{"as_of":"2026-08-08T22:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5036941422b582296841d1b5a037170e752a1721b380e4329d80301f7a8fab55","coverage":[{"denominator":54,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":54,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T12:37:37.991885Z","state":"measured"},{"denominator":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2505.24185/citation-record","integrity":"/paper/2505.24185/integrity","json":"/paper/2505.24185/citation-record.json","paper":"/paper/2505.24185"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:48.491223Z","title":"Neural multi-task learning in drug design","venue":null,"work_id":"ca20a073-e5ca-4d00-9670-66f6272ef254","year":2024},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:32.970953Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:3fdc7f0dadfc7f29c1d54513e27f6341a5065cfbf93ad2aef3f49b86387e7987","observation_id":"c765bfe9-386a-4220-a10f-2e87a4258eac","resolution":{"observed_at":"2026-08-07T12:37:48.570588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:48.304200Z","title":"Advancing covid-19 diagnosis with privacy-preserving collaboration in artificial intelligence","venue":null,"work_id":"ad338a7e-6992-4844-9f47-e991eaa72af8","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:33.064278Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:ced72a6d5f573d3e55edc073b2fa49dd51154a10f8fa549c3370518ac083da91","observation_id":"8cc88b3f-df73-455a-9369-8d5132c6a974","resolution":{"observed_at":"2026-08-07T12:37:48.378858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:47.991767Z","title":"Federated disentangled representation learning for unsupervised brain anomaly detection","venue":null,"work_id":"61fc3f77-e3d7-464a-bac4-52ed5155eace","year":2022},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:33.161168Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:75af3665325f646229249e2414ffa3eaea14343a4733f0b9da373c42692e9983","observation_id":"8f1a3539-b521-4898-9dc5-0e2005c67891","resolution":{"observed_at":"2026-08-07T12:37:48.141414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:47.680800Z","title":"Many-task federated learning: A new problem setting and a simple baseline","venue":null,"work_id":"70b82f7b-d931-40e6-8076-a0fe09459da4","year":2023},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:33.337634Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:66c45d81b73ad44f69e02205174bbb382fdd0fd02b93ceaeb914aa304a65a3f7","observation_id":"1e92e8df-34c0-4a00-8214-26b14abe1dfe","resolution":{"observed_at":"2026-08-07T12:37:47.812447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:33.436129Z","title":"Multitask learning","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:33.436129Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:d3d6ebe1b438a746b18bd0deed510573922a1e2356c1f8ff4b7a3a857ac80533","observation_id":"315cfdd9-4b3b-48b7-bc15-d896f0ab082a","resolution":{"observed_at":"2026-08-07T12:37:33.436129Z","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":"2026-08-07T12:37:47.304904Z","title":"Fraug: Tackling federated learning with non-iid features via representation augmentation","venue":null,"work_id":"6ec843b2-492c-43f3-9483-cc52e9ce577f","year":2023},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:33.522202Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:c096ad57365caaa55ac95b7838fdc7b738cb034347dd9a47e6819138aea3fe12","observation_id":"455f7ac3-04e6-470d-839f-831ff5bfca33","resolution":{"observed_at":"2026-08-07T12:37:47.491663Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:46.932682Z","title":"Multi-task learning in natural language processing: An overview","venue":null,"work_id":"f08b437b-7132-4f98-8e2e-c0c30b832ab7","year":2024},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:33.590021Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:ced008114a1c4e016690f1521aaa37e97dd5724c42baa0aa11c4d9258ee9f79e","observation_id":"07785fd8-a908-4724-ab18-37cc69900a8d","resolution":{"observed_at":"2026-08-07T12:37:47.123938Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:46.646661Z","title":"Adamv-moe: Adaptive multi-task vision mixture-of-experts","venue":null,"work_id":"c4ad215e-6952-4052-bfcd-4ccdbceac65e","year":2023},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:33.684717Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:e6847b05f1935c7f9175744da6f5a57a4bf0767106422caf5edbbfee7152f738","observation_id":"e94c4768-34cd-420f-9cd8-b748e4ffe8a5","resolution":{"observed_at":"2026-08-07T12:37:46.791804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:46.392244Z","title":"Fed- bone: Towards large-scale federated multi-task