{"as_of":"2026-08-10T11:20:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:05d398d1978d4d054c83967f17bf05abbf025add39d9b6ffccc35919e0a8f3a1","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T11:22:28.994652Z","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":"2026-08-05T13:46:03.418101Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.15587","last_updated":"2021-12-03T05:40:31Z","snapshot_observed_at":"2026-08-06T22:06:23.346843Z","submitted_at":"2021-06-29T17:21:59Z","title":"Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.15587","snapshot_observed_at":"2026-08-09T11:22:28.994652Z","title":"and Guo, Y","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02743","last_updated":"2025-02-04T22:09:43Z","snapshot_observed_at":"2026-08-09T16:32:54.357740Z","submitted_at":"2025-02-04T22:09:43Z","title":"LLM Bandit: Cost-Efficient LLM Generation via Preference-Conditioned Dynamic Routing","version":1},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-09T11:22:28.994652Z"},"links":{"cited_paper":"/paper/2106.15587","citing_paper":"/paper/2502.02743"},"observation_digest":"sha256:967df411d2a9c6d30800a1433b26cc6c6433cfb4db590601466e35a29d138f91","observation_id":"9050406b-4c85-4912-ab30-6fd5499245ce","resolution":{"observed_at":"2026-08-09T11:22:28.994652Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.15587","last_updated":"2021-12-03T05:40:31Z","snapshot_observed_at":"2026-08-06T22:06:23.346843Z","submitted_at":"2021-06-29T17:21:59Z","title":"Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation","version":2},"cited_work":{"arxiv_id":"2106.15587","doi":null,"metadata_source":"pith","pith_arxiv_id":"2106.15587","snapshot_observed_at":"2026-08-05T13:46:03.418101Z","title":"Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation","venue":"cs.LG","work_id":"058ba179-e4d4-4fc8-8ab7-47d2ca744f90","year":2021},"citing_paper":{"arxiv_id":"2509.00347","last_updated":"2025-08-30T04:02:33Z","snapshot_observed_at":"2026-08-09T19:57:10.685641Z","submitted_at":"2025-08-30T04:02:33Z","title":"LLM-Driven Policy Diffusion: Enhancing Generalization in Offline Reinforcement Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T13:46:03.192637Z"},"links":{"cited_paper":"/paper/2106.15587","citing_paper":"/paper/2509.00347"},"observation_digest":"sha256:91eb050079ac155107aaa644b7351fefbfb3a6e163849c3e4041f1628c04955e","observation_id":"ea991915-d6c7-4e22-a76d-27ddd1176e20","resolution":{"observed_at":"2026-08-05T13:46:03.459519Z","resolver_source":"local_arxiv","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/2106.15587/citation-record","integrity":"/paper/2106.15587/integrity","json":"/paper/2106.15587/citation-record.json","paper":"/paper/2106.15587"},"outbound":[],"paper":{"arxiv_id":"2106.15587","last_updated":"2021-12-03T05:40:31Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T22:06:23.346843Z","submitted_at":"2021-06-29T17:21:59Z","title":"Generalization of Reinforcement Learning with Policy-Aware Adversarial Data Augmentation"},"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 2 inbound Pith citation observations for arXiv:2106.15587."}