{"as_of":"2026-08-07T08:22:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cbcc604edfbb759fa4e754aa49f58769572048df36d4df98a06126533379e392","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":"2026-08-07T06:34:17.273281+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":"2026-06-27T04:07:26.224919Z","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":"2026-07-03T17:28:44.589552Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.23363","last_updated":"2025-05-29T11:40:34Z","snapshot_observed_at":"2026-07-06T21:32:52.588223Z","submitted_at":"2025-05-29T11:40:34Z","title":"Discriminative Policy Optimization for Token-Level Reward Models","version":1},"cited_work":{"arxiv_id":"2505.23363","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2505.23363","snapshot_observed_at":"2026-07-03T17:28:44.589552Z","title":"Discriminative policy optimization for token-level reward models.arXiv preprint arXiv:2505.23363, 2025","venue":null,"work_id":"a1495476-2a02-4410-afa0-f0e2c2837eb8","year":2025},"citing_paper":{"arxiv_id":"2606.15893","last_updated":"2026-06-22T03:05:35Z","snapshot_observed_at":"2026-08-04T09:50:38.097939Z","submitted_at":"2026-06-14T16:25:59Z","title":"BALTO: Balanced Token-Level Policy Optimization for Hallucination Mitigation","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-27T04:07:26.224919Z"},"links":{"cited_paper":"/paper/2505.23363","citing_paper":"/paper/2606.15893"},"observation_digest":"sha256:0b80a59ca0dee91ed478c2a62cc7708fb8135e01fedc38091053eb9541623b56","observation_id":"64672a6b-4d2b-4641-bb7a-29a6eee19258","resolution":{"observed_at":"2026-07-03T17:28:44.591020Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2505.23363/citation-record","integrity":"/paper/2505.23363/integrity","json":"/paper/2505.23363/citation-record.json","paper":"/paper/2505.23363"},"outbound":[],"paper":{"arxiv_id":"2505.23363","last_updated":"2025-05-29T11:40:34Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T21:32:52.588223Z","submitted_at":"2025-05-29T11:40:34Z","title":"Discriminative Policy Optimization for Token-Level Reward Models"},"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 1 inbound Pith citation observation for arXiv:2505.23363."}