{"as_of":"2026-08-09T07:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bd313dd95fc92a69a4331c213049b24d379f24fd01d2d05d8669e6c5d936e92c","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":"2026-08-07T18:54:37.728058Z","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":"2026-08-09T06:31:02.800959+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/2502.10292/citation-record","integrity":"/paper/2502.10292/integrity","json":"/paper/2502.10292/citation-record.json","paper":"/paper/2502.10292"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:54:38.719606Z","title":"Abernethy, Young Hun Jung, Chansoo Lee, Audra McMillan, and Ambuj Tewari","venue":null,"work_id":"dae2b8d2-4f98-410c-b565-9187e88d4366","year":2019},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:36.936005Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:f674d576f185ccd1085eb4ccd0c462b81511270f5dd2d50be1fd27cb831a3d95","observation_id":"e56fbf86-aee1-492d-b47f-8e15d6835b65","resolution":{"observed_at":"2026-08-07T18:54:38.722818Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.709329Z","title":null,"venue":null,"work_id":"3a8966d0-657a-4202-acfd-5ea8d25a51dd","year":2018},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:36.960881Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:0f4df8074257ddca57c3db9bf483f21ce2f6ee0dff10a28b7220ed7a7bff0455","observation_id":"e8363f3d-12c7-49c1-8630-5898ac56ba17","resolution":{"observed_at":"2026-08-07T18:54:38.712504Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.699328Z","title":"Learning in non-convex games with an optimization oracle","venue":null,"work_id":"3ebd9f3e-e7f7-43b8-84ad-daae8d8b4499","year":2019},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:36.964973Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:8717ca761540c5ed40c768c10c1f1487bb2e696d60284f83c7823d181723d287","observation_id":"d0bc625a-c985-4e0f-b912-5618d4a15ad6","resolution":{"observed_at":"2026-08-07T18:54:38.702703Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.688863Z","title":"Private PAC learning implies finite littlestone dimension","venue":null,"work_id":"5b069d27-d804-4bf9-b41b-65a2a1480ada","year":2019},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:36.969768Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:1d232454590279afd566f786dbcdbac1a293c6d292abe80b247b0209a402a124","observation_id":"ebb5e9ee-baf2-4f93-92f1-957fe9cad955","resolution":{"observed_at":"2026-08-07T18:54:38.692353Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.676969Z","title":"The multiplicative weights update method: a meta-algorithm and applications","venue":null,"work_id":"74dd69c8-1b01-45ee-811a-204b578c693e","year":2012},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:36.973712Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:14ce4aac08d632f963cfcb0de4f5fe752fa75bbe1da4c00aa0f5b30845572c30","observation_id":"6a134948-b267-4670-9aab-50d9f523e009","resolution":{"observed_at":"2026-08-07T18:54:38.681342Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.665626Z","title":"Bartlett and Shahar Mendelson","venue":null,"work_id":"d8aedcce-700c-4c70-8f5f-a3f5a038253a","year":2001},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:36.978052Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:13a28fe4f31bd5565e8312c0e4eb62d97c6685807556dc17990a253ac47cc4d1","observation_id":"f7072022-b587-48de-b60a-45151e6c1f5b","resolution":{"observed_at":"2026-08-07T18:54:38.669677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.651578Z","title":"Fat-shattering and the learnability of real-valued functions","venue":null,"work_id":"9f2f8f4c-d436-4236-b483-dd179f2f1ad6","year":1994},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:36.983777Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:91b3ac1f9f33efb54ad0e608807279a2053bb8d123dfa05ef61f088d6f3316fd","observation_id":"d86eb8c7-e4db-4763-8f62-c9ec250fa8fa","resolution":{"observed_at":"2026-08-07T18:54:38.656359Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.637829Z","title":"Limits of private learning with access to public data","venue":null,"work_id":"1860d14e-7d18-4863-8326-604942b93913","year":2019},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:36.986991Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:76f525e9b3e53dcd880456eeb8f8e7fc8341d72042804c80dd695f3a0f689271","observation_id":"fa3c644f-261f-4310-9a3d-5ada96c1e861","resolution":{"observed_at":"2026-08-07T18:54:38.642533Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.625291Z","title":"Learning privately with labeled and unlabeled