{"as_of":"2026-08-10T04:37:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:62d886a13f4949149bddb1015d15178e98b23f0ec439cae0d4b2da1326b465ea","coverage":[{"denominator":18,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":18,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T23:03:08.444115Z","state":"measured"},{"denominator":22,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":22,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T08:11:22.973978Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-07-04T07:29:39.501657Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"cited_work":{"arxiv_id":"2602.15136","doi":null,"metadata_source":"pith","pith_arxiv_id":"2602.15136","snapshot_observed_at":"2026-07-04T07:29:39.501657Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","venue":"stat.ML","work_id":"9a0eb49a-be86-478f-8648-5892b335e9cb","year":2026},"citing_paper":{"arxiv_id":"2605.03594","last_updated":"2026-05-05T10:14:30Z","snapshot_observed_at":"2026-08-02T08:39:14.137601Z","submitted_at":"2026-05-05T10:14:30Z","title":"Poisson Empirical Bayes via Gamma-Smoothed Nonparametric Maximum Likelihood","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-07T13:05:12.702912Z"},"links":{"cited_paper":"/paper/2602.15136","citing_paper":"/paper/2605.03594"},"observation_digest":"sha256:d7468745de2df8c38a376430684e87f8a9d84f07268cacecfd27c3c93eaf55ed","observation_id":"b38e7a3f-4f5c-4c5c-8d67-82ee49757578","resolution":{"observed_at":"2026-06-23T04:13:44.680708Z","resolver_source":"arxiv_id","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":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"cited_work":{"arxiv_id":"2602.15136","doi":null,"metadata_source":"pith","pith_arxiv_id":"2602.15136","snapshot_observed_at":"2026-07-04T07:29:39.501657Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","venue":"stat.ML","work_id":"9a0eb49a-be86-478f-8648-5892b335e9cb","year":2026},"citing_paper":{"arxiv_id":"2606.21707","last_updated":"2026-06-19T19:40:05Z","snapshot_observed_at":"2026-08-06T18:38:51.770777Z","submitted_at":"2026-06-19T19:40:05Z","title":"Quasi-Bayes empirical Bayes estimation of sums of random variables","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-06-26T13:20:45.010423Z"},"links":{"cited_paper":"/paper/2602.15136","citing_paper":"/paper/2606.21707"},"observation_digest":"sha256:3d15946c83f19a437b3771ec141b4f1213b1f201fa6e6719e4c3d39ee3d46454","observation_id":"c65408e3-04fd-4eff-b380-6f72ef23c624","resolution":{"observed_at":"2026-07-04T07:29:39.502857Z","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":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"cited_work":{"arxiv_id":"2602.15136","doi":null,"metadata_source":"pith","pith_arxiv_id":"2602.15136","snapshot_observed_at":"2026-07-04T07:29:39.501657Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","venue":"stat.ML","work_id":"9a0eb49a-be86-478f-8648-5892b335e9cb","year":2026},"citing_paper":{"arxiv_id":"2607.02340","last_updated":"2026-07-03T04:13:35Z","snapshot_observed_at":"2026-08-03T04:49:28.372018Z","submitted_at":"2026-07-02T15:48:05Z","title":"Merging of Bayes and quasi-Bayes empirical Bayes procedures for Poisson compound decisions","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-07-03T07:26:33.849829Z"},"links":{"cited_paper":"/paper/2602.15136","citing_paper":"/paper/2607.02340"},"observation_digest":"sha256:fdef976d1247c155e00536966d07f2f6cf1dfcbd02abea4587eda64c399408ef","observation_id":"15574225-b30d-405b-bfa2-557de0928b01","resolution":{"observed_at":"2026-07-03T07:27:43.815530Z","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":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2602.15136","snapshot_observed_at":"2026-07-12T08:11:22.973978Z","title":"and Polyanskiy, Y","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.02340","last_updated":"2026-07-03T04:13:35Z","snapshot_observed_at":"2026-08-03T04:49:28.372018Z","submitted_at":"2026-07-02T15:48:05Z","title":"Merging of Bayes and quasi-Bayes empirical Bayes procedures for Poisson compound decisions","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-07-12T08:11:22.973978Z"},"links":{"cited_paper":"/paper/2602.15136","citing_paper":"/paper/2607.02340"},"observation_digest":"sha256:93c36d3ab47e1c6d2f440c6fd0c8b8d9b852cb7ef3b61a4f7a638887c7808ff8","observation_id":"6f4ae3e3-b7a3-48ca-a65c-baa965533e0e","resolution":{"observed_at":"2026-07-12T08:11:22.973978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2602.15136/citation-record","integrity":"/paper/2602.15136/integrity","json":"/paper/2602.15136/citation-record.json","paper":"/paper/2602.15136"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2512.22471","last_updated":"2026-05-16T15:25:03Z","snapshot_observed_at":"2026-08-07T00:58:48.915042Z","submitted_at":"2025-12-27T05:28:58Z","title":"The