{"as_of":"2026-08-15T12:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:29e8e59d11dbc1a0f8ba909c651184df9ecb5651c11675eee979a88d96e97393","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":"2026-08-15T06:32:42.880941+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":"2026-08-07T05:15:33.500556Z","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":"2026-05-10T13:20:25.624340Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.13368","last_updated":"2025-04-17T22:21:35Z","snapshot_observed_at":"2026-08-07T16:01:17.621322Z","submitted_at":"2025-04-17T22:21:35Z","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.13368","snapshot_observed_at":"2026-08-07T05:15:33.500556Z","title":"An optimal discrimina- tor weighted imitation perspective for reinforcement learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.08644","last_updated":"2025-06-10T09:57:25Z","snapshot_observed_at":"2026-08-15T06:53:39.926040Z","submitted_at":"2025-06-10T09:57:25Z","title":"Semi-gradient DICE for Offline Constrained Reinforcement Learning","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T05:15:33.500556Z"},"links":{"cited_paper":"/paper/2504.13368","citing_paper":"/paper/2506.08644"},"observation_digest":"sha256:9faa53b74ee21e5e3556eca856e33daada37d21d2ca758e751b9390e8a6f6595","observation_id":"76e4dfae-42b7-4f45-8e16-afb9d4a6634c","resolution":{"observed_at":"2026-08-07T05:15:33.500556Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.13368","last_updated":"2025-04-17T22:21:35Z","snapshot_observed_at":"2026-08-07T16:01:17.621322Z","submitted_at":"2025-04-17T22:21:35Z","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.13368","snapshot_observed_at":"2026-08-03T13:18:31.831475Z","title":"Offline rl with no ood actions: In-sample learning via implicit value regularization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2601.00898","last_updated":"2026-07-17T14:56:12Z","snapshot_observed_at":"2026-08-15T09:57:00.601813Z","submitted_at":"2025-12-31T16:56:56Z","title":"Dichotomous Diffusion Policy Optimization","version":3},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T13:18:31.831475Z"},"links":{"cited_paper":"/paper/2504.13368","citing_paper":"/paper/2601.00898"},"observation_digest":"sha256:61c1a6cc4ecac6f400fe38bf0c71fcdad0a899a66c6c1af94ecafea2021c59e1","observation_id":"c6a1765c-5ccd-42f4-9528-f69f63c67c47","resolution":{"observed_at":"2026-08-03T13:18:31.831475Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.13368","last_updated":"2025-04-17T22:21:35Z","snapshot_observed_at":"2026-08-07T16:01:17.621322Z","submitted_at":"2025-04-17T22:21:35Z","title":"An Optimal Discriminator Weighted Imitation Perspective for Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2504.13368","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.13368","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"An optimal discriminator weighted imitation perspective for reinforcement learning","venue":null,"work_id":"605e6307-8c78-4b15-b6c0-327958462b60","year":2025},"citing_paper":{"arxiv_id":"2604.14265","last_updated":"2026-04-15T17:12:56Z","snapshot_observed_at":"2026-08-15T02:53:18.322914Z","submitted_at":"2026-04-15T17:12:56Z","title":"Reinforcement Learning via Value Gradient Flow","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-05-10T13:18:16.532434Z"},"links":{"cited_paper":"/paper/2504.13368","citing_paper":"/paper/2604.14265"},"observation_digest":"sha256:72f327d29b903321effa2e1f364932a732da5adc290f0cae861a0c74321d31d9","observation_id":"48d266f3-efc1-4b59-853c-1d004699c332","resolution":{"observed_at":"2026-05-10T13:20:25.626504Z","resolver_source":"arxiv_id","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"}}],"links":{"evidence":"/evidence","html":"/paper/2504.13368/citation-record","integrity":"/paper/2504.13368/integrity","json":"/paper/2504.13368/citation-record.json","paper":"/paper/2504.13368"},"outbound":[],"paper":{"arxiv_id":"2504.13368","last_updated":"2025-04-17T22:21:35Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T16:01:17.621322Z","submitted_at":"2025-04-17T22:21:35Z","title":"An Optimal Discriminator Weighted Imitation Perspective for 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":"2026-08-15T06:32:42.880941+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 3 inbound Pith citation observations for arXiv:2504.13368."}