{"as_of":"2026-08-09T16:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:33d3872c40ed8ab71062558f9bbae112e6b37cb22a0f241c028b1f464b4823b1","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"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":"2026-08-08T18:56:45.449121Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-19T09:04:53.161564Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"1912.02975","last_updated":"2019-12-28T04:04:43Z","snapshot_observed_at":"2026-07-06T08:42:30.413190Z","submitted_at":"2019-12-06T04:52:16Z","title":"Observational Overfitting in Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"1912.02975","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1912.02975","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Observational overfitting in reinforcement learning","venue":null,"work_id":"98c2db38-56e8-4f0e-9e1f-b80f6889daaa","year":1912},"citing_paper":{"arxiv_id":"2210.10760","last_updated":"2022-10-19T17:56:10Z","snapshot_observed_at":"2026-07-06T14:07:50.468967Z","submitted_at":"2022-10-19T17:56:10Z","title":"Scaling Laws for Reward Model Overoptimization","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-19T09:04:53.129737Z"},"links":{"cited_paper":"/paper/1912.02975","citing_paper":"/paper/2210.10760"},"observation_digest":"sha256:815ef0f58bd0bdee74b976f0018132a499306d2af3f673702dfac9732cd069e7","observation_id":"284a3bc7-1a9a-4435-ad07-f8998e363950","resolution":{"observed_at":"2026-05-19T09:04:53.169579Z","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":"1912.02975","last_updated":"2019-12-28T04:04:43Z","snapshot_observed_at":"2026-07-06T08:42:30.413190Z","submitted_at":"2019-12-06T04:52:16Z","title":"Observational Overfitting in Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.02975","snapshot_observed_at":"2026-08-08T18:56:45.449121Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.05555","last_updated":"2025-02-08T12:57:02Z","snapshot_observed_at":"2026-08-08T18:50:00.725926Z","submitted_at":"2025-02-08T12:57:02Z","title":"Efficient Reinforcement Learning Through Adaptively Pretrained Visual Encoder","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-08T18:56:45.449121Z"},"links":{"cited_paper":"/paper/1912.02975","citing_paper":"/paper/2502.05555"},"observation_digest":"sha256:88244c496cdce81c20881b805553a765443d7bf2e2919229b6a5f10f955554e8","observation_id":"09bcc3e7-ed47-4f63-a2b8-bc4aa3f068e4","resolution":{"observed_at":"2026-08-08T18:56:45.449121Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.02975","last_updated":"2019-12-28T04:04:43Z","snapshot_observed_at":"2026-07-06T08:42:30.413190Z","submitted_at":"2019-12-06T04:52:16Z","title":"Observational Overfitting in Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.02975","snapshot_observed_at":"2026-08-08T13:18:55.479689Z","title":", Jiang, Y","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.07280","last_updated":"2025-02-11T05:54:42Z","snapshot_observed_at":"2026-08-09T01:46:47.043866Z","submitted_at":"2025-02-11T05:54:42Z","title":"MIGT: Memory Instance Gated Transformer Framework for Financial Portfolio Management","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-08T13:18:55.479689Z"},"links":{"cited_paper":"/paper/1912.02975","citing_paper":"/paper/2502.07280"},"observation_digest":"sha256:621c70f8d0ea6a34a4de9398ec6f17f2a94f0dadbdc27a840809c71f08d0f812","observation_id":"e560523d-9194-440e-ad02-47776012ee6c","resolution":{"observed_at":"2026-08-08T13:18:55.479689Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.02975","last_updated":"2019-12-28T04:04:43Z","snapshot_observed_at":"2026-07-06T08:42:30.413190Z","submitted_at":"2019-12-06T04:52:16Z","title":"Observational Overfitting in Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1912.02975","snapshot_observed_at":"2026-08-06T17:05:16.229659Z","title":"Observational overfitting in reinforcement learning,","venue":null,"work_id":null,"year":1912},"citing_paper":{"arxiv_id":"2507.11975","last_updated":"2025-07-16T07:17:41Z","snapshot_observed_at":"2026-08-09T09:50:47.034393Z","submitted_at":"2025-07-16T07:17:41Z","title":"Online Training and Pruning of Deep Reinforcement Learning Networks","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-06T17:05:16.229659Z"},"links":{"cited_paper":"/paper/1912.02975","citing_paper":"/paper/2507.11975"},"observation_digest":"sha256:fdf420c67ffecac29994774e8ce4e24a368a347ed0358f16dbf9261c5c6eec1c","observation_id":"f0db245f-0116-47fc-b940-4fb12dc81a83","resolution":{"observed_at":"2026-08-06T17:05:16.229659Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/1912.02975/citation-record","integrity":"/paper/1912.02975/integrity","json":"/paper/1912.02975/citation-record.json","paper":"/paper/1912.02975"},"outbound":[],"paper":{"arxiv_id":"1912.02975","last_updated":"2019-12-28T04:04:43Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T08:42:30.413190Z","submitted_at":"2019-12-06T04:52:16Z","title":"Observational Overfitting in Reinforcement Learning"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"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 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:1912.02975."}