{"as_of":"2026-08-22T04:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:817a38cb7b1108d0e10607e7f98e3935c1624cba41a043d29b78c7dcf0c6f961","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":"2026-08-16T00:43:24.478182Z","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":"2026-08-21T06:32:19.484+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/2505.02972/citation-record","integrity":"/paper/2505.02972/integrity","json":"/paper/2505.02972/citation-record.json","paper":"/paper/2505.02972"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T00:43:23.822283Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.822283Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:e6837a38e5c0f1f3747de236daae162e5774c2e3c36e506664e907884a9002c6","observation_id":"13a8c89b-efec-43fd-b8b2-dd8fd99ec6f9","resolution":{"observed_at":"2026-08-16T00:43:23.822283Z","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":"2026-08-16T00:43:26.907834Z","title":"(2008), Optimization algorithms on matrix manifolds\\/ , Princeton University Press","venue":null,"work_id":"3bb139a5-5c79-4520-883f-1ac5d5e98144","year":2008},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.870738Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:a69fe78fffc94d4d6a552c9b478b31ffadff29b235e27454429e77c4bba657c9","observation_id":"716de14d-d5d5-4830-b305-4675966d0c31","resolution":{"observed_at":"2026-08-16T00:43:26.911554Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.893315Z","title":"L., et al","venue":null,"work_id":"2f92a80c-a466-4574-99bd-8a6a614f7ddd","year":2013},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.876316Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:ce9ebe7a4ad9a12acfb85e55a27c300ec93065b4a2e0b6c6304bbbcebf9b1919","observation_id":"cad3a091-5d52-4b65-99c5-e03f9a367be0","resolution":{"observed_at":"2026-08-16T00:43:26.897782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.879598Z","title":"(2021), Predicting with proxies: Transfer learning in high dimension, Management Science\\/ , 67, 2964--2984","venue":null,"work_id":"c701e714-9e8f-4ae3-89ba-e781e88fbd2a","year":2021},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.881488Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:cbfef7c45d53881f38af688b0dc1b86b70a691dac7f1de775e81d5c354b7b9e9","observation_id":"1a375ba7-4999-4328-9b80-2b396e58c1ba","resolution":{"observed_at":"2026-08-16T00:43:26.884133Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.866141Z","title":"(2000), A model of inductive bias learning, Journal of artificial intelligence research\\/ , 12, 149--198","venue":null,"work_id":"24ebe142-b85c-4c7a-9dc8-b3366e4d2268","year":2000},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.886206Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:d441f290ae174b8aa32270786b5a9edc4ecfe91fdd08ea5c387f74e6e780648e","observation_id":"1e5d1660-d832-4d45-8466-3d0f1a2069fc","resolution":{"observed_at":"2026-08-16T00:43:26.870587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.853026Z","title":null,"venue":null,"work_id":"cdeeb5a4-a39f-423e-82bd-0de05dd02b10","year":2010},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.891116Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:e00102a76238b5cb75a7b14f7b3db59a06a2c6fa6afcada7e1a041c183f963c8","observation_id":"cf568c04-54ea-41ef-ac4a-ea915c8d724c","resolution":{"observed_at":"2026-08-16T00:43:26.857382Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.03158","last_updated":"2020-10-08T07:54:24Z","snapshot_observed_at":"2026-08-21T11:03:29.304329Z","submitted_at":"2020-10-07T04:54:03Z","title":"Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer","version":2},"cited_work":{"arxiv_id":"2010.03158","doi":null,"metadata_source":"pith","pith_arxiv_id":"2010.03158","snapshot_observed_at":"2026-08-16T00:43:24.881125Z","title":"Multilingual Knowledge Graph Completion via Ensemble Knowledge