{"as_of":"2026-08-20T13:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:92590c3a3b8cf55fc2f133fb81f820950089bbaa0fdb4aad614607137dc074a3","coverage":[{"denominator":12,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-10T21:34:10.717235Z","state":"measured"},{"denominator":12,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":12,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+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/2501.06258/citation-record","integrity":"/paper/2501.06258/integrity","json":"/paper/2501.06258/citation-record.json","paper":"/paper/2501.06258"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-10T21:34:10.900742Z","title":"Complexity regularization for squared error loss, 2007","venue":null,"work_id":"12b692c5-6970-48bb-87bf-14f2d98dc8e0","year":2007},"citing_paper":{"arxiv_id":"2501.06258","last_updated":"2025-01-09T10:21:19Z","snapshot_observed_at":"2026-08-14T13:05:05.651477Z","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-10T21:34:10.665133Z"},"links":{"citing_paper":"/paper/2501.06258"},"observation_digest":"sha256:bc32c9d2bec331defd3cd368c674a5d48d2b145a3f4039722de09e4a4efc33e6","observation_id":"b739e923-7477-40af-82e6-94efd5a96459","resolution":{"observed_at":"2026-08-10T21:34:10.907552Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1109.5647","last_updated":"2012-12-09T21:19:27Z","snapshot_observed_at":"2026-08-15T04:34:09.911130Z","submitted_at":"2011-09-26T17:24:52Z","title":"Making Gradient Descent Optimal for Strongly Convex Stochastic Optimization","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1109.5647","snapshot_observed_at":"2026-08-10T21:34:10.670000Z","title":"Making gradient descent optimal for strongly convex stochastic optimization","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2501.06258","last_updated":"2025-01-09T10:21:19Z","snapshot_observed_at":"2026-08-14T13:05:05.651477Z","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-10T21:34:10.670000Z"},"links":{"cited_paper":"/paper/1109.5647","citing_paper":"/paper/2501.06258"},"observation_digest":"sha256:284b4bbad1dd479c98507927e078d26ae144db084c1b91779a6c5465e12c4f86","observation_id":"562e4ecf-1dd9-4a40-91a8-ef2324e42925","resolution":{"observed_at":"2026-08-10T21:34:10.670000Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1802.09127","last_updated":"2018-02-26T02:04:57Z","snapshot_observed_at":"2026-08-18T19:31:02.938218Z","submitted_at":"2018-02-26T02:04:57Z","title":"Deep Bayesian Bandits Showdown: An Empirical Comparison of Bayesian Deep Networks for Thompson Sampling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1802.09127","snapshot_observed_at":"2026-08-10T21:34:10.674867Z","title":"Deep bayesian bandits showdown: An empirical comparison of bayesian deep networks for thompson sampling","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2501.06258","last_updated":"2025-01-09T10:21:19Z","snapshot_observed_at":"2026-08-14T13:05:05.651477Z","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-10T21:34:10.674867Z"},"links":{"cited_paper":"/paper/1802.09127","citing_paper":"/paper/2501.06258"},"observation_digest":"sha256:78b9db26f2b72ff3c188ef397b1e4d593ed05107d39f890d0f0e50c9b21f3bc8","observation_id":"87656331-4796-4c35-890d-17f1864efcdb","resolution":{"observed_at":"2026-08-10T21:34:10.674867Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.07476","last_updated":"2017-10-05T13:28:50Z","snapshot_observed_at":"2026-08-14T21:29:08.308841Z","submitted_at":"2016-11-22T19:24:49Z","title":"Eigenvalues of the Hessian in Deep Learning: Singularity and Beyond","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.07476","snapshot_observed_at":"2026-08-10T21:34:10.679912Z","title":"Eigenvalues of the hessian in deep learning: Singularity and