d00-4883-4554-b2a3-abb0bfb1888c","year":2020},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.309915Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:b77bd3be1c244556e9325bb825fcb1b6958ca87cc62a0731157510d7fdd8c6c0","observation_id":"685b76db-80cd-488e-968e-d46ac3184383","resolution":{"observed_at":"2026-08-06T10:51:00.007675Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.978105Z","title":"Model-contrastive federated learning,","venue":null,"work_id":"ce55a7df-87f8-47b8-b23e-27d64aa549a7","year":2021},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.314902Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:b05754e1c4045f47487c7579dfb392a19714c920cdd6b3e41ac9f5e7c4857da7","observation_id":"5fc9bdbe-7717-43e9-996b-6cd1de48308b","resolution":{"observed_at":"2026-08-06T10:50:59.983961Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.959231Z","title":"Feddyn: A dynamic and efficient federated distillation approach on recommender system,","venue":null,"work_id":"11c9e440-38f4-4b43-8032-cd3268e918c9","year":2022},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.319940Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:1fdfbda866bfa6181d58cf7525dbc20134f9d436510a36cb8ffe4796cf3b30b1","observation_id":"04d64ab3-c76b-424a-9061-be1ecf083d82","resolution":{"observed_at":"2026-08-06T10:50:59.964651Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.324717Z","title":"Attention is all you need,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.324717Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:66d6521aef817f778cb0b22ea51736f98279b9382e03a096d66ac5de9a0e2608","observation_id":"e7572121-5665-476a-8daf-1c66e071b5bd","resolution":{"observed_at":"2026-08-06T10:50:59.324717Z","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":"2026-08-06T10:50:59.930237Z","title":"Bert: Pre-training of deep bidirectional transformers for language understanding,","venue":null,"work_id":"fc82e31e-874e-4c09-896b-3022f5b2e2b9","year":2019},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.329209Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:bc94b1fb9475c26ad317fe44b1f9204317f77124605110020f6eafac957a7108","observation_id":"3f723030-8e6d-4d23-8ee5-cf2d17b2c094","resolution":{"observed_at":"2026-08-06T10:50:59.935836Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.08774","last_updated":"2024-03-04T06:01:33Z","snapshot_observed_at":"2026-08-17T09:58:46.058102Z","submitted_at":"2023-03-15T17:15:04Z","title":"GPT-4 Technical Report","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.08774","snapshot_observed_at":"2026-08-06T10:50:59.333675Z","title":"Gpt-4 technical report,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.333675Z"},"links":{"cited_paper":"/paper/2303.08774","citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:304515bdcb0be32a890e69a6e06e53ccbf0eea329950355df3078c01c5e09e20","observation_id":"952b0054-4065-420a-9417-30b62795e6a9","resolution":{"observed_at":"2026-08-06T10:50:59.333675Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2302.13971","last_updated":"2023-02-27T17:11:15Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-02-27T17:11:15Z","title":"LLaMA: Open and Efficient Foundation Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.13971","snapshot_observed_at":"2026-08-06T10:50:59.338922Z","title":"Llama: Open and efficient foundation language models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.338922Z"},"links":{"cited_paper":"/paper/2302.13971","citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:3e75a905acd0cc566eb080332ba02b78c33ac5463717e53e2838ad2e4e23403d","observation_id":"e911fdb1-9126-4a69-a4c2-70f462d8dd26","resolution":{"observed_at":"2026-08-06T10:50:59.338922Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.08821","last_updated":"2024-12-15T21:20:12Z","snapshot_observed_at":"2026-08-16T08:10:37.041600Z","submitted_at":"2024-12-11T23:36:20Z","title":"Large Concept Models: Language Modeling in a Sentence Representation Space","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.08821","snapshot_observed_at":"2026-08-06T10:50:59.344074Z","title":"Large concept models: Language modeling in a sentence representation space,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.344074Z"},"links":{"cited_paper":"/paper/2412.08821","citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:c436f2ea4a5817b28de0f18f91c13ede9eac7e31ea59544662523d98ebd7d805","observation_id":"f6cd316c-689e-4eac-8460-81ee4ac5d8f1","resolution":{"observed_at":"2026-08-06T10:50:59.344074Z","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":"2026-08-06T10:50:59.349135Z","title":"An image is worth 16x16 words: Trans- formers for image recognition at scale,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.349135Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:601f408ee7545a97eb2bab8cbdd1892a6a7478267e1ba5f01be13ff3c38f663e","observation_id":"4e3d9598-39e3-4da3-8b6b-73039b00eb90","resolution":{"observed_at":"2026-08-06T10:50:59.349135Z","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":"2026-08-06T10:50:59.897935Z","title":"Training data-efficient image transformers & distillation through