{"as_of":"2026-08-22T21:49:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:03d45bef20775198f6cca01dbf05d8eb892462bbe13e05e5d481a336cfac2461","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":"2026-08-22T06:32:14.747728+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":"2026-08-16T00:09:18.854450Z","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":"2026-08-16T00:09:19.502677Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2503.13817","last_updated":"2025-03-18T01:51:27Z","snapshot_observed_at":"2026-08-16T12:49:09.428650Z","submitted_at":"2025-03-18T01:51:27Z","title":"VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.13817","snapshot_observed_at":"2026-08-02T17:38:54.349411Z","title":"Varp: Reinforcement learning from vision- language model feedback with agent regularized preferences,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2603.22169","last_updated":"2026-07-19T10:26:48Z","snapshot_observed_at":"2026-08-17T19:11:06.694842Z","submitted_at":"2026-03-23T16:28:36Z","title":"VersualRL: Closed-Loop Verbal Reinforcement Learning with Visual Execution Feedback for Task-Level Robot Planning","version":3},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-02T17:38:54.349411Z"},"links":{"cited_paper":"/paper/2503.13817","citing_paper":"/paper/2603.22169"},"observation_digest":"sha256:79861b87a3f4e097f95030c399e34d157e7f67ed44f9005c31d44d17a39ab26c","observation_id":"60273c1d-e5fe-4cd5-90c7-dc3873a1f7d9","resolution":{"observed_at":"2026-08-02T17:38:54.349411Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.13817","last_updated":"2025-03-18T01:51:27Z","snapshot_observed_at":"2026-08-16T12:49:09.428650Z","submitted_at":"2025-03-18T01:51:27Z","title":"VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.13817","snapshot_observed_at":"2026-07-13T16:10:12.689957Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2603.28730","last_updated":"2026-05-26T17:56:39Z","snapshot_observed_at":"2026-08-19T14:14:25.412292Z","submitted_at":"2026-03-30T17:46:31Z","title":"SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-07-13T16:10:12.689957Z"},"links":{"cited_paper":"/paper/2503.13817","citing_paper":"/paper/2603.28730"},"observation_digest":"sha256:d3cb0d6fff4ad09029c229c1d0984353feaff7fafda41318014f4797a0884508","observation_id":"f568d937-7887-47af-bb6d-07833bd943e1","resolution":{"observed_at":"2026-07-13T16:10:12.689957Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.13817","last_updated":"2025-03-18T01:51:27Z","snapshot_observed_at":"2026-08-16T12:49:09.428650Z","submitted_at":"2025-03-18T01:51:27Z","title":"VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences","version":1},"cited_work":{"arxiv_id":"2503.13817","doi":null,"metadata_source":"pith","pith_arxiv_id":"2503.13817","snapshot_observed_at":"2026-08-16T00:09:19.502677Z","title":"VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences","venue":"cs.AI","work_id":"e03d335f-12c6-4c0a-abb9-a0a33cb9eaa2","year":2025},"citing_paper":{"arxiv_id":"2608.12748","last_updated":"2026-08-13T02:57:21Z","snapshot_observed_at":"2026-08-21T03:07:27.974496Z","submitted_at":"2026-08-13T02:57:21Z","title":"Scaling Representation Diversity: Modulated Attention and Reconstructive Regularization for Visual Grounding","version":1},"reference_index":204,"source":"arxiv_source","source_observed_at":"2026-08-16T00:09:18.854450Z"},"links":{"cited_paper":"/paper/2503.13817","citing_paper":"/paper/2608.12748"},"observation_digest":"sha256:a555aba3bbe3f7b69cf19bcde414258117ea25244bfe2b71f46d9c6b82acb259","observation_id":"6676ba5c-d47a-499b-8c1f-b34f282f3d49","resolution":{"observed_at":"2026-08-16T00:09:19.506116Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-22T06:32:14.747728+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2503.13817/citation-record","integrity":"/paper/2503.13817/integrity","json":"/paper/2503.13817/citation-record.json","paper":"/paper/2503.13817"},"outbound":[],"paper":{"arxiv_id":"2503.13817","last_updated":"2025-03-18T01:51:27Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-16T12:49:09.428650Z","submitted_at":"2025-03-18T01:51:27Z","title":"VARP: Reinforcement Learning from Vision-Language Model Feedback with Agent Regularized Preferences"},"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":"2026-08-22T06:32:14.747728+00:00","source":"crossref"},{"observed_at":"2026-08-22T06:32:06.552537+00:00","source":"retraction_watch"}],"thesis":"As of 22 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 3 inbound Pith citation observations for arXiv:2503.13817."}