beyond","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2501.06258","last_updated":"2025-01-09T10:21:19Z","snapshot_observed_at":"2026-08-14T13:05:05.651477Z","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-10T21:34:10.679912Z"},"links":{"cited_paper":"/paper/1611.07476","citing_paper":"/paper/2501.06258"},"observation_digest":"sha256:6bdfb18d3aba8b14d0f857c7435ff6d8f2e71157c8471bd49e30d1189f220916","observation_id":"f7324a2b-ced8-4bde-962a-997d9fba396f","resolution":{"observed_at":"2026-08-10T21:34:10.679912Z","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":"2026-08-10T21:34:10.685210Z","title":"Understanding machine learning: From theory to algorithms","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2501.06258","last_updated":"2025-01-09T10:21:19Z","snapshot_observed_at":"2026-08-14T13:05:05.651477Z","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-10T21:34:10.685210Z"},"links":{"citing_paper":"/paper/2501.06258"},"observation_digest":"sha256:d44bf06aef1c475f41043d45eb9043214efbcfc3581a041afca90c0c9ed74069","observation_id":"85f461bc-fd2e-4bbb-9ad4-a76bf861c197","resolution":{"observed_at":"2026-08-10T21:34:10.685210Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"0912.3995","last_updated":"2010-06-09T23:24:13Z","snapshot_observed_at":"2026-08-15T05:30:44.958921Z","submitted_at":"2009-12-21T00:08:19Z","title":"Gaussian Process Optimization in the Bandit Setting: No Regret and Experimental Design","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"0912.3995","snapshot_observed_at":"2026-08-10T21:34:10.689747Z","title":"Gaussian process optimization in the bandit setting: No regret and experimental design","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2501.06258","last_updated":"2025-01-09T10:21:19Z","snapshot_observed_at":"2026-08-14T13:05:05.651477Z","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-10T21:34:10.689747Z"},"links":{"cited_paper":"/paper/0912.3995","citing_paper":"/paper/2501.06258"},"observation_digest":"sha256:9b266142989d287510111a61a2220ed3ea9420b08695ae1447f1b875a18cb142","observation_id":"ae8a0753-f82b-417a-86bd-6c51defefe32","resolution":{"observed_at":"2026-08-10T21:34:10.689747Z","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":"2026-08-10T21:34:10.876407Z","title":"The bitter lesson","venue":null,"work_id":"0718f8c9-e4da-487c-a13f-4db75c0e23a1","year":2019},"citing_paper":{"arxiv_id":"2501.06258","last_updated":"2025-01-09T10:21:19Z","snapshot_observed_at":"2026-08-14T13:05:05.651477Z","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-10T21:34:10.694899Z"},"links":{"citing_paper":"/paper/2501.06258"},"observation_digest":"sha256:d0b6e03271083115d98fa9c1ec1ef4c6baec9622ac60d3c9a825c2c85627dc1c","observation_id":"4592e48f-7b96-4825-8a54-45dfe2596925","resolution":{"observed_at":"2026-08-10T21:34:10.881596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+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":"2026-08-10T21:34:10.858975Z","title":"High-dimensional statistics: A non-asymptotic view- point, volume 48","venue":null,"work_id":"78533b27-c80c-42a2-93ac-9045c141529c","year":2019},"citing_paper":{"arxiv_id":"2501.06258","last_updated":"2025-01-09T10:21:19Z","snapshot_observed_at":"2026-08-14T13:05:05.651477Z","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-10T21:34:10.699704Z"},"links":{"citing_paper":"/paper/2501.06258"},"observation_digest":"sha256:58f1d0a2193ceef06190cb358d3e0bcf670340f863201a09db9f1df0193fb3a0","observation_id":"970c0128-82ef-447d-8c7d-97f1bc2dbd4b","resolution":{"observed_at":"2026-08-10T21:34:10.867341Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.01780","last_updated":"2020-12-03T09:17:55Z","snapshot_observed_at":"2026-08-16T19:01:19.319539Z","submitted_at":"2020-12-03T09:17:55Z","title":"Neural Contextual Bandits with Deep Representation