Transfer","venue":"cs.CL","work_id":"38dddbb6-e2c8-4fe3-b36c-7f91664ff077","year":2020},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.895893Z"},"links":{"cited_paper":"/paper/2010.03158","citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:a282686b1e6443cc6211beefa4a2e722dc96ac312be38cb4526b5e3f3a90334c","observation_id":"b99baff9-d50a-46ba-9fa2-e149a16b8bf7","resolution":{"observed_at":"2026-08-16T00:43:24.886122Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.690723Z","title":null,"venue":null,"work_id":"7043305e-786f-46ce-b571-a3fc86f2f9ef","year":2021},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.901849Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:8c2afc1967e4b0372cd6323118adc47e1f9086edfeb0ab17462edae1da39ebf8","observation_id":"44ea402a-5733-4599-b22d-eb3832d4514c","resolution":{"observed_at":"2026-08-16T00:43:26.782861Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.596918Z","title":"(2021), Exploiting shared representations for personalized federated learning, in International conference on machine learning\\/ , PMLR","venue":null,"work_id":"32148bdc-392c-42fc-9d70-a5a133473786","year":2021},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.906336Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:4477d816b960909b35a670d0b3db3c96317ad1ac6a5602c958d0eb62d446ccfa","observation_id":"5ff563fd-b8cc-466e-8bfe-6f66a4e005d8","resolution":{"observed_at":"2026-08-16T00:43:26.642317Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.569873Z","title":"(2008), Learning from Multiple Sources","venue":null,"work_id":"f90134d7-23b2-44cc-931a-88125d2d2154","year":2008},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.910485Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:13c0b03bec72502b4a4bd2e67df0a4b3a3aa63b6a691bc344ded2c1a190e3c6e","observation_id":"f5b3cd73-e337-4d7c-b7d3-bc707c50a015","resolution":{"observed_at":"2026-08-16T00:43:26.575582Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.543264Z","title":"(2020), The advantage of conditional meta-learning for biased regularization and fine tuning, Advances in Neural Information Processing Systems\\/ , 33, 964--974","venue":null,"work_id":"db4d4d52-3527-4c05-8427-0f539c6be0c2","year":2020},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.914902Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:c55603413b97e5b82ae917cbeb01bf3489624910016e7774e7f1b9029a39321b","observation_id":"8d78efcf-edd6-4e67-8468-a0dda085ce47","resolution":{"observed_at":"2026-08-16T00:43:26.549455Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.502156Z","title":"(2022), Learning tensor representations for meta-learning, in International Conference on Artificial Intelligence and Statistics\\/ , PMLR","venue":null,"work_id":"44ff18aa-8565-4312-9741-95e51f87de3c","year":2022},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.918790Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:d67cca1d9ab8510f6bc2991b95bd051f2034b1f8abdae5a111942bea8886b0b2","observation_id":"5a2a65d1-b994-4b07-ac8d-df66d2b821b3","resolution":{"observed_at":"2026-08-16T00:43:26.516847Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.477438Z","title":"(2014), Decaf: A deep convolutional activation feature for generic visual recognition, in International conference on machine learning\\/ , PMLR","venue":null,"work_id":"0221bc2f-fa56-47a4-9296-f0502f065cf0","year":2014},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.923319Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:1f54fe12f05d529ce59947ebb020ecb7a85fddb229c56dc7c43a23bd8fef0762","observation_id":"afebe91e-4e87-4f95-9b97-608c1cff40f2","resolution":{"observed_at":"2026-08-16T00:43:26.482973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.09434","last_updated":"2021-03-30T04:06:04Z","snapshot_observed_at":"2026-08-20T22:33:41.299002Z","submitted_at":"2020-02-21T17:30:00Z","title":"Few-Shot Learning via Learning the Representation, Provably","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2002.09434","snapshot_observed_at":"2026-08-16T00:43:23.927140Z","title":"S., Hu, W., Kakade, S","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.927140Z"},"links":{"cited_paper":"/paper/2002.09434","citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:bde5504061dd7832b83df2c3c01ec40acfbf32348756442750e63e37b932f926","observation_id":"7f132ba7-da4a-403e-a3e6-c694649c6af6","resolution":{"observed_at":"2026-08-16T00:43:23.927140Z","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":"2026-08-16T00:43:26.457221Z","title":"and