examples","venue":null,"work_id":"c4ef9860-54d5-40ca-bb26-c2e143d22830","year":2015},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:36.991121Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:210e03ff47c149243eabda0986b126cf2527c6a2053237d6713431eb6257e83d","observation_id":"9741c25e-a59f-4f12-9281-180dc9c73293","resolution":{"observed_at":"2026-08-07T18:54:38.629677Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.612598Z","title":"Agnostic online learning","venue":null,"work_id":"02790177-504d-4746-8073-f1c8d40960ff","year":2009},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:36.994925Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:f0c7521cffe33007cc4c9eceb8561c1e9d5c8124e14ce4ed6e808cb35e9e1627","observation_id":"91bd55fa-1610-4d5a-85cd-67729404707e","resolution":{"observed_at":"2026-08-07T18:54:38.616743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.600418Z","title":"Harmonic analysis and applications","venue":null,"work_id":"ffa250ac-131b-46e0-9533-67d091e5df18","year":2020},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:36.998478Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:da3b621753eef7b913c3012a0ea1ff0ced6fee4536cccdf6b1b1c0995966469b","observation_id":"2b17f9cc-8ac3-416c-89fe-f84a8dedf27d","resolution":{"observed_at":"2026-08-07T18:54:38.604808Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.586891Z","title":"Smoothed analysis of sequential probability assignment","venue":null,"work_id":"68f1f2c5-0766-46ac-8671-17516ec74ee9","year":2023},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.002486Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:a2f901b5211014778e33bd7697c0a360ce8b99ea6832fa9927a7c61678d62038","observation_id":"caf602ac-d473-462b-8f0b-69d6ba5e20c1","resolution":{"observed_at":"2026-08-07T18:54:38.591713Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.572483Z","title":"The sample complexity of approximate rejection sampling with applications to smoothed online learning","venue":null,"work_id":"32507ae4-69d3-449c-b8c5-6f010101ecc6","year":2023},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.006396Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:df4bc1250ae6635f259f204b005ef0dc57b90af321fea6d3a182f7dc42218d6e","observation_id":"c5996326-868f-49b2-91cc-f0d3c9fa2c82","resolution":{"observed_at":"2026-08-07T18:54:38.577686Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:54:37.010277Z","title":"Smoothed online learning is as easy as statistical learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.010277Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:2cc88d5314a8cbd4b34e1196bf0a298ebd7e279b0a9373e503692b384f6f1ae0","observation_id":"7c1cba6f-11b5-4153-9702-d8005cdba5d2","resolution":{"observed_at":"2026-08-07T18:54:37.010277Z","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":"2026-08-07T18:54:38.549086Z","title":"Oracle-efficient smoothed online learning for piecewise continuous decision making","venue":null,"work_id":"ba8376a4-cd46-47f7-b10c-cd960c90c532","year":2023},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.013788Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:c83fc0e7042b0517b89ec989adedccbc01f55e057a532d723dfacc9b35b664a0","observation_id":"2f534684-f656-4430-b6a9-5b8c71a4777f","resolution":{"observed_at":"2026-08-07T18:54:38.554247Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09483","last_updated":"2024-02-13T23:40:50Z","snapshot_observed_at":"2026-08-03T18:59:34.785905Z","submitted_at":"2024-02-13T23:40:50Z","title":"Oracle-Efficient Differentially Private Learning with Public Data","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09483","snapshot_observed_at":"2026-08-07T18:54:37.016944Z","title":"Oracle-efficient differentially private learning with public data","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.016944Z"},"links":{"cited_paper":"/paper/2402.09483","citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:9d96dc274394d3ff0e653de11eef4648d2e8d82634c172bf19dd45dd1aa6886e","observation_id":"76c60404-9441-45a5-8c67-3d4fff1f0ab2","resolution":{"observed_at":"2026-08-07T18:54:37.016944Z","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":"2026-08-07T18:54:38.536613Z","title":"On the performance of empirical risk minimization with smoothed data","venue":null,"work_id":"b5c10446-c3bb-4310-98e3-810b89fa298f","year":2024},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.020972Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:47de7d5c2cff1d400458b7028b3e6cfdbdcdfd0a798beee5101ad3db430ef0ce","observation_id":"41fc37d0-edc5-4ba6-ba63-a2d2267c597b","resolution":{"observed_at":"2026-08-07T18:54:38.540816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.524605Z","title":"Smoothed online learning