attention,","venue":null,"work_id":"bb5252a2-59eb-4526-9920-cc5a95a04dee","year":2021},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.353618Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:3cdc85a0cfb3dbbffdfc126cb2008f3eda51dc5458455cf746515f87468c3292","observation_id":"9cdb88e2-7274-4e98-9806-02bc4a3b29e1","resolution":{"observed_at":"2026-08-06T10:50:59.902725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.881449Z","title":"Scalable diffusion models with transformers,","venue":null,"work_id":"56ec7410-ff72-4f61-b306-47a1cb14d0df","year":2023},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.358063Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:6eef9a0495cea070d272c17516efe4c0d69323c39842b0cc68f69ec3102c63bd","observation_id":"04e2bca0-4900-4c16-9188-0d3cdc22a722","resolution":{"observed_at":"2026-08-06T10:50:59.886269Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.864159Z","title":"Dinov2: Learning robust visual features without supervi- sion,","venue":null,"work_id":"dd8bb355-0c77-4b31-99d4-75d358a835a2","year":2024},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.363020Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:52956f596c7cba5beda1d5119a40cb653cd528d8df26afc1ed30f349b61ed8a1","observation_id":"c16a4eb3-2c46-48d4-b968-1fa216a88f86","resolution":{"observed_at":"2026-08-06T10:50:59.869700Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.845128Z","title":"wav2vec 2.0: A framework for self-supervised learning of speech representations,","venue":null,"work_id":"0075cced-2fac-426a-80d4-fb41e78600c1","year":2020},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.367307Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:fb97a06c81f90b9fb9f96a8ae7f750d8cad8702c66dcdc9d42202b749e7bb4c2","observation_id":"a76f687e-9605-41c8-8739-ad873a2ddc62","resolution":{"observed_at":"2026-08-06T10:50:59.851113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.827305Z","title":"Audiolm: A language modeling approach to audio gen- eration,","venue":null,"work_id":"0da2108f-a2e9-446d-aa95-7a1c73fd3161","year":2023},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.371935Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:5bf4efa3b4f9d87023cb4e70f1553189e3870fe60d07b940fa8c8fbae77a021b","observation_id":"a5e6459a-8716-4a72-822b-4fb6fa87edf2","resolution":{"observed_at":"2026-08-06T10:50:59.832406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.808687Z","title":"Ast: Audio spectrogram transformer,","venue":null,"work_id":"68c5ade9-bae2-4e62-88a3-37118d36ffdf","year":2021},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.376656Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:e5d5e1a0cde5432e940d111ef507cfb8936ba98a238a811c6c1a67e3a152d7ca","observation_id":"c24f7a16-6326-49a9-ad12-9daaf5c69c82","resolution":{"observed_at":"2026-08-06T10:50:59.814153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.789004Z","title":"Learning transferable visual models from natural language supervision,","venue":null,"work_id":"93a78447-d305-40e6-8030-535f5bcff1f1","year":2021},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.382000Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:34d48987148e6b137a2f63bc0600cedaf3dcad1a7b8e40241fec5ceef4959955","observation_id":"1ca6f2a2-0915-4cd3-841e-8e5aa422c120","resolution":{"observed_at":"2026-08-06T10:50:59.794825Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.772196Z","title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models,","venue":null,"work_id":"73af339e-6ec4-4e31-8b5d-70e6caea235c","year":2023},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.387168Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:70f16bee6edb993f4c27e4efdfe544dc289dbd4ac24c6d86207bd983585b6397","observation_id":"925dc212-b911-4f4a-8353-d789d77dc418","resolution":{"observed_at":"2026-08-06T10:50:59.777101Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.755804Z","title":"Visual instruction tuning,","venue":null,"work_id":"40220d03-0b8a-4197-946e-d9ba87015cde","year":2023},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.392532Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:daef4d6e214ebcc58ccf60683786988fcb1a2dfc17310ad9bc456039c0103a77","observation_id":"5175cd84-3b41-4d1e-919b-e4d8d36429f8","resolution":{"observed_at":"2026-08-06T10:50:59.760406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.740230Z","title":"The prospect of enhancing large-scale heterogeneous federated learning with foundation models,","venue":null,"work_id":"912e8fdf-2e92-4b00-8941-95449fa67959","year":2024},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.398011Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:0ebb64c407419b93b8adb6596ec4c4f3eda675f9aca38db2ba3ff2732d11b887","observation_id":"c21fc75f-2b1f-4df7-af2b-9317e9f38c9a","resolution":{"observed_at":"2026-08-06T10:50:59.745168Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.04905","last_updated":"2023-07-10T21:08:52Z","snapshot_observed_at":"2026-08-19T12:24:35.392889Z","submitted_at":"2023-07-10T21:08:52Z","title":"FedYolo: Augmenting Federated Learning with Pretrained Transformers","version":1},"cited_work":{"arxiv_id":"2307.04905","doi":null,"metadata_source":"pith","pith_arxiv_id":"2307.04905","snapshot_observed_at":"2026-08-06T10:50:59.492535Z","title":"FedYolo: Augmenting Federated Learning with Pretrained