Wang, K","venue":null,"work_id":"966c0164-d4be-45e3-9e27-3bde0484cafa","year":2023},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.932404Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:4f180a3debb19b9c23bb6e005b4743d73306d8455cc3beea645a552feccd231f","observation_id":"97371733-0b5d-42f3-a10c-bca26bb974e5","resolution":{"observed_at":"2026-08-16T00:43:26.461603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.417625Z","title":"C., Feldman, V., Hu, L., and Talwar, K","venue":null,"work_id":"51d4e63d-4c66-4789-831d-ef6ff22a0f89","year":2022},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.936628Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:df1114266858bdbdf1e5fabb17de64e36c2f0f1e4307ec1a68a35923504039af","observation_id":"9939a250-91f4-4a05-9f21-d414f7bfd93c","resolution":{"observed_at":"2026-08-16T00:43:26.427742Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.402072Z","title":"(2019), Scaling and benchmarking self-supervised visual representation learning, in Proceedings of the ieee/cvf International Conference on computer vision\\/","venue":null,"work_id":"8c07116f-5fe9-41bf-b70f-faf5130ff520","year":2019},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.940414Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:d3a0620f63fdc81d23b5d9018ee7eb3d836ce7d6324be146c63f03e54723c5b0","observation_id":"0f3f57c1-f3ed-4c31-ac55-1a34dbc7fae4","resolution":{"observed_at":"2026-08-16T00:43:26.406534Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2210.12759","last_updated":"2023-11-10T15:41:46Z","snapshot_observed_at":"2026-08-16T16:21:51.931418Z","submitted_at":"2022-10-23T15:57:59Z","title":"Robust angle-based transfer learning in high dimensions","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.12759","snapshot_observed_at":"2026-08-16T00:43:23.976781Z","title":"(2022), Robust angle-based transfer learning in high dimensions, arXiv preprint arXiv:2210.12759\\/","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:23.976781Z"},"links":{"cited_paper":"/paper/2210.12759","citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:0328ce249cd2b0f646140feaf10643c9e22dc4a8beb1d3603481caa9940c93ab","observation_id":"b79fdecf-812e-4aea-9447-ab7473363f58","resolution":{"observed_at":"2026-08-16T00:43:23.976781Z","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":"2026-08-16T00:43:26.302989Z","title":"H., and Duan, R","venue":null,"work_id":"84c33471-8974-4dc8-8b05-fd123da73784","year":2023},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.084020Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:4c2c24f296a7a8c64700692764b6ed903cedf7b574fb28a9ccaf64acfd4b915d","observation_id":"49485216-3f63-4a0b-b8c2-a7cc6c4e1b7e","resolution":{"observed_at":"2026-08-16T00:43:26.392951Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1703.02949","last_updated":"2017-03-08T18:09:32Z","snapshot_observed_at":"2026-08-14T21:12:49.992908Z","submitted_at":"2017-03-08T18:09:32Z","title":"Learning Invariant Feature Spaces to Transfer Skills with Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1703.02949","snapshot_observed_at":"2026-08-16T00:43:24.137177Z","title":"(2017), Learning invariant feature spaces to transfer skills with reinforcement learning, arXiv preprint arXiv:1703.02949\\/","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.137177Z"},"links":{"cited_paper":"/paper/1703.02949","citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:47a405caa60d50a4a09e671be185bfc04ce8666eb6868e53adc1a58172805613","observation_id":"e69c0ddb-fe3d-491e-ab3b-e80d73b279a5","resolution":{"observed_at":"2026-08-16T00:43:24.137177Z","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":"2026-08-16T00:43:26.162585Z","title":"(2022), Multi-task manifold learning for small sample size datasets, Neurocomputing\\/ , 473, 