learning","venue":null,"work_id":"8fc33015-bff4-44d2-891d-37e5b32be24f","year":2024},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:33.765885Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:5387d0940d7ab1acd4051f71546f1f691dfa6966de1882ebafbfbbe1b4cc2e39","observation_id":"49ca02b5-ee12-4229-ad9e-ff8d8a903132","resolution":{"observed_at":"2026-08-07T12:37:46.519342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:45.987343Z","title":"Fair federated learning under domain skew with local consistency and domain diversity","venue":null,"work_id":"d1a1eb25-42c1-4819-bed2-0f8d66aa9cae","year":2024},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:33.840832Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:6d5cd51c24495826476a2c8b4b4ebcd325ebda56bda359b570551540d60893e5","observation_id":"be7b48e0-e151-4592-9bd4-184491f5c307","resolution":{"observed_at":"2026-08-07T12:37:46.129573Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:45.678797Z","title":"Federated learning for predicting clinical outcomes in patients with covid-19","venue":null,"work_id":"06e79de0-7366-4e19-9c6b-4f33ca9d22cb","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:33.941388Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:7d1507353cfae510c1dbce3da3a9a208982c43fb297afa99e246182d27089825","observation_id":"56271eb2-3158-4d91-961b-22909c324b19","resolution":{"observed_at":"2026-08-07T12:37:45.789516Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:34.017203Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:34.017203Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:1927616a4ef5c61db0406fc554a3c6c6e3c90f9726e60b06f01f95c14541642c","observation_id":"2666eea7-0eac-4e0a-a865-647b92146dd1","resolution":{"observed_at":"2026-08-07T12:37:34.017203Z","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":"2026-08-07T12:37:45.265274Z","title":"Multi-task self-supervised visual learning","venue":null,"work_id":"ef435b54-b1a9-42b9-a7fc-bb9927c81e80","year":2017},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:34.143119Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:8d21bfff0f4322035948acae72e0bb1b73eb4b6978dfd166a9e9e35eea68f591","observation_id":"4521f5b4-7630-4b4b-b96b-2c68d9671f90","resolution":{"observed_at":"2026-08-07T12:37:45.404274Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:45.114671Z","title":"Federated learning based on dynamic regularization","venue":null,"work_id":"3cb95e8b-117b-4f69-8017-a1b4b551d5c4","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:34.267874Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:e75cf613f61ee020b3cfdc56f16a2c5609df17ba4c578a7e5f2819ba3389dcbe","observation_id":"4ea9c416-cb1c-421e-a9ed-547b56584054","resolution":{"observed_at":"2026-08-07T12:37:45.156826Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:44.917098Z","title":"Spreadgnn: Decentralized multi-task federated learning for graph neural networks on molecular data","venue":null,"work_id":"dc6a4a55-9580-4886-b9dd-8c5e28e3d2e4","year":2022},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:34.338103Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:7c60dfab2291dfdcdf9fe2c97e9fcb4347631794bd89b2b54cf2aa4755e00974","observation_id":"28bbc9e7-a72b-4485-84ff-6bfe4525c479","resolution":{"observed_at":"2026-08-07T12:37:45.049730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:44.758222Z","title":"Delving deep into rectifiers: Surpassing human-level performance on imagenet classification","venue":null,"work_id":"80db1aa3-d77b-4fb7-bedf-9b2dfce4f9e8","year":2015},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:34.414210Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:abb18683b683b39c94544b6721f20476dadcf1f751407f67bc22309e6131cfde","observation_id":"094257e4-22a3-4e9d-b271-8d5e1febee6d","resolution":{"observed_at":"2026-08-07T12:37:44.830560Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:34.501388Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:34.501388Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:02c56b238dfe5170c817da42cd840b6a374ed4fa100e3f728ce80d4aa7ae2a05","observation_id":"77d389cf-2303-4b5f-abc6-ab1ccc0b0a76","resolution":{"observed_at":"2026-08-07T12:37:34.501388Z","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":"2026-08-07T12:37:44.584473Z","title":"Rethinking federated learning with domain shift: A prototype view","venue":null,"work_id":"dcbab2d2-a8c1-4943-b219-b5f7f783531f","year":2023},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:34.588773Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:5b608b95ce2927c8ce661d7faa705c1f342bc2d4c087c879a2c88c59d58e11c7","observation_id":"dbaa5707-abc6-4b31-8a92-ac7863e4f465","resolution":{"observed_at":"2026-08-07T12:37:44.650188Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:44.467037Z","title":"Federated