{"as_of":"2026-08-15T14:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0ffc2b5aa4ba99e73ff88ca234f990d8bb974e5742286e429aa32c13d10f24be","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":"2026-08-15T06:32:42.880941+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":"2026-08-11T12:40:45.571142Z","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":"2026-08-11T12:40:45.923824Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2102.11941","last_updated":"2023-09-21T14:36:25Z","snapshot_observed_at":"2026-08-13T20:09:37.006834Z","submitted_at":"2021-02-23T21:07:35Z","title":"State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards","version":2},"cited_work":{"arxiv_id":"2102.11941","doi":null,"metadata_source":"pith","pith_arxiv_id":"2102.11941","snapshot_observed_at":"2026-08-11T12:40:45.923824Z","title":"State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards","venue":"cs.LG","work_id":"439809a0-a9f7-4e51-b16d-587edbbcb24b","year":2021},"citing_paper":{"arxiv_id":"2412.14002","last_updated":"2024-12-18T16:17:25Z","snapshot_observed_at":"2026-08-14T22:23:08.376654Z","submitted_at":"2024-12-18T16:17:25Z","title":"Operator Splitting for Convex Constrained Markov Decision Processes","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-11T12:40:45.571142Z"},"links":{"cited_paper":"/paper/2102.11941","citing_paper":"/paper/2412.14002"},"observation_digest":"sha256:b0bbd7799075bca2a95383da505cb6e1d6dad0c26b98ed5cc2f2ae674e75733d","observation_id":"e5e4fd73-681f-4d25-8067-da8a5f2ce359","resolution":{"observed_at":"2026-08-11T12:40:45.928287Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-15T06:32:42.880941+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2102.11941","last_updated":"2023-09-21T14:36:25Z","snapshot_observed_at":"2026-08-13T20:09:37.006834Z","submitted_at":"2021-02-23T21:07:35Z","title":"State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with Rewards","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.11941","snapshot_observed_at":"2026-08-01T15:24:38.191162Z","title":"State augmented constrained reinforcement learning: Overcoming the limitations of learning with rewards,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.18480","last_updated":"2026-07-20T19:57:38Z","snapshot_observed_at":"2026-08-15T12:12:25.011557Z","submitted_at":"2026-07-20T19:57:38Z","title":"Long-Horizon Wireless Link Scheduling with State-Augmented Graph Neural Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T15:24:38.191162Z"},"links":{"cited_paper":"/paper/2102.11941","citing_paper":"/paper/2607.18480"},"observation_digest":"sha256:55544be36311ff785b5e10161448a5fd762068258c61c9d03ddf2c4ee6f7b562","observation_id":"a55c1d69-749e-47e5-ad55-d77e4a5d6366","resolution":{"observed_at":"2026-08-01T15:24:38.191162Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2102.11941/citation-record","integrity":"/paper/2102.11941/integrity","json":"/paper/2102.11941/citation-record.json","paper":"/paper/2102.11941"},"outbound":[],"paper":{"arxiv_id":"2102.11941","last_updated":"2023-09-21T14:36:25Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T20:09:37.006834Z","submitted_at":"2021-02-23T21:07:35Z","title":"State Augmented Constrained Reinforcement Learning: Overcoming the Limitations of Learning with 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":"2026-08-15T06:32:42.880941+00:00","source":"crossref"},{"observed_at":"2026-08-15T06:32:39.529945+00:00","source":"retraction_watch"}],"thesis":"As of 15 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2102.11941."}