138--157","venue":null,"work_id":"f9c4286d-3d02-43ac-9e4f-4e0ed77b5b90","year":2022},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.142326Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:fb6bfa218a7c57143608dd50c3dc6e4df64c2bc9e23473e2f8f77cdfc3481e48","observation_id":"f0e46423-0d53-486c-a528-b4d6504cf29b","resolution":{"observed_at":"2026-08-16T00:43:26.222326Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.105122Z","title":"(2010), A dirty model for multi-task learning, Advances in neural information processing systems\\/ , 23","venue":null,"work_id":"9643e07e-eb33-4bd2-9110-acaf0a22e857","year":2010},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.146541Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:ebe68f79bef7e42efe6922362ab0415d659282f401c97555c375b0910b230099","observation_id":"195bc78b-8feb-4d9d-89b6-a460b588cc44","resolution":{"observed_at":"2026-08-16T00:43:26.109624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.091385Z","title":null,"venue":null,"work_id":"951563b8-6394-4547-980f-1790c888b738","year":2015},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.150212Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:0dfe90f4d5f20438d6b8c0304766da5be3449c4b415a27c777b68abb7574d2e7","observation_id":"6cccfd9e-a71d-4a1d-b16b-23d4de70fe41","resolution":{"observed_at":"2026-08-16T00:43:26.095512Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.078059Z","title":null,"venue":null,"work_id":"8867f06c-6715-493e-9949-debef0ef779d","year":2015},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.155069Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:3a3c669c530ba031fd2bf2f3eacfca8e1c3cd671c6f2de17a709400f865f946c","observation_id":"3f3d246a-186c-4263-ac58-99358bdcdba4","resolution":{"observed_at":"2026-08-16T00:43:26.082231Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.064082Z","title":"(2020), On the sample complexity of adversarial multi-source pac learning, in International Conference on Machine Learning\\/ , PMLR","venue":null,"work_id":"279a9d22-bdbe-426d-888f-569518dfee1b","year":2020},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.159159Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:a5c20e2a327bddd5bb4587975dc92bac79c7e78128cb8d8224e33224f06b0319","observation_id":"fa41947d-ae78-42f3-8fb0-02f3e747a1e1","resolution":{"observed_at":"2026-08-16T00:43:26.067957Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.050556Z","title":"and Orabona, F","venue":null,"work_id":"80163e9f-ab3e-4f39-a4f1-6a24b9f398a4","year":2013},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.163389Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:692d30107bf83f9d8e077058e128e509b00e16df640997887985616b10be5d6d","observation_id":"0ec92a89-0ad8-448a-a82c-398e0891c86d","resolution":{"observed_at":"2026-08-16T00:43:26.054901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.037634Z","title":null,"venue":null,"work_id":"9b210046-8323-44b8-8540-2b0cca2b3e1b","year":2017},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.167728Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:3dd4ba869d47c0a42e87accf5aa46cccc58471b51302dd38fc2e76b45f5dfd1f","observation_id":"94e0446f-35d7-413a-a029-af2d8320f738","resolution":{"observed_at":"2026-08-16T00:43:26.041767Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.021253Z","title":"(2023), Targeting underrepresented populations in precision medicine: A federated transfer learning approach, The Annals of Applied Statistics\\/ , 17, 2970--2992","venue":null,"work_id":"bd2f4876-e31f-4346-9ada-e5b3d989478e","year":2023},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.171972Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:ec88c59e8370d6b1d9342d5a28e6b1dee3e0ba17514ee5ed5a49ba17b8055897","observation_id":"7346057f-2fb3-43d6-90be-97a3913fcf52","resolution":{"observed_at":"2026-08-16T00:43:26.025858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:26.008212Z","title":"T., and