learning for generalization, robustness, fairness: A survey and benchmark","venue":null,"work_id":"75455a81-4b6b-4887-b2cc-2c73b5ad90b9","year":2024},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:34.672896Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:c1922c7d814425c1fde5357f140c9e7bc5fa23c7dcfc127e127897b51ddd9cd0","observation_id":"5da8b4a7-f84b-4ae3-9abc-ece669e2f1e3","resolution":{"observed_at":"2026-08-07T12:37:44.512858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:44.269720Z","title":"Personalized cross-silo federated learning on non-iid data","venue":null,"work_id":"cce8b4ed-123e-4eca-ac63-357a9aa9b1bc","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:34.756880Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:dbf30e8f92cb8f4f48fefc1aca99156fe00ec59cca303f7c822c9df4627db55b","observation_id":"6231a771-3072-4d6c-80bd-cffa3e648b71","resolution":{"observed_at":"2026-08-07T12:37:44.351045Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:44.094477Z","title":"Personalized cross-silo federated learning on non-iid data","venue":null,"work_id":"b04a7211-f42b-4500-9d57-bf6e079f1979","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:34.859780Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:06abd0a0feba0193493ee9e8cba9360fc0fa04802ac38c80226b6f85d40dc945","observation_id":"fdf12747-4a6c-414b-a7b1-e16dd673d04c","resolution":{"observed_at":"2026-08-07T12:37:44.175389Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:43.933182Z","title":"Editing models with task arithmetic","venue":null,"work_id":"509d6f44-ccc2-4adf-802e-b6260fc39db9","year":2022},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:34.986070Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:4941c471c01591b4a82f1495c299b646c7d26deba021b2856eb8203a7d7dcee9","observation_id":"c586c0f5-0c7c-44eb-af1e-faa0e7abe5d7","resolution":{"observed_at":"2026-08-07T12:37:43.990174Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:43.798856Z","title":"Scaffold: Stochastic controlled averaging for federated learning","venue":null,"work_id":"174cd7c9-1943-487b-a599-d024710364c4","year":2020},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:35.079471Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:a0676c9432b05e16e6c7250347dd8fdf0021d4e3916d0432cad16e2c67bcc4b4","observation_id":"ebe500c0-b31e-4ac8-8131-90be2a62b6b5","resolution":{"observed_at":"2026-08-07T12:37:43.847503Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:43.622497Z","title":"Communication-efficient federated learning with accelerated client gradient","venue":null,"work_id":"ff14c5da-e129-4756-93a8-641d38ad51fc","year":2024},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:35.227718Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:295f655ee9a169a57a98d3b69c98317da2a082277921f386f9fbf912dd9e370f","observation_id":"cf85ad11-3245-4077-bf0f-193958de1de5","resolution":{"observed_at":"2026-08-07T12:37:43.693186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:43.424437Z","title":"Ubernet: Training a universal convolutional neural network for low-, mid-, and high-level vision using diverse datasets and limited memory","venue":null,"work_id":"784eff74-07d4-4da1-8de4-4f952263b790","year":2017},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:35.296797Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:6a2fc52a0e68e9ced25ce65c90165721abb395b44b935830f0c4f090e26fd730","observation_id":"a164bc5e-0c3e-4cb6-9a89-dd3ec24987f4","resolution":{"observed_at":"2026-08-07T12:37:43.495247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:43.184384Z","title":"Model-contrastive federated learning","venue":null,"work_id":"b0e68e7d-9070-414e-a682-ce0baaae542b","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:35.358568Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:0a70fdc851f0d190646b10357321ef90ae7b479e27034158d60e27534c6f8edd","observation_id":"d847766a-9c3f-477b-b65a-2ea9b4dfd73d","resolution":{"observed_at":"2026-08-07T12:37:43.280506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:43.037242Z","title":"Ditto: Fair and robust federated learning through personalization","venue":null,"work_id":"03e44afe-3e34-48f6-9b63-2f93bd5a63c6","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:35.462804Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:277aae84c4db6979cfd214c75dc27d9fc12c0d58785b6f0c4db470f3617565b5","observation_id":"f985315c-cb3e-47ff-9e0c-d02680306872","resolution":{"observed_at":"2026-08-07T12:37:43.101865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:42.861923Z","title":"Federated optimization in heterogeneous