Bayesian Geometry of Transformer Attention","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2512.22471","snapshot_observed_at":"2026-08-02T23:03:05.909471Z","title":"The Bayesian geometry of transformer attention.arXiv preprint arXiv:2512.22471,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:05.909471Z"},"links":{"cited_paper":"/paper/2512.22471","citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:9acd916133e14f3d5f2b7478b7896c02326091d37ab7a84c964e89607c9b7d0e","observation_id":"cec5dd0b-0e82-4dda-bca9-7e1f2963e353","resolution":{"observed_at":"2026-08-02T23:03:05.909471Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.02547","last_updated":"2025-07-08T16:32:46Z","snapshot_observed_at":"2026-07-06T20:16:44.607678Z","submitted_at":"2025-01-05T13:56:51Z","title":"Transformers Simulate MLE for Sequence Generation in Bayesian Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.02547","snapshot_observed_at":"2026-08-02T23:03:06.220395Z","title":"Trans- formers Simulate MLE for Sequence Generation in Bayesian Networks.arXiv preprint arXiv:2501.02547,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:06.220395Z"},"links":{"cited_paper":"/paper/2501.02547","citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:8ec12e9f69028336f3e0951d0ed0247f283de68263b5a74115f8806b8d8b97c3","observation_id":"2d3171b4-363e-4e75-b8f9-dbcce074e9e7","resolution":{"observed_at":"2026-08-02T23:03:06.220395Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.11430","last_updated":"2020-06-19T22:49:42Z","snapshot_observed_at":"2026-08-08T05:05:00.916427Z","submitted_at":"2020-06-19T22:49:42Z","title":"Learning Minimax Estimators via Online Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.11430","snapshot_observed_at":"2026-08-02T23:03:06.643921Z","title":"Learning minimax estimators via online learning.arXiv preprint arXiv:2006.11430,","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:06.643921Z"},"links":{"cited_paper":"/paper/2006.11430","citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:320c1e50b3cb50a712b0731148fd82747376a15d0e429013b40c39116156efd5","observation_id":"485328a3-3341-4ab0-80cf-a47d3d521e82","resolution":{"observed_at":"2026-08-02T23:03:06.643921Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2509.07355","last_updated":"2025-09-09T03:04:06Z","snapshot_observed_at":"2026-08-09T23:02:11.344249Z","submitted_at":"2025-09-09T03:04:06Z","title":"Besting Good--Turing: Optimality of Non-Parametric Maximum Likelihood for Distribution Estimation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2509.07355","snapshot_observed_at":"2026-08-02T23:03:06.816797Z","title":"Besting Good– Turing: Optimality of Non-Parametric Maximum Likelihood for Distribution Esti- mation.arXiv preprint arXiv:2509.07355,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:06.816797Z"},"links":{"cited_paper":"/paper/2509.07355","citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:3c7ad2acaa112e9caefa2379b4a3df31d52a828d1ab496955ed49ba529518793","observation_id":"41e686a6-1e97-4c6e-8216-d55b19cd35b3","resolution":{"observed_at":"2026-08-02T23:03:06.816797Z","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":"2026-08-02T23:03:07.071159Z","title":"Quantitative bounds for length generalization in transformers.arXiv preprint arXiv:2510.27015,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:07.071159Z"},"links":{"citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:5f506ccac7a4fd18093ef5f185f12983b3f0184beaaffb37a6f7764e2142e248","observation_id":"5cfa8f86-9323-4689-b09b-b5ce04028d79","resolution":{"observed_at":"2026-08-02T23:03:07.071159Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.11617","last_updated":"2025-02-17T10:00:24Z","snapshot_observed_at":"2026-08-07T18:13:08.730050Z","submitted_at":"2025-02-17T10:00:24Z","title":"In-Context Parametric Inference: Point or Distribution Estimators?","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.11617","snapshot_observed_at":"2026-08-02T23:03:07.624315Z","title":"In- context parametric inference: Point or distribution estimators?arXiv preprint arXiv:2502.11617,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:07.624315Z"},"links":{"cited_paper":"/paper/2502.11617","citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:735cf6d42f1c269c87f4f325354bf77a1247d8a7601a95ca93d801125dc4a407","observation_id":"01b34881-3ecb-43d1-a0b5-a489f283bc81","resolution":{"observed_at":"2026-08-02T23:03:07.624315Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.10040","last_updated":"2019-04-02T14:17:40Z","snapshot_observed_at":"2026-08-03T12:17:10.040125Z","submitted_at":"2019-04-02T14:17:40Z","title":"A