Li, H","venue":null,"work_id":"96aec47f-1627-44a2-896a-d1b07c1ef0d2","year":2022},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.176613Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:b5a685a1adc8257d89c9c52fd931f47f6725adbfdbe08b381fb8c36ca2450ea7","observation_id":"3cb3980b-2770-4542-b0bf-5efdc03fdae6","resolution":{"observed_at":"2026-08-16T00:43:26.012547Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2206.04277","last_updated":"2025-06-09T15:50:41Z","snapshot_observed_at":"2026-08-20T09:51:26.855118Z","submitted_at":"2022-06-09T04:50:16Z","title":"On Hypothesis Transfer Learning of Functional Linear Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2206.04277","snapshot_observed_at":"2026-08-16T00:43:24.180269Z","title":"and Reimherr, M","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.180269Z"},"links":{"cited_paper":"/paper/2206.04277","citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:87b8170bddfd8b7f95aed8d2ea6ee66204f354403b2a6abea2136a8539eb8e16","observation_id":"0b3befa7-ea66-4ac4-81da-fbbdee5aff6d","resolution":{"observed_at":"2026-08-16T00:43:24.180269Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"0903.1468","last_updated":"2009-03-09T00:54:46Z","snapshot_observed_at":"2026-08-15T05:53:23.577346Z","submitted_at":"2009-03-09T00:54:46Z","title":"Taking Advantage of Sparsity in Multi-Task Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"0903.1468","snapshot_observed_at":"2026-08-16T00:43:24.185010Z","title":"B., and Van De Geer, S","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.185010Z"},"links":{"cited_paper":"/paper/0903.1468","citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:ca53dd61c725a03c90b4fae089d3a9c0d15b654edd12f02725e164f1f6cd856e","observation_id":"7e12fd77-236f-4f92-bb39-82b31232c137","resolution":{"observed_at":"2026-08-16T00:43:24.185010Z","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":"2026-08-16T00:43:25.994227Z","title":null,"venue":null,"work_id":"eccd7f24-0810-4522-b83c-0a0c69c3300a","year":2012},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.189598Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:8c6e7160442a663ae466e0453013dca83abf5d9bd1d27daee80a24adc99c6ba8","observation_id":"4ccaefc0-2658-4e47-a966-def0747a4d91","resolution":{"observed_at":"2026-08-16T00:43:25.998460Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:25.864239Z","title":"(2016), The benefit of multitask representation learning, Journal of Machine Learning Research\\/ , 17, 1--32","venue":null,"work_id":"f3802e35-d0e5-4507-adca-ef33adb2294e","year":2016},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.193698Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:e629856f4c8074e73f6156c5c5d99e376ec6455767cf425a91d786c3d93b2ff0","observation_id":"e9e862a8-acea-4637-a893-f1e21165d310","resolution":{"observed_at":"2026-08-16T00:43:25.984205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:25.635003Z","title":"(2019), Pytorch: An imperative style, high-performance deep learning library, Advances in neural information processing systems\\/ , 32","venue":null,"work_id":"72b2d1e0-a02d-4a2c-b583-3d6c6be2a3b9","year":2019},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.198147Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:014bd88cefe221dc0a63f34b2fabd8df69aaea3039311624cf4e2ad6bcc32a16","observation_id":"b34a672f-ef8d-48e8-8b9b-d5d2626cecb6","resolution":{"observed_at":"2026-08-16T00:43:25.793039Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:25.506365Z","title":"(2018), Do Outliers Ruin Collaboration? in International Conference on Machine Learning\\/ , PMLR","venue":null,"work_id":"0dcedf05-59fe-496b-a1e8-4ce35d9c000e","year":2018},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.202280Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:6d5c3cdd36347744cad116e768c251f99824bb2325bcd4a1fa86b8cc6bb0cce3","observation_id":"29934f59-e947-454a-9025-d5010a76e29c","resolution":{"observed_at":"2026-08-16T00:43:25.541557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1711.08113","last_updated":"2017-11-22T02:39:21Z","snapshot_observed_at":"2026-08-14T20:11:15.159046Z","submitted_at":"2017-11-22T02:39:21Z","title":"Learning Discrete Distributions from Untrusted