networks","venue":null,"work_id":"1b632a5c-1789-42d7-94e2-ca748c7050df","year":2020},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:35.538479Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:ec677fef09040e7a5663b64114e81eaeaefacef9a9bd7d707faef5cbdc222152","observation_id":"fabe2810-336f-4d7e-ae28-e548f5a3b773","resolution":{"observed_at":"2026-08-07T12:37:42.908994Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:42.667094Z","title":"Fedbn: Federated learning on non-iid features via local batch normalization","venue":null,"work_id":"d9dcd908-9501-4502-a3a2-362448fd4352","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:35.602149Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:16679ea343c32cf2596bcdf1ec84c91b373a9dab745fa8b54e23b2c6ae68f1df","observation_id":"ac51344d-c407-4d70-a847-af25c134170b","resolution":{"observed_at":"2026-08-07T12:37:42.741750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:35.677800Z","title":"Swin transformer: Hierarchical vision transformer using shifted windows","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:35.677800Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:fdb1abe58ab1eaeb8003dd0c00328309dea0d3bcb2fbc1f9fe53d84938e06f09","observation_id":"f227aa21-c395-4468-9d87-be48bb710e0d","resolution":{"observed_at":"2026-08-07T12:37:35.677800Z","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":"2026-08-07T12:37:42.399765Z","title":"Fully convolutional networks for semantic segmenta- tion","venue":null,"work_id":"29051c16-5435-45b7-90b8-15b6ef3599d4","year":2015},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:35.742069Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:f761b69885c6dc489eb92bd4123f6d36f7bb04d89b923bddb6637257b9628a23","observation_id":"c69849e4-415c-4840-90b7-4568e77929f6","resolution":{"observed_at":"2026-08-07T12:37:42.511693Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:42.145928Z","title":"Fedhca2: Towards hetero-client federated multi-task learning","venue":null,"work_id":"8312ccdc-1ad4-4a43-9f11-a6814ed7291c","year":2024},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:35.831644Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:c53282c34727de0252a60329ffc128280d10ed734189bb42cc26e021425bfd4a","observation_id":"4d686996-ba30-48e5-9645-35888ef8547f","resolution":{"observed_at":"2026-08-07T12:37:42.242859Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:41.962728Z","title":"Attentive single-tasking of multiple tasks","venue":null,"work_id":"55312871-5c74-4d69-9581-ac20e6766022","year":2019},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:35.920497Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:9dde84f07e6279d2d070e6e9e23dbc9cbca5fc3c920789727253685433c96528","observation_id":"8b59838a-a6ca-4a82-89c6-ea34d6322733","resolution":{"observed_at":"2026-08-07T12:37:42.050208Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:41.760382Z","title":"Federated multi-task learning under a mixture of distributions","venue":null,"work_id":"8647f43d-9e44-47a2-8ec9-747c729ec37b","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:35.994931Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:51a5e348c7e6523f32d10fb786a35ce11ebc2eedd21c605ca20731f178e74fbb","observation_id":"8876b941-fe31-4d9b-b5c2-9691816a8155","resolution":{"observed_at":"2026-08-07T12:37:41.849433Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:41.549116Z","title":"Communication-efficient learning of deep networks from decentralized data","venue":null,"work_id":"78014704-0d22-40aa-82cc-eccfcbacb7d0","year":2017},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:36.088156Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:e38416b826b01f4b0e26d2865da87cbb1fe5d3d17aaed4c4d4c88b52ab5b2852","observation_id":"6fd3d06b-fff1-40b5-9409-f4ad6b997785","resolution":{"observed_at":"2026-08-07T12:37:41.637436Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:41.390388Z","title":"Fedseg: Class-heterogeneous federated learning for semantic segmentation","venue":null,"work_id":"73d1e91a-fcb4-412c-80ef-b9ef97e0695e","year":2023},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:36.159347Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:a988e3a5d11c40709f5fad02c289c721ebd5ca326170d38637cde93d3850ac8b","observation_id":"492e1cc1-e079-4d0c-ab85-4ddda091ca12","resolution":{"observed_at":"2026-08-07T12:37:41.445093Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:41.255176Z","title":"Multi-task federated learning for personalised deep neural networks in edge