{"as_of":"2026-08-07T19:47:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:514510c9e22e9f8624a0383f91cae0fd266d0dfd8c86c7383b39a443b8bef8f2","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":"2026-08-07T06:34:17.273281+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":"2026-08-07T00:25:19.493021Z","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":"2026-05-21T05:33:58.556671Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2401.14758","last_updated":"2024-04-15T13:44:11Z","snapshot_observed_at":"2026-07-06T17:20:49.161755Z","submitted_at":"2024-01-26T10:33:38Z","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2401.14758","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.14758","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dsrl: Benchmarking safe offline reinforce- ment learning with diverse safety requirements","venue":null,"work_id":"36f4b1f3-0cce-4bec-8413-509242680a26","year":2024},"citing_paper":{"arxiv_id":"2602.02924","last_updated":"2026-05-05T18:05:36Z","snapshot_observed_at":"2026-07-06T22:44:14.347235Z","submitted_at":"2026-02-02T23:53:53Z","title":"How Does the Lagrangian Guide Safe Reinforcement Learning through Diffusion Models?","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-16T07:55:31.706717Z"},"links":{"cited_paper":"/paper/2401.14758","citing_paper":"/paper/2602.02924"},"observation_digest":"sha256:4fb3d4fdb62bc24750fc8fe898b4df49216c5ee9743d7d527aee8615c1f3c89f","observation_id":"9d0ad8ed-6e32-4fcb-b826-9748be050b13","resolution":{"observed_at":"2026-05-16T07:57:33.119515Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14758","last_updated":"2024-04-15T13:44:11Z","snapshot_observed_at":"2026-07-06T17:20:49.161755Z","submitted_at":"2024-01-26T10:33:38Z","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2401.14758","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2401.14758","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Dsrl: Benchmarking safe offline reinforce- ment learning with diverse safety requirements","venue":null,"work_id":"36f4b1f3-0cce-4bec-8413-509242680a26","year":2024},"citing_paper":{"arxiv_id":"2605.21225","last_updated":"2026-05-20T14:19:45Z","snapshot_observed_at":"2026-08-02T07:24:19.595402Z","submitted_at":"2026-05-20T14:19:45Z","title":"PREFINE: Preference-Based Implicit Reward and Cost Fine-Tuning for Safety Alignment","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-21T05:32:04.237084Z"},"links":{"cited_paper":"/paper/2401.14758","citing_paper":"/paper/2605.21225"},"observation_digest":"sha256:a5a590f9329b2f33fe632720c382212f2a6614fdbcec1087af04986b61f6b10e","observation_id":"0e68b6d8-03f4-484f-b19c-15736431ce3b","resolution":{"observed_at":"2026-05-21T05:33:58.558598Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2401.14758","last_updated":"2024-04-15T13:44:11Z","snapshot_observed_at":"2026-07-06T17:20:49.161755Z","submitted_at":"2024-01-26T10:33:38Z","title":"Off-Policy Primal-Dual Safe Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2401.14758","snapshot_observed_at":"2026-08-07T00:25:19.493021Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.04421","last_updated":"2026-08-05T04:04:07Z","snapshot_observed_at":"2026-08-07T19:19:19.046192Z","submitted_at":"2026-08-05T04:04:07Z","title":"Generative Optimization for Incentivized Advertising with Global Level Constraints","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T00:25:19.493021Z"},"links":{"cited_paper":"/paper/2401.14758","citing_paper":"/paper/2608.04421"},"observation_digest":"sha256:3921a9187cbd28b6c234e929055c804c85efef9900695e13b1edbeb389952aba","observation_id":"c904069d-959b-43c8-b140-762f8fd1ab42","resolution":{"observed_at":"2026-08-07T00:25:19.493021Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2401.14758/citation-record","integrity":"/paper/2401.14758/integrity","json":"/paper/2401.14758/citation-record.json","paper":"/paper/2401.14758"},"outbound":[],"paper":{"arxiv_id":"2401.14758","last_updated":"2024-04-15T13:44:11Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-07-06T17:20:49.161755Z","submitted_at":"2024-01-26T10:33:38Z","title":"Off-Policy Primal-Dual Safe 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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2401.14758."}