Survey on Practical Applications of Multi-Armed and Contextual Bandits","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.10040","snapshot_observed_at":"2026-08-02T23:03:08.024947Z","title":null,"venue":null,"work_id":null,"year":1904},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:08.024947Z"},"links":{"cited_paper":"/paper/1904.10040","citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:6a36c3142035e71c5ec08a4417a7b2ef7c9be8bcd1bf59047b137bab0a769a9f","observation_id":"07be77e3-042a-4b05-8294-d6fdb14f4cb5","resolution":{"observed_at":"2026-08-02T23:03:08.024947Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.09844","last_updated":"2025-05-28T00:52:33Z","snapshot_observed_at":"2026-08-09T11:39:39.690395Z","submitted_at":"2025-02-14T01:06:15Z","title":"Solving Empirical Bayes via Transformers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.09844","snapshot_observed_at":"2026-08-02T23:03:08.310761Z","title":"Solving empirical Bayes via trans- formers.arXiv preprint arXiv:2502.09844,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:08.310761Z"},"links":{"cited_paper":"/paper/2502.09844","citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:587a0c110b46279a951f8fac75d6d14f53c13525d87daddbcbacd67a3a34dd4b","observation_id":"183c3e76-4545-4b7e-8023-05f90ca6f11c","resolution":{"observed_at":"2026-08-02T23:03:08.310761Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09371","last_updated":"2024-02-14T18:18:29Z","snapshot_observed_at":"2026-08-06T06:01:35.329783Z","submitted_at":"2024-02-14T18:18:29Z","title":"Transformers Can Achieve Length Generalization But Not Robustly","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09371","snapshot_observed_at":"2026-08-02T23:03:08.444115Z","title":"Transformers can achieve length generalization but not robustly.arXiv preprint arXiv:2402.09371,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:08.444115Z"},"links":{"cited_paper":"/paper/2402.09371","citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:b268780f890ddd5e6d6fc0b9876ddd49dda50486963c3d8641352c9fde16c5da","observation_id":"c4ef6ee2-10e3-43c1-949f-70ce9c48904c","resolution":{"observed_at":"2026-08-02T23:03:08.444115Z","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":"2026-08-02T23:03:06.369815Z","title":"Epsilon-Minimax Solutions of Statistical Decision Problems","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":1953,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:06.369815Z"},"links":{"citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:508b49f43547cab84f1e572e8adffb45389348f7140ab35dbc077ab8bdc9c891","observation_id":"0d5c3fa0-5b79-42b6-8139-3d4bdd79dfa1","resolution":{"observed_at":"2026-08-02T23:03:06.369815Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2211.12692","last_updated":"2024-11-19T20:38:18Z","snapshot_observed_at":"2026-08-05T22:27:07.750044Z","submitted_at":"2022-11-23T04:01:53Z","title":"Empirical Bayes estimation: When does $g$-modeling beat $f$-modeling in theory (and in practice)?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2211.12692","snapshot_observed_at":"2026-08-02T23:03:08.164630Z","title":"Empirical Bayes estimation: When doesg-modeling beatf-modeling in theory (and in practice)?arXiv preprint arXiv:2211.12692,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":1956,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:08.164630Z"},"links":{"cited_paper":"/paper/2211.12692","citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:baae46f0055195d2200ba3957fcc7f7ac78031aff227f0732b54815a41e0c032","observation_id":"7a597387-113c-4d05-9e05-c8a2d645c337","resolution":{"observed_at":"2026-08-02T23:03:08.164630Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.06601","last_updated":"2025-02-10T16:00:48Z","snapshot_observed_at":"2026-08-10T01:04:26.706666Z","submitted_at":"2025-02-10T16:00:48Z","title":"Amortized In-Context Bayesian Posterior Estimation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.06601","snapshot_observed_at":"2026-08-02T23:03:07.460954Z","title":"Amortized in-context bayesian posterior estimation.arXiv preprint arXiv:2502.06601,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":1983,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:07.460954Z"},"links":{"cited_paper":"/paper/2502.06601","citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:a8dd0674537b9841df63ba60335c97d6021841649ee7f22138a63df072662a43","observation_id":"c28667f3-3f74-434c-af89-fc9671160027","resolution":{"observed_at":"2026-08-02T23:03:07.460954Z","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":"2026-08-02T23:03:06.535334Z","title":"Stein’s