computing","venue":null,"work_id":"ecafe69a-6701-4f4d-9dee-212c3b20c0ff","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:36.324636Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:dde4c30d5c53a1420fa2c95598d281a268e1cfce9a9428a5f60893429cdb1b3a","observation_id":"232cb117-ff20-46aa-bd23-5b1933e1b501","resolution":{"observed_at":"2026-08-07T12:37:41.296996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:41.106199Z","title":"The role of context for object detection and semantic segmentation in the wild","venue":null,"work_id":"8f4e1e8e-5fd8-4f56-a4cb-c129b1b293fa","year":2014},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:36.418384Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:d3aa650b3e03bb9c99fd0e1e9756b14b96810f60fb8e7e89152f0cd05c0c8a45","observation_id":"19c18a9b-f9ca-418c-a3a6-a927054308a7","resolution":{"observed_at":"2026-08-07T12:37:41.162012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:40.918522Z","title":"Federated split task- agnostic vision transformer for covid-19 cxr diagnosis","venue":null,"work_id":"affc6a23-a73f-483d-9ee3-eeee177b8b16","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:36.481921Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:efdc811855b44366bfafa9fc930d99acbc48babb9ac193c6a58c45c430866fa3","observation_id":"c10b944f-3696-4743-a666-291a530da28e","resolution":{"observed_at":"2026-08-07T12:37:41.000694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:40.723142Z","title":"Rethinking architecture design for tackling data heterogeneity in federated learning","venue":null,"work_id":"2e5796fa-6420-4a48-91d7-256cd6510405","year":2022},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:36.592981Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:f89ed9c82b6004b3e4fb2f3e99686532a73bf6c150f7044cf0c33fc76d95672b","observation_id":"abd5a816-26d9-44b1-96a7-b696e4e6a1ff","resolution":{"observed_at":"2026-08-07T12:37:40.821807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:40.571109Z","title":"Adaptive federated optimization","venue":null,"work_id":"464d90f6-db48-4481-a5b0-4f250a54f185","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:36.659909Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:257cdfcf1cbf034bb13b75715323810c7783d1c8947a331647f8f59f8d86f96a","observation_id":"34714667-0794-4dac-b4bc-1a2986010416","resolution":{"observed_at":"2026-08-07T12:37:40.617315Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:40.411000Z","title":"Indoor segmentation and support inference from rgbd images","venue":null,"work_id":"595925a0-6768-4e8c-8d8d-615b184db2c0","year":2012},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:36.738310Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:1800dccd1280f2dfb65e6a6bcd2f6c9d63c3e1c8d125a36d2a7eb150a9533f33","observation_id":"1ad6a3b2-6b21-4cf9-81c8-5454077e55f3","resolution":{"observed_at":"2026-08-07T12:37:40.464212Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:40.192827Z","title":"Federated multi-task learning","venue":null,"work_id":"4a31ade0-b7c8-4650-8e7d-4f4f9072aa29","year":2017},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:36.868662Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:9dcb6862532acfde41c95c748b15281539a0ba28eb8d7f497402a8b6b89f2ca4","observation_id":"418fdddc-35ef-41ef-ab19-8959fc4d2ca3","resolution":{"observed_at":"2026-08-07T12:37:40.274367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:40.027632Z","title":"Mti-net: Multi-scale task interaction networks for multi-task learning","venue":null,"work_id":"a17e7e7f-f67b-4572-a85d-e5eb5cc0acb8","year":2020},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:36.990921Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:ae2c4a9aae36d5d066fbf8a2a8538a04c3a7df9979b8ab44aa55bbcec0b684b6","observation_id":"19fbaded-65d7-4192-8bb5-dcda8d2bf681","resolution":{"observed_at":"2026-08-07T12:37:40.093972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:39.785241Z","title":"Tackling the objective incon- sistency problem in heterogeneous federated optimization","venue":null,"work_id":"32fd7005-de8b-4aaa-84e7-afef5931907b","year":2020},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:37.054374Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:1e4961054c057769109d4adb1915bfadb78c2ac8d5e817c2b68c9cff467d7a12","observation_id":"5b05e6e3-3db4-4349-b955-92de84e028e4","resolution":{"observed_at":"2026-08-07T12:37:39.926820Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:39.572476Z","title":"Pad-net: Multi-tasks guided prediction-and- distillation network for simultaneous depth estimation and scene parsing","venue":null,"work_id":"eadf805c-d6cc-43d6-a92a-974627b884e4","year":2018},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:37.138821Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:6bfead685bdaeb565d4df260508cef7571c754c160e001f3bf6d74d10e3ad17c","observation_id":"26929e0b-c0a4-426d-b429-0051b9e0a151","resolution":{"observed_at":"2026-08-07T12:37:39.673024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:37.233993Z","title":"Federated