Batches","version":1},"cited_work":{"arxiv_id":"1711.08113","doi":null,"metadata_source":"pith","pith_arxiv_id":"1711.08113","snapshot_observed_at":"2026-08-16T00:43:24.790510Z","title":"Learning Discrete Distributions from Untrusted Batches","venue":"cs.LG","work_id":"7223a7da-ad82-4590-b15d-9a192f5a4539","year":2017},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.206336Z"},"links":{"cited_paper":"/paper/1711.08113","citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:4c7b829aeb84300da007b86d356d99d8ffb6be812125c6beb0e81d5deccc05bf","observation_id":"23e538a1-6fbf-4209-bfef-a15b6c1c198e","resolution":{"observed_at":"2026-08-16T00:43:24.795010Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:25.493815Z","title":"(2019), Transfusion: Understanding transfer learning for medical imaging, Advances in neural information processing systems\\/ , 32","venue":null,"work_id":"029f7a0a-914e-42fe-8381-42e84306f408","year":2019},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.253972Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:b960018c6b1a23dffcf9ac8c2b9edfb845f0a84b66106ea7e010fc2045d77691","observation_id":"d12e86c4-aa07-44f7-b8b7-f4ec97083e52","resolution":{"observed_at":"2026-08-16T00:43:25.497833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:25.480466Z","title":"(2022), Transfer learning via representation learning, in Federated and Transfer Learning\\/ , Springer, 233--257","venue":null,"work_id":"91b2805d-7ef4-4b96-9b99-7901221056d7","year":2022},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.330176Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:4e192470b00b364221601b9f4a8d65774622d1666c1dfde0f9a175a73baa8ed7","observation_id":"5cb63af2-c004-469c-8a44-866fb15d4546","resolution":{"observed_at":"2026-08-16T00:43:25.484680Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:25.468071Z","title":null,"venue":null,"work_id":"d5c06bc8-86e1-4fcb-8ce0-d926586babed","year":2001},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.407288Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:1dc0f9b17645c1f17a49f33f60a1c635e3c994cafab5f99b4c09b45a77787b0d","observation_id":"bb805b31-eabb-4d39-a953-8aa7b42a5587","resolution":{"observed_at":"2026-08-16T00:43:25.472228Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:25.455715Z","title":"K., Jain, P., Netrapalli, P., and Oh, S","venue":null,"work_id":"0c589d42-06c9-46f1-8033-28b5fc0ffadc","year":2021},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.412329Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:f25404359ea78f90d2109b1cfb42a19dd2f9908bbe429a12e6ca5dce12a9596e","observation_id":"b7a20eb2-e83a-40e8-8761-8f6afe2eeb41","resolution":{"observed_at":"2026-08-16T00:43:25.459775Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:25.441875Z","title":"and Feng, Y","venue":null,"work_id":"4fdc5aa6-89de-48b8-962e-7aa6a1e51e53","year":2023},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.416398Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:e5077b4033d8fb5c63920183bd035e77b372d527322d6c06950af47de07cbb15","observation_id":"8f584f67-5c4d-4784-b804-974c47b1c4de","resolution":{"observed_at":"2026-08-16T00:43:25.446473Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2303.17765","last_updated":"2025-07-06T20:36:55Z","snapshot_observed_at":"2026-08-16T15:43:54.615265Z","submitted_at":"2023-03-31T01:56:13Z","title":"Learning from Similar Linear Representations: Adaptivity, Minimaxity, and Robustness","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2303.17765","snapshot_observed_at":"2026-08-16T00:43:24.420834Z","title":"(2023), Learning from similar linear representations: Adaptivity, minimaxity, and robustness, arXiv preprint arXiv:2303.17765\\/","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.420834Z"},"links":{"cited_paper":"/paper/2303.17765","citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:374c5ed61aa3bf949134a935fb1658fb2e6c044549473bb0596e0338a6378e08","observation_id":"de950419-6017-4188-8ef9-951a68030e86","resolution":{"observed_at":"2026-08-16T00:43:24.420834Z","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":"2026-08-16T00:43:24.425783Z","title":"(2022), Unsupervised