{"as_of":"2026-08-10T15:16:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b62dbe7d003875625d68da4b807ebabe5309c5ab7856ee1d02f45f5c00fb83ee","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":3,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":3,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T19:28:38.116055Z","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":"2026-07-04T08:59:43.297294Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2101.09207","last_updated":"2021-03-09T08:44:43Z","snapshot_observed_at":"2026-08-09T07:05:33.477963Z","submitted_at":"2021-01-22T16:52:06Z","title":"Differentiable Trust Region Layers for Deep Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2101.09207","snapshot_observed_at":"2026-08-05T19:28:38.116055Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.12518","last_updated":"2025-08-17T22:51:27Z","snapshot_observed_at":"2026-08-09T11:34:43.360867Z","submitted_at":"2025-08-17T22:51:27Z","title":"Towards Adaptive External Communication in Autonomous Vehicles: A Conceptual Design Framework","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-05T19:28:38.116055Z"},"links":{"cited_paper":"/paper/2101.09207","citing_paper":"/paper/2508.12518"},"observation_digest":"sha256:34dd8e53d3082a1e70f40f352741552717cee0544b38d88dc4a56ed15a5e867d","observation_id":"f3804849-ec23-43d0-a701-e0234c9a40b2","resolution":{"observed_at":"2026-08-05T19:28:38.116055Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2101.09207","last_updated":"2021-03-09T08:44:43Z","snapshot_observed_at":"2026-08-09T07:05:33.477963Z","submitted_at":"2021-01-22T16:52:06Z","title":"Differentiable Trust Region Layers for Deep Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2101.09207","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.09207","snapshot_observed_at":"2026-07-04T08:59:43.297294Z","title":"Differentiable trust region layers for deep reinforcement learning.arXiv preprint arXiv:2101.09207, 2021","venue":null,"work_id":"713a3af1-a46b-4538-91c9-e1614f7328cb","year":2021},"citing_paper":{"arxiv_id":"2605.26784","last_updated":"2026-05-26T09:53:42Z","snapshot_observed_at":"2026-08-06T13:00:03.980604Z","submitted_at":"2026-05-26T09:53:42Z","title":"Ratio-Variance Regularized Policy Optimization","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-29T19:44:02.317303Z"},"links":{"cited_paper":"/paper/2101.09207","citing_paper":"/paper/2605.26784"},"observation_digest":"sha256:e86735218ae053fc21eea40da9a155fd2c051006425185619bd407b03b0a7960","observation_id":"d4d5ce8c-2441-4c57-ac10-1e8ddc904bb4","resolution":{"observed_at":"2026-06-29T19:53:55.990855Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2101.09207","last_updated":"2021-03-09T08:44:43Z","snapshot_observed_at":"2026-08-09T07:05:33.477963Z","submitted_at":"2021-01-22T16:52:06Z","title":"Differentiable Trust Region Layers for Deep Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2101.09207","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2101.09207","snapshot_observed_at":"2026-07-04T08:59:43.297294Z","title":"Differentiable trust region layers for deep reinforcement learning.arXiv preprint arXiv:2101.09207, 2021","venue":null,"work_id":"713a3af1-a46b-4538-91c9-e1614f7328cb","year":2021},"citing_paper":{"arxiv_id":"2606.22630","last_updated":"2026-06-21T18:32:25Z","snapshot_observed_at":"2026-08-01T19:14:01.648100Z","submitted_at":"2026-06-21T18:32:25Z","title":"Scalable Maximum Entropy Reinforcement Learning for Diffusion Policies via Adjoint Matching","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-06-26T10:38:05.185415Z"},"links":{"cited_paper":"/paper/2101.09207","citing_paper":"/paper/2606.22630"},"observation_digest":"sha256:400c09a0e6ba3eb747b825680c356959acf72d9fb3f563498871d0d4dee0f67c","observation_id":"02cad5d6-48f2-4a5b-90f2-c430c8be6b71","resolution":{"observed_at":"2026-07-04T08:59:43.299493Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2101.09207/citation-record","integrity":"/paper/2101.09207/integrity","json":"/paper/2101.09207/citation-record.json","paper":"/paper/2101.09207"},"outbound":[],"paper":{"arxiv_id":"2101.09207","last_updated":"2021-03-09T08:44:43Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T07:05:33.477963Z","submitted_at":"2021-01-22T16:52:06Z","title":"Differentiable Trust Region Layers for Deep 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":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2101.09207."}