machine learning: Concept and applications","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:37.233993Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:1db9709ec9d200c81cc8de425a121562c16074c0405674cee3e7510e28860b3a","observation_id":"3b73e80e-ee70-4638-bcbc-a11bb7ea90c0","resolution":{"observed_at":"2026-08-07T12:37:37.233993Z","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":"2026-08-07T12:37:39.347846Z","title":"Heterogeneous federated learning: State-of-the-art and research challenges","venue":null,"work_id":"2c09a830-b3d1-4ab6-9b03-8581a94f4d3c","year":2023},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:37.337468Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:a145084a4e0ffed0edc786b4c974b1227f32ae2c0a25c4b2866bf0b7531dec83","observation_id":"857d2e8c-8df9-400d-9085-dfbe2f1c518f","resolution":{"observed_at":"2026-08-07T12:37:39.422858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:39.144515Z","title":"Unleashing the power of multi-task learning: A comprehensive survey spanning traditional, deep, and pretrained foundation model eras","venue":null,"work_id":"a6839397-d23a-4452-acf3-1fc459f1e04f","year":2024},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:37.512647Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:6abc0fea08bf9453cc355f831f701c8b0949b65b987783145e4967fe4e33c471","observation_id":"bd135dfc-d58f-481e-9d56-9025d40fe5e7","resolution":{"observed_at":"2026-08-07T12:37:39.252292Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:38.954137Z","title":"Gradient surgery for multi-task learning","venue":null,"work_id":"8615683c-655c-48aa-b3ab-c0c16298b306","year":2020},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:37.625271Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:654c9cb56a8fa4ab38010cbf17830988f0e8bfd26d7a16dfd6c0c0b29145954f","observation_id":"125981ef-bec2-4ec9-b34c-5c2756be6092","resolution":{"observed_at":"2026-08-07T12:37:39.008504Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:38.757038Z","title":"Achievement-based training progress balancing for multi-task learning","venue":null,"work_id":"701c9aa5-b7f1-43b8-abdc-6993cff619d3","year":2023},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:37.725615Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:08d9e1c9b4c1f3c60320b533929be42e0a96a8e6d912be0748f6f9c379eae6e4","observation_id":"71d51339-5453-4e41-b4d2-0b37523011a8","resolution":{"observed_at":"2026-08-07T12:37:38.847787Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:38.584927Z","title":"Federated learning for non-iid data via unified feature learning and optimization objective alignment","venue":null,"work_id":"6a662071-18c8-43cd-b3c3-047faf63c70e","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:37.828442Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:716349a7f608b1457cf3cb03140b9a01e9b10a1b8a2ef959b10d8aae3952050d","observation_id":"76379342-187f-4a00-b285-77918831aef9","resolution":{"observed_at":"2026-08-07T12:37:38.630949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:38.334472Z","title":"Federated domain generalization with generalization adjustment","venue":null,"work_id":"25ff9869-f122-48eb-8938-e0556cdae071","year":2023},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:37.917897Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:b62fb42a84eb7f5ee3b3475e3205cf0621a09fdf32850a3ed5228616e5d81e8f","observation_id":"67847e3f-7fec-4937-894c-a3d84fc780be","resolution":{"observed_at":"2026-08-07T12:37:38.454990Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T12:37:38.120941Z","title":"A survey on multi-task learning","venue":null,"work_id":"92c88b57-6814-46bd-a4b9-2f3a58d267e7","year":2021},"citing_paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T12:37:37.991885Z"},"links":{"citing_paper":"/paper/2505.24185"},"observation_digest":"sha256:f91cd8dbb53d85acf5e55d85ee4c49ff1d72732b7bb3de81aa397d88ed9e229c","observation_id":"b2d467f6-a688-4ccd-a170-a06638b6ea39","resolution":{"observed_at":"2026-08-07T12:37:38.226890Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.24185","last_updated":"2025-05-30T03:53:21Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T12:28:16.192607Z","submitted_at":"2025-05-30T03:53:21Z","title":"Towards Unified Modeling in Federated Multi-Task Learning via Subspace Decoupling"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":5,"verified_exact":0,"verified_fuzzy":48},"total_outbound_references":54},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2505.24185."}