multi-task and transfer learning on gaussian mixture models, arXiv preprint arXiv:2209.15224\\/","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.425783Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:692a42522313f13558ebbcfd22e7822397c7047602d0b828a1c10b821d1c34b0","observation_id":"613161b7-9be9-4128-962e-6ec4d8e4fd5d","resolution":{"observed_at":"2026-08-16T00:43:24.425783Z","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":"2026-08-16T00:43:25.427854Z","title":"(2021), Provable meta-learning of linear representations, in International Conference on Machine Learning\\/ , PMLR","venue":null,"work_id":"011a9e91-16a3-40ef-b46f-ee672771c351","year":2021},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.430894Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:4012e48c244ceab6af1c506cd4fc7128eb4bd5a93c26ad75f36bc6a8f1d9e693","observation_id":"5f18f902-003d-4d94-9204-1bb880b1e54a","resolution":{"observed_at":"2026-08-16T00:43:25.432715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:25.334734Z","title":"(2020), On the theory of transfer learning: The importance of task diversity, Advances in neural information processing systems\\/ , 33, 7852--7862","venue":null,"work_id":"cfa72346-2a6f-4b6d-be29-25fd97aadcda","year":2020},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.437122Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:b715df6e69885381cc254f7b3f6101c22710a6e12ebe0f95490cae079e5539e6","observation_id":"647c552f-57d3-4956-9213-aeacc8749754","resolution":{"observed_at":"2026-08-16T00:43:25.374560Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:25.166730Z","title":null,"venue":null,"work_id":"7c9a7a8c-2c46-4b73-853a-57fdfa1f9eac","year":2019},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.441566Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:42a42e0ff77622935bd8771c08da7d4fb72d76384ccd44cd0e86d13edfe3eff8","observation_id":"87b30182-a6df-41ac-9b59-8cf7393ae512","resolution":{"observed_at":"2026-08-16T00:43:25.235186Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1812.10860","last_updated":"2019-07-22T22:38:54Z","snapshot_observed_at":"2026-08-21T11:03:12.116391Z","submitted_at":"2018-12-28T01:21:17Z","title":"Can You Tell Me How to Get Past Sesame Street? Sentence-Level Pretraining Beyond Language Modeling","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.10860","snapshot_observed_at":"2026-08-16T00:43:24.445550Z","title":"T., Patel, R., Kim, N., Tenney, I., Huang, Y., Yu, K., et al","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.445550Z"},"links":{"cited_paper":"/paper/1812.10860","citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:6ee94c8f4a4901466a2dcb08f1d3455b5222d4b9b889229f5d57e2a425e53c40","observation_id":"7a61d678-20dc-478b-8f99-524cff820ccc","resolution":{"observed_at":"2026-08-16T00:43:24.445550Z","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":"2026-08-16T00:43:25.109926Z","title":"M., Wilson, T","venue":null,"work_id":"18b6aaca-fa8f-4eb6-9491-5c04340781a3","year":2019},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.450283Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:18b2dc4525744406d14a1e524b03e12b4158ab8c2b073bb042a58e6e40c6d75a","observation_id":"008f8fe8-2e23-4aa1-a835-60f94ab11a2d","resolution":{"observed_at":"2026-08-16T00:43:25.114484Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.14233","last_updated":"2024-07-28T04:42:39Z","snapshot_observed_at":"2026-08-16T17:31:33.925729Z","submitted_at":"2021-12-28T17:37:08Z","title":"Multitask Learning and Bandits via Robust Statistics","version":5},"cited_work":{"arxiv_id":"2112.14233","doi":null,"metadata_source":"pith","pith_arxiv_id":"2112.14233","snapshot_observed_at":"2026-08-16T00:43:24.669840Z","title":"Multitask Learning and Bandits via Robust