{"as_of":"2026-08-14T13:17:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:bbc4b1ed67d28f913e0148f8ff8b9eb56ea8d332771da01ae74c9ea7ec0baddb","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":"2026-08-14T06:32:32.682623+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":"2026-08-12T10:48:41.660384Z","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":"2026-08-12T10:48:44.969330Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2311.17565","last_updated":"2023-11-29T11:59:03Z","snapshot_observed_at":"2026-08-14T11:16:43.465644Z","submitted_at":"2023-11-29T11:59:03Z","title":"Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning","version":1},"cited_work":{"arxiv_id":"2311.17565","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.17565","snapshot_observed_at":"2026-08-12T10:48:44.969330Z","title":"Bias Resilient Multi-Step Off-Policy Goal-Conditioned Reinforcement Learning","venue":"cs.LG","work_id":"6fae6db1-f8d3-43f5-944d-b9d08b27f840","year":2023},"citing_paper":{"arxiv_id":"2411.18892","last_updated":"2025-02-01T23:49:26Z","snapshot_observed_at":"2026-08-13T05:19:39.475481Z","submitted_at":"2024-11-28T03:53:14Z","title":"A Comprehensive Survey of Reinforcement Learning: From Algorithms to Practical Challenges","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-12T10:48:41.660384Z"},"links":{"cited_paper":"/paper/2311.17565","citing_paper":"/paper/2411.18892"},"observation_digest":"sha256:d759717727cc332f04b827e309f6fd6ab38c96d8f78240f48936b53001493bba","observation_id":"c6c4bdc8-0c82-417b-83d7-04a38bf00b3d","resolution":{"observed_at":"2026-08-12T10:48:45.014071Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2311.17565/citation-record","integrity":"/paper/2311.17565/integrity","json":"/paper/2311.17565/citation-record.json","paper":"/paper/2311.17565"},"outbound":[],"paper":{"arxiv_id":"2311.17565","last_updated":"2023-11-29T11:59:03Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-14T11:16:43.465644Z","submitted_at":"2023-11-29T11:59:03Z","title":"Bias Resilient Multi-Step Off-Policy Goal-Conditioned 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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2311.17565."}