Transformers","venue":"cs.LG","work_id":"72498fc9-8a3b-43e6-b274-965ccf8cc163","year":2023},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.403019Z"},"links":{"cited_paper":"/paper/2307.04905","citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:e35c32c74ea402b26840eeac8e9d1c1645bd9adfa41db428dc0a422237e1297a","observation_id":"1c208ca9-2b89-42c1-bd65-878d2c3098be","resolution":{"observed_at":"2026-08-06T10:50:59.500574Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.723876Z","title":"Deep high-resolution representation learning for visual recognition,","venue":null,"work_id":"0211b645-ebc7-4d8a-9fca-bff823f0cd46","year":2021},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.407966Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:03b88f143ab649a299e5e71d8f5d7d5a98ee65501374c0fc003281badbdc3123","observation_id":"53c3dc91-dcd0-47d7-a14f-c5c043300399","resolution":{"observed_at":"2026-08-06T10:50:59.728707Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.704291Z","title":"Bootstrap your own latent – a new approach to self- supervised learning,","venue":null,"work_id":"55be5088-f225-4fc8-b32d-9fca3db4072c","year":2020},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.412873Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:11a9929b0ab7ab9c41f28d12c8eca7a1a3c9a2fe89b6d8e6ca714db1e5bf2407","observation_id":"46a36c6b-aa04-42b5-aaab-25561eed4359","resolution":{"observed_at":"2026-08-06T10:50:59.710219Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.684577Z","title":"On lazy training in differentiable programming,","venue":null,"work_id":"9034d7dc-bae7-4d47-81f0-5ef58538880d","year":2019},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.417516Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:11f7af2778b55706ede5db538808d12a9f30d05d61a4a8d9d75328ae35097367","observation_id":"91962131-793a-4f99-96fe-ae73cce4c088","resolution":{"observed_at":"2026-08-06T10:50:59.689724Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.667170Z","title":"Gradient descent maximizes the margin of ho- mogeneous neural networks,","venue":null,"work_id":"f71e7e3c-53c5-4471-b2a7-a8072ee35311","year":2019},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.422657Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:73b11a031a12e3f7f53e10b2b937cabd9604145513d93150bcb67ac2c8e29480","observation_id":"5b8f9e71-51bc-427b-8380-fbcb950f25fb","resolution":{"observed_at":"2026-08-06T10:50:59.672528Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.649536Z","title":"Prevalence of neural collapse during the terminal phase of deep learning training,","venue":null,"work_id":"a8db693d-7cfc-4ad6-9a3d-9d72f4db5c32","year":2020},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.427421Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:b714d4e32fcb17de16fa37a1e5b3e287649abd813645d212ab4fc3dfa75ddcdb","observation_id":"7faf076a-a0ea-4537-9273-a673f4f83da0","resolution":{"observed_at":"2026-08-06T10:50:59.654156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.632742Z","title":"On the convergence of fedavg on non-iid data,","venue":null,"work_id":"52fd0b5a-a275-4b1f-9907-42bc2fdb5f6b","year":2020},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.432938Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:e63c898440b30cd5e60d094f9fd2b1b449ade888497b6571e6bbb0e08f21681f","observation_id":"6e4c1f47-4e0e-4461-9bc9-18b1ecfccc3a","resolution":{"observed_at":"2026-08-06T10:50:59.638188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.615861Z","title":"2d human pose estimation: New benchmark and state of the art analysis,","venue":null,"work_id":"86543a92-c531-48de-9d98-b02a1466d56b","year":2014},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.438287Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:f6d183d106da6251d1453e6016e639669cac4eda2a3629b7bc5c3ce8693d54ad","observation_id":"7220b2bb-4a4a-4cdc-b3da-c52204b96109","resolution":{"observed_at":"2026-08-06T10:50:59.620779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+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":"2026-08-06T10:50:59.443212Z","title":"Deep residual learning for image recognition,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.443212Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:b68d3254469528252222c9b968e8de3fe098bd53eddbf22ae16cef0d7b06eea2","observation_id":"8d4d7e05-501e-4b98-a5ae-bb0ab72b858b","resolution":{"observed_at":"2026-08-06T10:50:59.443212Z","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":"2026-08-06T10:50:59.588347Z","title":"Fully convolutional networks for semantic segmentation,","venue":null,"work_id":"c47587f1-c9e1-422e-8db2-0d88c2d2ad80","year":2015},"citing_paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-06T10:50:59.447686Z"},"links":{"citing_paper":"/paper/2507.23461"},"observation_digest":"sha256:635852105560ecf179d52bbb734a99f8e98e7dcdebdbaaa77c1d03f189e48c2b","observation_id":"33d322c6-fb9a-4a64-a95a-92f7f15c3dae","resolution":{"observed_at":"2026-08-06T10:50:59.593481Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.23461","last_updated":"2025-07-31T11:38:20Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-17T16:01:47.327042Z","submitted_at":"2025-07-31T11:38:20Z","title":"Mitigating Resolution-Drift in Federated Learning: Case of Keypoint Detection"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":1,"verified_fuzzy":37},"total_outbound_references":46},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 0 inbound Pith citation observations for arXiv:2507.23461."}