{"as_of":"2026-08-10T05:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:84fd0f02609dfe800f972e2333cdd5f39cc97481111533fb1a8aad20d174895a","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":1,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":1,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T11:22:28.883218Z","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":"2026-08-09T11:22:29.383161Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2011.01928","last_updated":"2020-11-03T18:58:39Z","snapshot_observed_at":"2026-08-10T02:55:39.264386Z","submitted_at":"2020-11-03T18:58:39Z","title":"Generalization to New Actions in Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2011.01928","doi":null,"metadata_source":"pith","pith_arxiv_id":"2011.01928","snapshot_observed_at":"2026-08-09T11:22:29.383161Z","title":"Generalization to New Actions in Reinforcement Learning","venue":"cs.LG","work_id":"7b1c34aa-1704-498a-b792-a7f0ce7c4232","year":2020},"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":14,"source":"pdf_text","source_observed_at":"2026-08-09T11:22:28.883218Z"},"links":{"cited_paper":"/paper/2011.01928","citing_paper":"/paper/2502.02743"},"observation_digest":"sha256:7f97e4d7a1b7de139877bab3a8f0401f6c3f38d99089a4303ed8afe916fb580f","observation_id":"c8758b8f-16a6-4368-9ef1-576f4dbd4189","resolution":{"observed_at":"2026-08-09T11:22:29.388179Z","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/2011.01928/citation-record","integrity":"/paper/2011.01928/integrity","json":"/paper/2011.01928/citation-record.json","paper":"/paper/2011.01928"},"outbound":[],"paper":{"arxiv_id":"2011.01928","last_updated":"2020-11-03T18:58:39Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-10T02:55:39.264386Z","submitted_at":"2020-11-03T18:58:39Z","title":"Generalization to New Actions 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 10 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2011.01928."}