for prediction in piecewise affine systems","venue":null,"work_id":"22d456e2-4d2d-4b67-9efb-ddb75628c95a","year":2024},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.057371Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:09e4abeee3289397f4b10b2a6ea778aadbfc323be71564672e0cc750c96391ff","observation_id":"1baf3e85-dc07-4bfc-9ada-40f1532a86cb","resolution":{"observed_at":"2026-08-07T18:54:38.528904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.513160Z","title":"Concentration Inequalities: A Nonasymptotic Theory of Independence","venue":null,"work_id":"0b358bb4-f800-4c28-831c-c0ecd7341f9b","year":2013},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.110749Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:20cbc16e9592eb51d90d0cf0cf4244fa2643e9361c3d98df52951b2fccf0b2f2","observation_id":"8b5f876b-c92b-4b74-b7ce-d0a29b0cf9ea","resolution":{"observed_at":"2026-08-07T18:54:38.516814Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.501704Z","title":"An equivalence between private classification and online prediction","venue":null,"work_id":"bf9ab790-07e4-4790-a838-820845971c04","year":2020},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.183793Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:81b97002d6bfe8a581cd524f435cb82bed85416a04cd577f4c3d70bf8cefc26a","observation_id":"2aa4e9a4-c788-475a-b5e4-50a9a180665c","resolution":{"observed_at":"2026-08-07T18:54:38.505598Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:54:37.212459Z","title":"Prediction, learning, and games","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.212459Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:2e3f59f0f1f0bd659ecc7ea8a6c9daae8c2d34ec5d9c48498befdc1e57830626","observation_id":"e04ef1cc-8179-469d-ae50-0667ee1b50c5","resolution":{"observed_at":"2026-08-07T18:54:37.212459Z","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":"2026-08-07T18:54:37.217060Z","title":"Oracle-efficient online learning and auction design","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.217060Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:808ea5e58bfaf9a158d898cf28cbbbbf5efd123739e896daecd803e52b0e504c","observation_id":"469b9131-2f53-4469-b747-2d5357d198c1","resolution":{"observed_at":"2026-08-07T18:54:37.217060Z","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":"2026-08-07T18:54:38.476596Z","title":"The speed of mean glivenko-cantelli convergence","venue":null,"work_id":"efa3caf5-9212-449c-a30f-c17c8207d0b4","year":1969},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.221043Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:f498f7a4684794fcbaf475160981e09ce50e6f8f8eaa9aca647ffc7256f854df","observation_id":"8024c85d-cb55-4c3a-a585-04867e555870","resolution":{"observed_at":"2026-08-07T18:54:38.480182Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.465589Z","title":null,"venue":null,"work_id":"27cb8769-f935-41ae-93dd-67c4dbb7a66c","year":2006},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.224746Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:e91d0b6cf2cf07317ed8b0ca4858102efeb95e367c8b02ed8a7d8d766fd74902","observation_id":"8a7e8779-14da-469e-9caa-a81fd7088309","resolution":{"observed_at":"2026-08-07T18:54:38.469804Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.453563Z","title":"The algorithmic foundations of differential privacy","venue":null,"work_id":"61baec2f-530b-4ca8-a3c7-383cccfb9ef8","year":2014},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.228908Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:0f7b61f6fcfb79b80eea04b6643b444c1d173f8fa39da1564bef94a3ebf5ee47","observation_id":"f41a7017-4bb2-4140-a8b6-d1e0cf64b335","resolution":{"observed_at":"2026-08-07T18:54:38.457978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.440040Z","title":"Dual query: Practical private query release for high dimensional data","venue":null,"work_id":"b61402af-e8f0-4244-ba85-76b983b6e987","year":2014},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.232901Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:4d477fe4bc437478a1ca9b72eca2f3474c2965bd07473adaf6b5c304fecfc3c3","observation_id":"5b12828c-7cd2-49dc-9132-09e74297c13a","resolution":{"observed_at":"2026-08-07T18:54:38.445008Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.424212Z","title":"Exact identification of read-once formulas using fixed points of amplification functions","venue":null,"work_id":"b4089c56-d40e-421f-8a3c-898ddad1d0f2","year":1993},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.236816Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:5b853210d4f3db673b02dcd71a5a28d001ae4d048497f5caca12ff8049d6cf8b","observation_id":"16b5d3e6-6a2e-4e92-91ca-7e76edab9bd4","resolution":{"observed_at":"2026-08-07T18:54:38.429611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.408581Z","title":"Smoothed