{"as_of":"2026-08-19T13:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c918f514f5e4e872efa84563a968a96cc4258c7f3154b105fb91c757fdb29937","coverage":[{"denominator":41,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":41,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T04:38:28.905504Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-19T06:32:44.657259+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T10:33:32.263320Z","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":[{"citation":{"cited_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.10616","snapshot_observed_at":"2026-08-01T10:33:32.263320Z","title":"arXiv preprint arXiv:2506.10616 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.20239","last_updated":"2026-07-22T14:59:09Z","snapshot_observed_at":"2026-08-14T10:12:09.996815Z","submitted_at":"2026-07-22T14:59:09Z","title":"Adaptive Bayesian Online Learning via Expert Aggregation","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-01T10:33:32.263320Z"},"links":{"cited_paper":"/paper/2506.10616","citing_paper":"/paper/2607.20239"},"observation_digest":"sha256:af329cf6b1521cc8adc3b022c2a7e523765a7de68c58208615d950e74cdd10de","observation_id":"5ecb1a17-8c15-484e-a5ff-5513462ee330","resolution":{"observed_at":"2026-08-01T10:33:32.263320Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2506.10616/citation-record","integrity":"/paper/2506.10616/integrity","json":"/paper/2506.10616/citation-record.json","paper":"/paper/2506.10616"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T04:38:23.854751Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:23.854751Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:19702c94e9b0bed0155bc5cc2a97b0c60f1c0960508b2b7cb849298d608300fc","observation_id":"5a97a4ac-781b-4a65-8971-53720ea5c8b3","resolution":{"observed_at":"2026-08-07T04:38:23.854751Z","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":"2026-08-07T04:38:39.603742Z","title":"M., Chernov, A","venue":null,"work_id":"94bd17e2-8770-4734-99d5-2c357329bb8f","year":2016},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:23.917687Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:e73d0d9b86d6120c4af80255b621fcf9b6bb1a5a7b9ad1c2da59efcf0df9dc3a","observation_id":"fc93fa47-14b6-4003-845d-b4ba9483ddc9","resolution":{"observed_at":"2026-08-07T04:38:39.774385Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:39.304389Z","title":"and Wang, Y.-X","venue":null,"work_id":"3422e29f-ddb6-4a44-95f5-824a529f867e","year":2021},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:24.033426Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:c064d256d89045388764fd25e123ca08ada25303e78286d59c59776e0f11e531","observation_id":"3fbb0016-dfef-4c15-83c3-a77d0b6e56f0","resolution":{"observed_at":"2026-08-07T04:38:39.445476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:39.031130Z","title":"and Wang, Y.-X","venue":null,"work_id":"59af0623-25aa-4c49-bc4b-a6e1d84d5c14","year":2022},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:24.164883Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:2a54186e6f3a37b3a9d61ade9f69dec1aa8d2e55725d0cd633a3045224056613","observation_id":"541ad762-aa37-42df-bb23-add149037a2c","resolution":{"observed_at":"2026-08-07T04:38:39.171617Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:38.797647Z","title":"and Wang, Y.-X","venue":null,"work_id":"510450c1-2d17-41be-9ff4-086816a1ed4c","year":2022},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:24.349201Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:d7962d3f3b70814d80b3c8acb84633760b8b44e56f79c9b4bafdbf8ff93f8e73","observation_id":"b164c2d1-936b-4a0b-83b5-313b9502338b","resolution":{"observed_at":"2026-08-07T04:38:38.892332Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:38.585784Z","title":"Non-stationary contextual pricing with safety constraints","venue":null,"work_id":"995abb2a-11ec-4c40-8640-1159db962fe3","year":2023},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:24.483062Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:010f90e9e0b8d70938353a1f0bd64a339db1b7a181765f4172c7f91cca9255a7","observation_id":"f9dc0e34-4b4d-4121-8ef6-3dec21b5b462","resolution":{"observed_at":"2026-08-07T04:38:38.673253Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:38.294207Z","title":null,"venue":null,"work_id":"4c38370f-0adf-46e8-b7f2-dde3b3335763","year":2015},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:24.574775Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:fbd53ea5d462b1df2ab3cfe5f24462fe8de43905596d0298aed3e8f3b6eea611","observation_id":"c00cec0d-8dba-417f-920f-b31c226eacdd","resolution":{"observed_at":"2026-08-07T04:38:38.432609Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:38.036590Z","title":null,"venue":null,"work_id":"3e4a33f0-8c0a-42aa-9d19-41ce83d33192","year":2021},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:24.756734Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:1dacc86c20e2238010f66feac268a665e5d4e10d87d8e5852d66ab45f5484a1f","observation_id":"901f6fa4-72dc-4d71-bf6b-3197977801d0","resolution":{"observed_at":"2026-08-07T04:38:38.178930Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:37.823034Z","title":"and