and Shallow Exploration","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2012.01780","snapshot_observed_at":"2026-08-10T21:34:10.703817Z","title":"Neural con- textual bandits with deep representation and shallow exploration","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2501.06258","last_updated":"2025-01-09T10:21:19Z","snapshot_observed_at":"2026-08-14T13:05:05.651477Z","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-10T21:34:10.703817Z"},"links":{"cited_paper":"/paper/2012.01780","citing_paper":"/paper/2501.06258"},"observation_digest":"sha256:21bdca4585110f0015c331f508ecc99bc6148e1211652df2fe7a3ebeba1f58c9","observation_id":"235bd3e7-b4f3-481b-ba42-e3e768248ee0","resolution":{"observed_at":"2026-08-10T21:34:10.703817Z","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":"2026-08-10T21:34:10.842109Z","title":"Pyhessian: Neural networks through the lens of the hessian","venue":null,"work_id":"fed5ae86-8f58-4633-943e-577465a83def","year":2020},"citing_paper":{"arxiv_id":"2501.06258","last_updated":"2025-01-09T10:21:19Z","snapshot_observed_at":"2026-08-14T13:05:05.651477Z","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-10T21:34:10.708609Z"},"links":{"citing_paper":"/paper/2501.06258"},"observation_digest":"sha256:38be5c6080ae50494cdccbbceefc9a43d5316a3ee537a682134d17395b8e1986","observation_id":"f0ff7f27-7efa-4e50-9e1c-6f8a7bc39d7a","resolution":{"observed_at":"2026-08-10T21:34:10.849164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1901.00301","last_updated":"2019-06-21T19:25:56Z","snapshot_observed_at":"2026-08-17T03:05:34.104817Z","submitted_at":"2019-01-02T09:15:02Z","title":"Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1901.00301","snapshot_observed_at":"2026-08-10T21:34:10.712466Z","title":"Warm-starting contextual bandits: Robustly com- bining supervised and bandit feedback","venue":null,"work_id":null,"year":1901},"citing_paper":{"arxiv_id":"2501.06258","last_updated":"2025-01-09T10:21:19Z","snapshot_observed_at":"2026-08-14T13:05:05.651477Z","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-10T21:34:10.712466Z"},"links":{"cited_paper":"/paper/1901.00301","citing_paper":"/paper/2501.06258"},"observation_digest":"sha256:f98552d413c2b300f8aedf6b0937066aeab8e8855ca1cbbca89e9d6dfb18bd00","observation_id":"cc984855-21ad-4262-a47f-4472ed617441","resolution":{"observed_at":"2026-08-10T21:34:10.712466Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.00827","last_updated":"2021-12-30T09:21:04Z","snapshot_observed_at":"2026-08-16T19:16:23.498911Z","submitted_at":"2020-10-02T07:44:09Z","title":"Neural Thompson Sampling","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.00827","snapshot_observed_at":"2026-08-10T21:34:10.717235Z","title":"Neural thompson sampling","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2501.06258","last_updated":"2025-01-09T10:21:19Z","snapshot_observed_at":"2026-08-14T13:05:05.651477Z","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-10T21:34:10.717235Z"},"links":{"cited_paper":"/paper/2010.00827","citing_paper":"/paper/2501.06258"},"observation_digest":"sha256:cfafd3f539ccea91cb41d7db9696ccb93775cadbf9eeb3b72d3e109cdd97d659","observation_id":"09cc7512-7735-441c-826e-87fcabac08ca","resolution":{"observed_at":"2026-08-10T21:34:10.717235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2501.06258","last_updated":"2025-01-09T10:21:19Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T13:05:05.651477Z","submitted_at":"2025-01-09T10:21:19Z","title":"Contextual Bandit Optimization with Pre-Trained Neural Networks"},"reference_resolution":{"displayed":12,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":4},"total_outbound_references":12},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 0 inbound Pith citation observations for arXiv:2501.06258."}