unbi- ased risk estimate and Hyvärinen’s score matching.arXiv preprint arXiv:2502.20123,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":2000,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:06.535334Z"},"links":{"citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:68c9a28e93235b982990d193808ecad5a142496e79ee054c369283067ac4cd64","observation_id":"f3e7988d-7af3-472c-a999-b05d5ba32eb3","resolution":{"observed_at":"2026-08-02T23:03:06.535334Z","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":"2026-08-02T23:03:07.304497Z","title":"Function estimation in the empirical Bayes setting.arXiv preprint arXiv:2601.18689,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:07.304497Z"},"links":{"citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:470e99477f0e4a371b6c5672a6d5ceeac1b44fbf34c2342d857e8f7f0a295acb","observation_id":"95a593ce-3f77-479b-9243-6de8f11be344","resolution":{"observed_at":"2026-08-02T23:03:07.304497Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2205.00336","last_updated":"2023-05-29T04:21:54Z","snapshot_observed_at":"2026-07-06T13:05:26.571347Z","submitted_at":"2022-04-30T19:56:16Z","title":"A nonparametric regression alternative to empirical Bayes approaches to simultaneous estimation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2205.00336","snapshot_observed_at":"2026-08-02T23:03:06.117103Z","title":"A nonparametric regression alterna- tive to empirical bayes approaches to simultaneous estimation.arXiv preprint arXiv:2205.00336,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:06.117103Z"},"links":{"cited_paper":"/paper/2205.00336","citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:273f8ca7e5b9c018eb660bba22845b863c7e9b3882791836954b273d2d44c676","observation_id":"84190108-801a-44ec-8ad8-569f8aed154f","resolution":{"observed_at":"2026-08-02T23:03:06.117103Z","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":"2026-08-02T23:03:07.717405Z","title":"Tabdpt: Scaling tabular foundation models.arXiv preprint arXiv:2410.18164,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:07.717405Z"},"links":{"citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:eef5ff6d8d2dbb50d34162131f800282aebe8a22a60a208f2f52d3cb32d741e2","observation_id":"91dfd19f-eea4-4b61-83de-cfcdca62cc8b","resolution":{"observed_at":"2026-08-02T23:03:07.717405Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2109.03943","last_updated":"2021-09-10T15:25:37Z","snapshot_observed_at":"2026-08-07T04:46:54.471150Z","submitted_at":"2021-09-08T21:34:47Z","title":"Sharp regret bounds for empirical Bayes and compound decision problems","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2109.03943","snapshot_observed_at":"2026-08-02T23:03:07.847887Z","title":"Sharp regret bounds for empirical Bayes and com- pound decision problems.arXiv preprint arXiv:2109.03943,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:07.847887Z"},"links":{"cited_paper":"/paper/2109.03943","citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:a049228b6d4c6c177a2f2ec9910fc45742b1f3e55253a65ee897fd9db4d649da","observation_id":"32aade56-2c37-4dd6-aa31-ba09d2b5c564","resolution":{"observed_at":"2026-08-02T23:03:07.847887Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04875","last_updated":"2025-05-28T11:19:25Z","snapshot_observed_at":"2026-07-06T17:26:51.461337Z","submitted_at":"2024-02-07T14:16:28Z","title":"On Provable Length and Compositional Generalization","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.04875","snapshot_observed_at":"2026-08-02T23:03:06.012233Z","title":"On provable length and compositional generaliza- tion.arXiv preprint arXiv:2402.04875,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-02T23:03:06.012233Z"},"links":{"cited_paper":"/paper/2402.04875","citing_paper":"/paper/2602.15136"},"observation_digest":"sha256:61daa161e74709a65a6aca685d56c5807ba4581a0c7ef7ab6e3c8bfff29eaf3a","observation_id":"8226d218-d160-4205-96fe-8239edb51c8b","resolution":{"observed_at":"2026-08-02T23:03:06.012233Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2602.15136","last_updated":"2026-06-22T12:21:25Z","latest_version":2,"primary_category":"stat.ML","snapshot_observed_at":"2026-08-03T05:55:36.234632Z","submitted_at":"2026-02-16T19:29:27Z","title":"Universal priors: solving empirical Bayes via Bayesian inference and pretraining"},"reference_resolution":{"displayed":18,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":18},"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 10 August 2026, this Paper Citation Record lists 18 of 18 outbound references and 4 inbound Pith citation observations for arXiv:2602.15136."}