analysis of online and differentially private learning","venue":null,"work_id":"8477521a-d43c-4f4e-8afd-f17d4b8b25b6","year":2020},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.241125Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:21322662eac99278d18fd11294a887cf66e3353e724b91702262859032fcb4e2","observation_id":"ec619249-a10c-45d5-95d1-f3da1e0660b4","resolution":{"observed_at":"2026-08-07T18:54:38.414586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.393919Z","title":"Oracle-efficient online learning for beyond worst-case adversaries","venue":null,"work_id":"9e6dde22-91b5-45c9-9bec-fde254535a73","year":2022},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.245888Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:2e40c92ebf44189e3a4bc52d06048f1ea26f543e3173f0360f3e1b4e62ed92ba","observation_id":"d471368c-f6d3-48cf-b46c-ad439440a784","resolution":{"observed_at":"2026-08-07T18:54:38.399266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.380568Z","title":"Smoothed analysis with adaptive adversaries","venue":null,"work_id":"dcb51b7c-228d-4dad-a615-9ae5815b62bd","year":2021},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.250951Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:e49575857b67fb9503544ed846f63f3b4319ec228feda8c88814d4fbec67dab9","observation_id":"531ad67d-f0c1-4f85-a1d4-09779404462f","resolution":{"observed_at":"2026-08-07T18:54:38.385513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.367421Z","title":"Jordan, and Eric Zhao","venue":null,"work_id":"3a25dc6b-f159-4cf9-8f74-f23697c5a7db","year":2023},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.323131Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:f6cd86e6382b913283aee1c8fb6b4b77d8ed4c9405f0e883da11256449157076","observation_id":"b480da8c-73eb-4d51-afc9-2fc7248b16c0","resolution":{"observed_at":"2026-08-07T18:54:38.371780Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:54:37.390081Z","title":"The computational power of optimization in online learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.390081Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:6760782d0237577fe37d43e9238390cc5f99ddfa1e6f537dbcad1c6a2f48b9aa","observation_id":"1d9fde88-e23c-45d0-8ffb-d6ba7b424ec1","resolution":{"observed_at":"2026-08-07T18:54:37.390081Z","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":"2026-08-07T18:54:38.346039Z","title":"Prediction with expert advice by following the perturbed leader for general weights","venue":null,"work_id":"3252b53d-d4c7-4435-aa7d-39f1a0089919","year":2004},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.413934Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:657a6d7ca288a74cb5dcb1cc164f8b495c92a4c51c8500056a34175f231902ad","observation_id":"936d3774-d949-47c7-8123-cbb47ef59ffa","resolution":{"observed_at":"2026-08-07T18:54:38.350869Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:54:37.418087Z","title":"Efficient algorithms for online decision problems","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.418087Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:96dd3966507db9a353d237074f53f4c8d1112954d82f3215d284733afc0cba15","observation_id":"8d7c5c43-57a9-4a34-af4e-bcd9d965a360","resolution":{"observed_at":"2026-08-07T18:54:37.418087Z","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":"2026-08-07T18:54:37.422627Z","title":"Bandit Algorithms","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.422627Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:953c7171402feb007bf4763ebce895227931ede282ba09b35881f6c6680e31e4","observation_id":"0800d918-b717-4d95-b5f5-cec95683132d","resolution":{"observed_at":"2026-08-07T18:54:37.422627Z","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":"2026-08-07T18:54:37.427015Z","title":"Deep learning","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.427015Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:753f323f0dcf23d92e29bb290154653eb3e22a8a17e681f077eafd91c232615a","observation_id":"2e3fa8a9-e4b4-4534-a270-1506cdd828d4","resolution":{"observed_at":"2026-08-07T18:54:37.427015Z","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":"2026-08-07T18:54:38.308555Z","title":"Learning quickly when irrelevant attributes abound: A new linear-threshold algorithm","venue":null,"work_id":"652c51f7-8295-4956-abc1-f70bb997ff67","year":1988},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.431043Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:d3d3d388d171a4340ba20750573e9378a79d24ea57ed0bdba7b786bf8b10bcdf","observation_id":"6c524a57-9fc0-40cd-97c5-3470bcf289d3","resolution":{"observed_at":"2026-08-07T18:54:38.313084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.294762Z","title":"Entropy