{"as_of":"2026-08-07T01:42:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:474fa0ed379348b121a22436655250143843acb865080e8298ab561b74e90823","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":"2026-08-06T06:34:29.942622+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":"2026-07-31T00:47:51.583975Z","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":"2026-07-01T14:25:45.860480Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2302.14372","last_updated":"2023-04-19T04:13:38Z","snapshot_observed_at":"2026-08-07T00:28:09.897132Z","submitted_at":"2023-02-28T07:55:02Z","title":"The In-Sample Softmax for Offline Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2302.14372","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2302.14372","snapshot_observed_at":"2026-07-01T14:25:45.860480Z","title":"The in-sample softmax for offline reinforcement learning.arXiv preprint arXiv:2302.14372,","venue":null,"work_id":"595728d7-37ff-48c8-ba65-d8ba6723050b","year":null},"citing_paper":{"arxiv_id":"2605.14779","last_updated":"2026-05-14T12:48:44Z","snapshot_observed_at":"2026-07-06T23:26:09.066863Z","submitted_at":"2026-05-14T12:48:44Z","title":"Peng's Q($\\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-30T21:45:43.298829Z"},"links":{"cited_paper":"/paper/2302.14372","citing_paper":"/paper/2605.14779"},"observation_digest":"sha256:63a5ca72b1b514323ee663a776647331e054f6cdbeb599a382aebe65dba9aac3","observation_id":"074a7bf1-b074-4330-849a-e8ed19515610","resolution":{"observed_at":"2026-07-01T14:25:45.862209Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.14372","last_updated":"2023-04-19T04:13:38Z","snapshot_observed_at":"2026-08-07T00:28:09.897132Z","submitted_at":"2023-02-28T07:55:02Z","title":"The In-Sample Softmax for Offline Reinforcement Learning","version":2},"cited_work":{"arxiv_id":"2302.14372","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2302.14372","snapshot_observed_at":"2026-07-01T14:25:45.860480Z","title":"The in-sample softmax for offline reinforcement learning.arXiv preprint arXiv:2302.14372,","venue":null,"work_id":"595728d7-37ff-48c8-ba65-d8ba6723050b","year":null},"citing_paper":{"arxiv_id":"2605.27877","last_updated":"2026-05-27T02:53:41Z","snapshot_observed_at":"2026-07-06T23:37:31.844094Z","submitted_at":"2026-05-27T02:53:41Z","title":"SPAR: Support-Preserving Action Rectification","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-29T14:34:39.094753Z"},"links":{"cited_paper":"/paper/2302.14372","citing_paper":"/paper/2605.27877"},"observation_digest":"sha256:650248328680f1c10364bf7176c9baa004fb7ac3c31432155e767ef77d98a85b","observation_id":"473d9785-0df0-4c6f-ac35-0d70d13490c0","resolution":{"observed_at":"2026-06-29T14:43:30.993584Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-06T06:34:29.942622+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.14372","last_updated":"2023-04-19T04:13:38Z","snapshot_observed_at":"2026-08-07T00:28:09.897132Z","submitted_at":"2023-02-28T07:55:02Z","title":"The In-Sample Softmax for Offline Reinforcement Learning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.14372","snapshot_observed_at":"2026-07-31T00:47:51.583975Z","title":"The in-sample softmax for offline reinforcement learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.25123","last_updated":"2026-07-27T22:33:09Z","snapshot_observed_at":"2026-08-04T14:34:29.536691Z","submitted_at":"2026-07-27T22:33:09Z","title":"Endpoint Replay: Compressing the Recency Buffer in Deep Reinforcement Learning","version":1},"reference_index":172,"source":"arxiv_source","source_observed_at":"2026-07-31T00:47:51.583975Z"},"links":{"cited_paper":"/paper/2302.14372","citing_paper":"/paper/2607.25123"},"observation_digest":"sha256:cf28483744c4dbd3300dbc0c21a642e76517c7ae6dee1596780e02befa83199b","observation_id":"b1be10ef-3b39-4dce-bc1c-f7174ab9763f","resolution":{"observed_at":"2026-07-31T00:47:51.583975Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2302.14372/citation-record","integrity":"/paper/2302.14372/integrity","json":"/paper/2302.14372/citation-record.json","paper":"/paper/2302.14372"},"outbound":[],"paper":{"arxiv_id":"2302.14372","last_updated":"2023-04-19T04:13:38Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T00:28:09.897132Z","submitted_at":"2023-02-28T07:55:02Z","title":"The In-Sample Softmax for Offline 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":"2026-08-06T06:34:29.942622+00:00","source":"crossref"},{"observed_at":"2026-08-06T06:34:23.284952+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:2302.14372."}