Lugosi, G","venue":null,"work_id":"96eb35b8-4936-4939-8374-344b879d5355","year":2006},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:24.859582Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:3bf6543f615c722f2223632b6bc07d91a9c983e7fbe2195deb50776d806f1fd7","observation_id":"28ac2170-f0fa-4aee-937a-b8b72072963a","resolution":{"observed_at":"2026-08-07T04:38:37.923624Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1202.3323","last_updated":"2012-09-27T19:39:42Z","snapshot_observed_at":"2026-08-15T04:19:11.976297Z","submitted_at":"2012-02-15T14:39:42Z","title":"Mirror Descent Meets Fixed Share (and feels no regret)","version":2},"cited_work":{"arxiv_id":"1202.3323","doi":null,"metadata_source":"pith","pith_arxiv_id":"1202.3323","snapshot_observed_at":"2026-08-07T04:38:29.045121Z","title":"Mirror Descent Meets Fixed Share (and feels no regret)","venue":"cs.LG","work_id":"ed740a58-179e-4ccf-9ae5-6401d7a6ad45","year":2012},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:24.966318Z"},"links":{"cited_paper":"/paper/1202.3323","citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:bc632cc05eeb5de7222bdc8e3eb8bf996298eed54fd3912b3f0010b41766eea9","observation_id":"44ad8126-24eb-4b0a-8c24-58ee053d4fc6","resolution":{"observed_at":"2026-08-07T04:38:29.195433Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:37.581718Z","title":"Mirror descent meets fixed share (and feels no regret)","venue":null,"work_id":"75b4e36d-ffd4-425a-b9e8-24b31cf1a8ed","year":2012},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:25.116766Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:53411dd52355f7637df98810f3b254c8f62050560f32cc0fef0a8e93c351b131","observation_id":"27331ec4-25d0-4cc9-871b-31911ca3a29b","resolution":{"observed_at":"2026-08-07T04:38:37.690974Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:37.363157Z","title":"I-divergence geometry of probability distributions and minimization problems","venue":null,"work_id":"4aafebbf-3ce1-4d3c-bf8c-dab0bffe9221","year":1975},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:25.234361Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:3be7ba2f12b5ef48e07bd6db876d29463ca7c11deeb514e92f96f9f23aa8fb76","observation_id":"746cb21c-e129-4752-b811-ce22b09cfb5d","resolution":{"observed_at":"2026-08-07T04:38:37.479790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:37.159579Z","title":"and Matus, F","venue":null,"work_id":"ebe4a1ae-d7e4-4659-9e3a-cba66ebc17a0","year":2003},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:25.360458Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:f6ada3f7b73f9efdb58184755f41078da47cc4990c592badddea8aab39431113","observation_id":"c9f0ebb9-6070-4b5a-96dc-8cd3889eddd1","resolution":{"observed_at":"2026-08-07T04:38:37.240682Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:36.840903Z","title":"Parameter-free, dynamic, and strongly-adaptive online learning","venue":null,"work_id":"22192081-dafe-47d4-8afc-35ec183b6c03","year":2020},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:25.463553Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:5a6e07879da045505dbeb728acf9cfae4f8bf602ccad11a14c8cd47702bd3bf8","observation_id":"33a66c31-9303-4cf7-b79c-473c6ad7d32d","resolution":{"observed_at":"2026-08-07T04:38:36.972784Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:36.497184Z","title":"J., Kale, S., Luo, H., Mohri, M., and Sridharan, K","venue":null,"work_id":"07a9b88d-03c4-4964-8e9f-58d8de8b5d61","year":2018},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:25.533238Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:c1fa11949c1d556978b1aab89e09f0dcaa8109926802a8f04232cc46c09af73f","observation_id":"6703f382-8061-4a06-ae42-111c2c467594","resolution":{"observed_at":"2026-08-07T04:38:36.656187Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:36.193557Z","title":"Introduction