and the combinatorial dimension","venue":null,"work_id":"d9ea311f-1807-4f7f-b73f-07dfa7aaf945","year":2003},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.434824Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:5329fb16b828ecd4025d1eaf190e727a2b05b4a37b22bdd8857f19153ded8ab2","observation_id":"7fdd550e-25f1-42c4-880f-3088ee5be577","resolution":{"observed_at":"2026-08-07T18:54:38.299681Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.281630Z","title":"How to use heuristics for differential privacy","venue":null,"work_id":"00cb2096-d143-4f28-92fe-c9d869cd8866","year":2019},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.485356Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:29b27f7b37e8d5d63cafc22addc683e6592b0f5002308db74042788573822a06","observation_id":"96ade268-6893-4341-90d5-9b2f3d4a7ae6","resolution":{"observed_at":"2026-08-07T18:54:38.285658Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.269375Z","title":null,"venue":null,"work_id":"7a523998-4cd9-400a-b1e4-1e77deef4990","year":2020},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.559505Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:03a2f33f12a513844dbafd27b0a7f98f294d998ef4125d075145f4f9231c67cf","observation_id":"9fa633c0-2524-4f86-b9b6-41fb71d45562","resolution":{"observed_at":"2026-08-07T18:54:38.273132Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.195558Z","title":"The geometry of differential privacy: the sparse and approximate cases","venue":null,"work_id":"6f6ed3fc-27b8-4cc8-a642-56b96f6d28f2","year":2013},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.585274Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:a0a09789dbaf1015053fe6cab366560eea29d4cc9d3b99bf316a826a4b0c21b3","observation_id":"81e878a2-31d9-46fd-9aed-14b77905585f","resolution":{"observed_at":"2026-08-07T18:54:38.260911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1104.5070","last_updated":"2011-04-27T04:11:10Z","snapshot_observed_at":"2026-07-06T02:26:52.901468Z","submitted_at":"2011-04-27T04:11:10Z","title":"Online Learning: Stochastic and Constrained Adversaries","version":1},"cited_work":{"arxiv_id":"1104.5070","doi":null,"metadata_source":"pith","pith_arxiv_id":"1104.5070","snapshot_observed_at":"2026-08-07T18:54:37.760302Z","title":"Online Learning: Stochastic and Constrained Adversaries","venue":"stat.ML","work_id":"28bccf6c-69e0-4684-9e70-c51b4c4c6e63","year":2011},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.589535Z"},"links":{"cited_paper":"/paper/1104.5070","citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:48e0dd6f70c71a46eedb714b3e83cb38f4436516b0b1c8268cd4a1cca4b9b8d8","observation_id":"cbe4a3be-b662-419e-8e48-edf40ab6fe4e","resolution":{"observed_at":"2026-08-07T18:54:37.777230Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.048967Z","title":"Sequential complexities and uniform martingale laws of large numbers","venue":null,"work_id":"71407810-22fb-42b6-a98e-ee590e753cef","year":2015},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.594335Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:fd7c6c65ca9afa1c13e07a040fbeab31e1fed5cc4463fcc0fff0a4adbf0ecceb","observation_id":"992d4279-3c0c-4284-9aaa-fe91868bb622","resolution":{"observed_at":"2026-08-07T18:54:38.117178Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:38.012804Z","title":"Shalev-Shwartz and S","venue":null,"work_id":"682aa518-b8f6-422a-a61c-ea96eae0dd40","year":2014},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.599355Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:48c999f079f8545912df249d5358352d63ea9356f82493bf8b938a588bcf54ed","observation_id":"c264ab23-ad44-47a5-adbc-b44c617c0429","resolution":{"observed_at":"2026-08-07T18:54:38.017435Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:54:37.604580Z","title":"A wavelet tour of signal processing, 1999","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.604580Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:aa037416a5766bf7dc66507429567682b0a64aee60996e1264d29c31cb617a6e","observation_id":"53671b76-09c1-481b-8fed-2502799689bd","resolution":{"observed_at":"2026-08-07T18:54:37.604580Z","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":"2026-08-07T18:54:37.992771Z","title":"Online non-convex learning: Following the perturbed leader is