{"as_of":"2026-08-10T00:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4427ea509b31df722c9f9625df6d2f6ba6743c398a591e85efa7115b74b3bec0","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":"2026-08-09T06:31:02.800959+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":"2026-08-08T19:17:22.005131Z","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":"2026-08-06T21:17:42.981556Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2410.05782","last_updated":"2024-10-08T08:04:09Z","snapshot_observed_at":"2026-07-06T19:29:36.787126Z","submitted_at":"2024-10-08T08:04:09Z","title":"Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2410.05782","snapshot_observed_at":"2026-08-08T19:17:22.005131Z","title":"Reinforcement learning from imperfect corrective ac- tions and proxy rewards","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.06869","last_updated":"2025-02-08T05:30:31Z","snapshot_observed_at":"2026-08-08T19:12:44.055177Z","submitted_at":"2025-02-08T05:30:31Z","title":"A Survey on Explainable Deep Reinforcement Learning","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-08T19:17:22.005131Z"},"links":{"cited_paper":"/paper/2410.05782","citing_paper":"/paper/2502.06869"},"observation_digest":"sha256:3ad8a6d9554a5e042c98ad14a77a7502041b274e15a76ed76dadd70c0f80dedb","observation_id":"639bc1e6-02bb-4c76-aff6-82d189ed02b8","resolution":{"observed_at":"2026-08-08T19:17:22.005131Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2410.05782","last_updated":"2024-10-08T08:04:09Z","snapshot_observed_at":"2026-07-06T19:29:36.787126Z","submitted_at":"2024-10-08T08:04:09Z","title":"Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards","version":1},"cited_work":{"arxiv_id":"2410.05782","doi":null,"metadata_source":"pith","pith_arxiv_id":"2410.05782","snapshot_observed_at":"2026-08-06T21:17:42.981556Z","title":"Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards","venue":"cs.LG","work_id":"ea03a24b-51f9-4740-9b61-7bde114f133b","year":2024},"citing_paper":{"arxiv_id":"2507.00611","last_updated":"2025-07-01T09:43:57Z","snapshot_observed_at":"2026-08-06T21:08:39.566215Z","submitted_at":"2025-07-01T09:43:57Z","title":"Residual Reward Models for Preference-based Reinforcement Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-06T21:17:39.950999Z"},"links":{"cited_paper":"/paper/2410.05782","citing_paper":"/paper/2507.00611"},"observation_digest":"sha256:424d5cc0278ba4500dd6c48bf63fd329cbc4de88415633c14a6358602edec697","observation_id":"c1684f84-881d-48ea-aa18-f1427180e22b","resolution":{"observed_at":"2026-08-06T21:17:43.213962Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2410.05782/citation-record","integrity":"/paper/2410.05782/integrity","json":"/paper/2410.05782/citation-record.json","paper":"/paper/2410.05782"},"outbound":[],"paper":{"arxiv_id":"2410.05782","last_updated":"2024-10-08T08:04:09Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T19:29:36.787126Z","submitted_at":"2024-10-08T08:04:09Z","title":"Reinforcement Learning From Imperfect Corrective Actions And Proxy Rewards"},"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 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2410.05782."}