Statistics","venue":"stat.ML","work_id":"2e245c43-05b1-48fc-927d-1752d767b95a","year":2021},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.454633Z"},"links":{"cited_paper":"/paper/2112.14233","citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:883468cfd1722adb92a88acf0acc59f0f89d68625f6a7bc6b752e7bc2b3bd017","observation_id":"bd3e5a34-36ad-428b-9c04-1a587678eddf","resolution":{"observed_at":"2026-08-16T00:43:24.675930Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:25.094511Z","title":"and Yang, Q","venue":null,"work_id":"20fb1d7a-38c5-49fd-9c26-b080c11a6765","year":2018},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.459913Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:647e624fd950c2e03c10b7ecdbf75955baf128b850e8b0f30ccbd9fbfe3455dc","observation_id":"5c723c4d-c837-4265-9d8e-a034844b771f","resolution":{"observed_at":"2026-08-16T00:43:25.099597Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:25.080375Z","title":null,"venue":null,"work_id":"3fce4c26-7020-43d0-acc6-c9d81776fa32","year":2021},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.463728Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:422ec213051ef10fbea9a831d2813bfbd4a2d437ab17c8651d2195a30e04f3bc","observation_id":"5b532b74-699c-45ee-afb4-448c2badf66d","resolution":{"observed_at":"2026-08-16T00:43:25.084673Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2309.15032","last_updated":"2025-07-01T15:14:09Z","snapshot_observed_at":"2026-08-21T11:08:45.308894Z","submitted_at":"2023-09-26T16:01:54Z","title":"SOFARI: High-Dimensional Manifold-Based Inference","version":2},"cited_work":{"arxiv_id":"2309.15032","doi":null,"metadata_source":"pith","pith_arxiv_id":"2309.15032","snapshot_observed_at":"2026-08-16T00:43:24.615226Z","title":"SOFARI: High-Dimensional Manifold-Based Inference","venue":"stat.ME","work_id":"8296393f-d1b4-4153-b21e-1513060b93d9","year":2023},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.468585Z"},"links":{"cited_paper":"/paper/2309.15032","citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:81936e8cbd6ee6cf5bb72bb59d33fd9b9ea4e6a25fe63367ea5905d1972361fc","observation_id":"ccf76da2-d004-4646-88c6-ab434b496893","resolution":{"observed_at":"2026-08-16T00:43:24.655932Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2105.10360","last_updated":"2021-10-09T18:21:29Z","snapshot_observed_at":"2026-08-21T11:08:40.169835Z","submitted_at":"2021-05-21T13:55:30Z","title":"Multi-source Learning via Completion of Block-wise Overlapping Noisy Matrices","version":3},"cited_work":{"arxiv_id":"2105.10360","doi":null,"metadata_source":"pith","pith_arxiv_id":"2105.10360","snapshot_observed_at":"2026-08-16T00:43:24.513217Z","title":"Multi-source Learning via Completion of Block-wise Overlapping Noisy Matrices","venue":"stat.ML","work_id":"5895a8d9-a3e7-42da-bc1a-c75cf5374329","year":2021},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.472977Z"},"links":{"cited_paper":"/paper/2105.10360","citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:c9a85a15c420b644c65fef8f7c3210c91c4b22ce864245ae7cbefdde0324f8ce","observation_id":"c8c5203d-8ca9-43e2-b236-da0e549d6f0a","resolution":{"observed_at":"2026-08-16T00:43:24.560639Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-16T00:43:24.896156Z","title":"(2024), Doubly robust augmented model accuracy transfer inference with high dimensional features, Journal of the American Statistical Association\\/ , 1--26","venue":null,"work_id":"708b7b77-d5b3-4397-bc8f-ca4889d2584e","year":2024},"citing_paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-16T00:43:24.478182Z"},"links":{"citing_paper":"/paper/2505.02972"},"observation_digest":"sha256:859a6a9acfc996156d81080d975d800be8a0e7c9dd5709c601d8a484bcc6ca64","observation_id":"dba8f54e-ee9f-4b06-91b5-f66d4adfdc21","resolution":{"observed_at":"2026-08-16T00:43:24.989381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.02972","last_updated":"2025-05-05T18:56:16Z","latest_version":1,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-19T04:09:27.351786Z","submitted_at":"2025-05-05T18:56:16Z","title":"GeoERM: Geometry-Aware Multi-Task Representation Learning on Riemannian Manifolds"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":5,"verified_fuzzy":31},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2505.02972."}