optimal","venue":null,"work_id":"1a7cfabc-6254-443e-ab11-445c40435279","year":2020},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.608914Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:aa28fd8146cf7a2d0ff98c28ed319e553b2876e3214fe3b88c49de51cfb50161","observation_id":"410e0c78-c017-4531-bade-c8b970e0ec33","resolution":{"observed_at":"2026-08-07T18:54:37.997085Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:54:37.672872Z","title":"Efficient algorithms for adversarial contextual learning","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.672872Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:7e0d4a50b639e3e725761db469cc8f7dbeab83fa9b7596aa8ce0a34c9eca86c5","observation_id":"baf0eba5-2018-4ff4-8d00-de0f61878a92","resolution":{"observed_at":"2026-08-07T18:54:37.672872Z","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":"2026-08-07T18:54:37.973454Z","title":"Hardness of agnostically learning halfspaces from worst-case lattice problems, 2022","venue":null,"work_id":"9138e744-2d22-4b31-921c-1b6dcaae69f0","year":2022},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.701854Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:e6039af14e8b886aa486859a364340593bfe333d403d498f528f9b1fb82f049f","observation_id":"aea7939b-c092-4993-be8a-a9784967e26f","resolution":{"observed_at":"2026-08-07T18:54:37.977659Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:37.960550Z","title":"A theory of the learnable","venue":null,"work_id":"62f7baf3-5067-4974-bd78-b8d099e3700c","year":1984},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.706373Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:097c07d5be97a1f304325b493912a49e6fc33882dc8783e5d746b048c7ec2711","observation_id":"dd841a4f-ccf0-4fbf-8504-e11279c25eea","resolution":{"observed_at":"2026-08-07T18:54:37.965387Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:37.948688Z","title":"A class of algorithms for pattern recognition learning","venue":null,"work_id":"6fc05dfc-98b3-4728-93b9-0031734afd6a","year":1964},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.710452Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:09cef3ad4460cee07508e0de050743ae92593ccab6f42a2c8cc1a4b29d18c77f","observation_id":"9e1a34b4-7c69-4ed9-ad03-6df3389407ee","resolution":{"observed_at":"2026-08-07T18:54:37.952850Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:54:37.714590Z","title":"High-dimensional probability: An introduction with applications in data science, volume 47","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.714590Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:7e408f9309b6d58f232adde018929514e8599bd847174dd1e2fbcf879df05497","observation_id":"78e25ada-098a-47ab-ac71-3c6fae60fae5","resolution":{"observed_at":"2026-08-07T18:54:37.714590Z","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":"2026-08-07T18:54:37.929676Z","title":"Foundations of signal processing","venue":null,"work_id":"5f41454a-2b66-41db-b140-89b3bdfd2efa","year":2014},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.719184Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:296ce0c398b836ec415bf93359ca7af06a55074c7867c03bc7bf3c5f4c710ddb","observation_id":"2ac9dbcf-dbdb-439a-9efe-95a111a816d3","resolution":{"observed_at":"2026-08-07T18:54:37.933550Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-07T18:54:37.885170Z","title":"New oracle-efficient algorithms for private synthetic data release","venue":null,"work_id":"376c4bd7-0a93-4f79-a2c5-47017c9cbcbc","year":2020},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.723311Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:93f06301e915ca19e14b480de23267415e27b8a935b9102642416a7dc1ed9a41","observation_id":"20a1ff05-73fd-41a5-92a9-8fc55e6e43b6","resolution":{"observed_at":"2026-08-07T18:54:37.920946Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T18:54:37.728058Z","title":"Adaptive oracle-efficient online learning","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-07T18:54:37.728058Z"},"links":{"citing_paper":"/paper/2502.10292"},"observation_digest":"sha256:150e31b1280baffe6544f61485b088124da934809a6ec896882ba584a070979f","observation_id":"d761c3b8-60c3-4239-9473-50715c28ebe5","resolution":{"observed_at":"2026-08-07T18:54:37.728058Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.10292","last_updated":"2025-02-14T16:52:50Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T18:37:39.300128Z","submitted_at":"2025-02-14T16:52:50Z","title":"Small Loss Bounds for Online Learning Separated Function Classes: A Gaussian Process Perspective"},"reference_resolution":{"displayed":54,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":15,"verified_exact":1,"verified_fuzzy":38},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 54 of 54 outbound references and 0 inbound Pith citation observations for arXiv:2502.10292."}