to O nline C onvex O ptimization","venue":null,"work_id":"5ae9e369-4e51-4f46-b3d0-73380f1f837d","year":2016},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:25.686600Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:f0149328b0b144cc105c45a459dd9577f9f5424a52b676b0ea1bb267c16bdded","observation_id":"95d2d4b5-be6a-478e-87ed-9529907a198a","resolution":{"observed_at":"2026-08-07T04:38:36.353154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:35.866179Z","title":"and Seshadhri, C","venue":null,"work_id":"bc0f9354-3a5b-42c3-8c28-08fc18865607","year":2009},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:25.829321Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:5733ec8cb48390877f88862cec867018ffac7e535e88309be5894be884931866","observation_id":"a8d84607-bc2a-493d-8cbb-3466e75a59cc","resolution":{"observed_at":"2026-08-07T04:38:36.044804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:35.575494Z","title":"Logarithmic regret algorithms for online convex optimization","venue":null,"work_id":"e15fbb99-7248-46a1-a331-9254805498f1","year":2007},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:26.005646Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:4f9223b5833bff4747e94b14a434d81651a8a63da5290c302f6e00b0eb39d697","observation_id":"1d1b9f0e-7502-4db5-b0a0-a532f973eee4","resolution":{"observed_at":"2026-08-07T04:38:35.725970Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:35.208493Z","title":"Information Theory for Continuous Systems","venue":null,"work_id":"a78ef29e-6749-4195-8b1c-3e2ea4ec028d","year":1993},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:26.087378Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:bfacccda3aeeffa7a9563e288ca70b80b58806f473e2f0881ebc337d1b587c12","observation_id":"7052a411-bf70-43d3-a69e-a745565d47a1","resolution":{"observed_at":"2026-08-07T04:38:35.396004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:34.935091Z","title":"An optimal algorithm for bandit convex optimization with strongly-convex and smooth loss","venue":null,"work_id":"3962b539-908c-46d2-8054-fdf936bd82e4","year":2020},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:26.287091Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:152833215e90f1ca83fd57a4af7591d3ff3d77c0f968ebfcad879f4960e7d161","observation_id":"fd3de33c-0b69-45d0-9539-6dfa4315eae1","resolution":{"observed_at":"2026-08-07T04:38:35.026306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:34.665010Z","title":"and Cutkosky, A","venue":null,"work_id":"44102d2a-79b4-4988-bb07-309b9999e15a","year":2023},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:26.387050Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:75207100537305b9d31f40733f175eeab6a3eb817d4c5d0b9501a772dbb0fcd5","observation_id":"4531446e-cb52-4d6e-a763-a7d42210b04e","resolution":{"observed_at":"2026-08-07T04:38:34.791714Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:34.414638Z","title":"Mixability made efficient: Fast online multiclass logistic regression","venue":null,"work_id":"40046c71-1076-43fe-a726-23e0b323f4d1","year":2021},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:26.436411Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:1230996c5e8d88fcaf2a469e2cd15ee5c8c059bfc042abc2dbc266cd74d5e33f","observation_id":"3513fe37-44aa-4ddf-9129-defa2ddd6d1b","resolution":{"observed_at":"2026-08-07T04:38:34.522067Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:34.150329Z","title":"Near-optimal dynamic regret for adversarial linear mixture mdps","venue":null,"work_id":"fdb37b34-e2bf-4738-b5a9-7a18c4a3def6","year":2024},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:26.585864Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:069e99c57dfc7dfe3fed4d9c9fd3652fee292196c19ab6c68ef20d7a43b7f276","observation_id":"1c98d144-fc10-4cc6-aea4-016de5ccc54a","resolution":{"observed_at":"2026-08-07T04:38:34.284578Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:33.808004Z","title":"J., Hadiji, H., and van Erven, T","venue":null,"work_id":"9a861300-7565-4a50-98ae-f526ba940253","year":2022},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:26.702668Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:fa28fbf1222b395aa599ecd86a060fcba39cda8af1bcd9d783103d0804373ff9","observation_id":"19ae5522-a99e-41a9-8b21-4493123e9e41","resolution":{"observed_at":"2026-08-07T04:38:33.949069Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:33.550596Z","title":"Online learning via sequential complexities","venue":null,"work_id":"246005c4-4adf-4f60-807d-067381951e6b","year":2015},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:26.807657Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:778224bacbbd1240e627b55c6370756be4e0c93f5bd6bab6276e63e8adb5c50a","observation_id":"d0d541fb-09b6-444b-bf97-f900e24ed630","resolution":{"observed_at":"2026-08-07T04:38:33.679024Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:33.294981Z","title":"and Ben-David, S","venue":null,"work_id":"e22ff5c6-a5f9-4ade-b5ec-14a0c1d5a06f","year":2014},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:26.909268Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:961ca5820173050ac3a09f1992491779e3cf0b6bc81437c1f40485ad594dbbeb","observation_id":"1451fe17-54db-42f9-86df-cc42a21d625a","resolution":{"observed_at":"2026-08-07T04:38:33.421281Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:33.030994Z","title":"The many faces of exponential weights in online learning","venue":null,"work_id":"15eafeaa-b850-428c-8623-75ed4ce56e9e","year":2018},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:27.106125Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:56622d9eb30ab4b3b41aa0abaaa7e6094109784b17e6d2e9aada7f3dbd77a65b","observation_id":"f55faf6b-35bb-4361-bd2a-87b1ab2ac24e","resolution":{"observed_at":"2026-08-07T04:38:33.151288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:32.751956Z","title":"and Koolen, W","venue":null,"work_id":"f034569d-1f3f-413b-8bd9-c237ce2510e5","year":2016},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:27.207650Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:ef2f8743def72b4cd8a03d5d651e63b4ab24a12fd648edc0d79fe8c2d21948db","observation_id":"91dfe9c6-318a-4774-9b0c-8f75a088ddd9","resolution":{"observed_at":"2026-08-07T04:38:32.871210Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:32.519933Z","title":"D., and Williamson, R","venue":null,"work_id":"92d49294-4670-4a16-9ce8-9234d4f4c13e","year":2012},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:27.321956Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:05b8dd3b15f85b3ad2a7e4c7312b0b9d69d1810f3488adfcbbabf845a7bc6a41","observation_id":"dfe21616-087d-4d82-89b7-2f8b40ccb346","resolution":{"observed_at":"2026-08-07T04:38:32.660139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:32.149300Z","title":"D., Mehta, N","venue":null,"work_id":"3be3f3bd-b286-43d4-93cc-a53246224b61","year":2015},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:27.456058Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:1bc2bf918856016827a93b7020543ca6cfe8ca23ad330c9f60e01ec2697486e1","observation_id":"3a724d75-06bc-4a36-bc73-c28428f2b0cd","resolution":{"observed_at":"2026-08-07T04:38:32.343613Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:31.936111Z","title":"A game of prediction with expert advice","venue":null,"work_id":"5fbd0476-cdf0-444a-89bf-d8411f1b9e80","year":1998},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:27.604644Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:e72e8f086d1b0deb3da811a0cb209ae48a856fcd8905668c87d80ee5b025870f","observation_id":"a2a740a7-07b8-4a12-8998-9b44b41234e1","resolution":{"observed_at":"2026-08-07T04:38:32.044831Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:31.662312Z","title":"Competitive on-line statistics","venue":null,"work_id":"d10402b6-03e2-4476-857d-97cb24c30788","year":2001},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:27.727945Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:f22b852c635b0853ff19527bcb2f48d5a737b31162e8744ea800cb54877848a1","observation_id":"6c5d5732-7cea-4809-a2cf-0c842fa7780d","resolution":{"observed_at":"2026-08-07T04:38:31.764012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:31.445378Z","title":"and Zhdanov, F","venue":null,"work_id":"670fbac5-754f-4b2e-9bf9-5fcaa713f216","year":2008},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:27.869223Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:770fc50e589fd87392498e80fc26909096c28bdfd9b9377fd24042816c193009","observation_id":"750395ee-bcef-4e41-a3c4-5952c26097f2","resolution":{"observed_at":"2026-08-07T04:38:31.546899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:31.150910Z","title":"and Luo, H","venue":null,"work_id":"50a7f532-5e64-48e7-918b-7bde9126daf8","year":2021},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:28.005771Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:676da903bd622f5e5161bc45a0ac8e35ba17b72ac4f906a9404a58d63fd40342","observation_id":"98708636-c295-4c91-aad3-27017c105f6e","resolution":{"observed_at":"2026-08-07T04:38:31.287730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:30.883450Z","title":"Adaptive online learning in dynamic environments","venue":null,"work_id":"d882e739-612e-4461-bc4b-ff4a1fcac580","year":2018},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:28.116442Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:4ea4d0114ddc31f38173e5c08bf89f61aafe363a39bdfdf0eb6144a3d4a0dcc3","observation_id":"7038781c-e1db-4eeb-b7a6-fe739f3c230c","resolution":{"observed_at":"2026-08-07T04:38:30.986461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:30.663983Z","title":"Adapting to continuous covariate shift via online density ratio estimation","venue":null,"work_id":"8b0a5297-4b42-42ed-a2b9-2d275a37a12f","year":2023},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:28.275232Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:2da788dd9bf0e183c941569e2212c5dcf731c45bb03bf85589de2b31a10bed41","observation_id":"c0980bdd-3510-4fdb-94d3-196be18ed6cc","resolution":{"observed_at":"2026-08-07T04:38:30.758442Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:30.412732Z","title":"Unconstrained dynamic regret via sparse coding","venue":null,"work_id":"293149d2-1e48-488a-bc8a-31cfab6604d8","year":2023},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:28.385509Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:7edc0f9cdecf73d76a85344a36ad438e7542f3b3db4aa2a56e667795f08eb3e1","observation_id":"08e339e7-b236-41ca-89c8-7115a1c1b8b1","resolution":{"observed_at":"2026-08-07T04:38:30.559371Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:30.185354Z","title":"Dynamic regret of convex and smooth functions","venue":null,"work_id":"9092bcde-4f89-4543-aa07-ad4ab4ea3353","year":2020},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:28.515154Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:b0277ddce7c7c0271ae276b8f9d37c666ac5df99b97d172b2cb1d2ae0615dc53","observation_id":"4f053094-f813-415c-9e48-c64c21114dc8","resolution":{"observed_at":"2026-08-07T04:38:30.335466Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:29.930774Z","title":"Efficient methods for non-stationary online learning","venue":null,"work_id":"111b65fe-d625-4851-8874-c10f34b3e051","year":2022},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:28.648045Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:02969b8e2f21961ca3f6d22265301f8aebab3b5305c5f93c78452ab76a508132","observation_id":"f4c24c05-f12f-4e8c-bf78-e1665a93a86a","resolution":{"observed_at":"2026-08-07T04:38:30.058868Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:29.715615Z","title":"Adaptivity and non-stationarity: Problem-dependent dynamic regret for online convex optimization","venue":null,"work_id":"292ef7a6-8638-47e3-96d7-65536c94ae34","year":2024},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:28.771767Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:257c68397a61aa6db084d851e31fc2026b4e66be74f4de67e98f5eccf0c86cc9","observation_id":"3fa9d2c7-6069-4b45-94b0-eadb6efd06c6","resolution":{"observed_at":"2026-08-07T04:38:29.836447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+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":"2026-08-07T04:38:29.403525Z","title":"Online convex programming and generalized infinitesimal gradient ascent","venue":null,"work_id":"ab781dd1-088f-43d3-9f99-013b6941c26c","year":2003},"citing_paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T04:38:28.905504Z"},"links":{"citing_paper":"/paper/2506.10616"},"observation_digest":"sha256:f70365107e1298306ed58fb03e75175852e48a4b971ecb9542e6ce753eab563b","observation_id":"f118db62-ef2c-49e8-b05b-32a35264d124","resolution":{"observed_at":"2026-08-07T04:38:29.550345Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-19T06:32:44.657259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.10616","last_updated":"2025-06-12T12:00:08Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T04:19:15.133946Z","submitted_at":"2025-06-12T12:00:08Z","title":"Non-stationary Online Learning for Curved Losses: Improved Dynamic Regret via Mixability"},"reference_resolution":{"displayed":41,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":3,"verified_exact":1,"verified_fuzzy":37},"total_outbound_references":41},"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":"2026-08-19T06:32:44.657259+00:00","source":"crossref"},{"observed_at":"2026-08-19T06:32:39.956319+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 41 of 41 outbound references and 1 inbound Pith citation observation for arXiv:2506.10616."}