{"as_of":"2026-08-23T16:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:9ecb335ad41101d08df38a15ed7f1c1526f068a286dbb197797a06546e68dc5e","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":2,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":2,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T04:17:28.064277Z","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":"2026-08-05T20:21:08.858224Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2505.04842","last_updated":"2026-04-12T16:48:19Z","snapshot_observed_at":"2026-08-02T13:20:15.810974Z","submitted_at":"2025-05-07T22:41:26Z","title":"Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers","version":2},"cited_work":{"arxiv_id":"2505.04842","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.04842","snapshot_observed_at":"2026-08-05T20:21:08.858224Z","title":"Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers","venue":"cs.LG","work_id":"60b17354-00f6-460f-9176-6c873d498703","year":2025},"citing_paper":{"arxiv_id":"2508.10751","last_updated":"2025-08-14T15:34:47Z","snapshot_observed_at":"2026-08-18T20:12:03.334534Z","submitted_at":"2025-08-14T15:34:47Z","title":"Pass@k Training for Adaptively Balancing Exploration and Exploitation of Large Reasoning Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T20:21:08.155057Z"},"links":{"cited_paper":"/paper/2505.04842","citing_paper":"/paper/2508.10751"},"observation_digest":"sha256:8281edad42b562f5881b018b1c76ae715495730a037b81c7e9e3844a2e1058b5","observation_id":"4c3ddb77-da42-4ce6-a580-5cc87dd8b440","resolution":{"observed_at":"2026-08-05T20:21:08.865359Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.04842","last_updated":"2026-04-12T16:48:19Z","snapshot_observed_at":"2026-08-02T13:20:15.810974Z","submitted_at":"2025-05-07T22:41:26Z","title":"Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.04842","snapshot_observed_at":"2026-08-11T04:17:28.064277Z","title":"arXiv preprint arXiv:2505.04842 , year =","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.07424","last_updated":"2026-08-10T06:21:10Z","snapshot_observed_at":"2026-08-15T15:01:59.235255Z","submitted_at":"2026-08-07T17:12:13Z","title":"CoBa: Cost-Effective Test-Time Scaling via Compute-Balanced Routing","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-11T04:17:28.064277Z"},"links":{"cited_paper":"/paper/2505.04842","citing_paper":"/paper/2608.07424"},"observation_digest":"sha256:8a55fb4444b1b3ca05a20df14642679dbe829947441da47c56e4b587e6bfa44a","observation_id":"3248d106-bf70-4246-a449-32b3074ef3a4","resolution":{"observed_at":"2026-08-11T04:17:28.064277Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2505.04842/citation-record","integrity":"/paper/2505.04842/integrity","json":"/paper/2505.04842/citation-record.json","paper":"/paper/2505.04842"},"outbound":[],"paper":{"arxiv_id":"2505.04842","last_updated":"2026-04-12T16:48:19Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-02T13:20:15.810974Z","submitted_at":"2025-05-07T22:41:26Z","title":"Putting the Value Back in RL: Better Test-Time Scaling by Unifying LLM Reasoners With Verifiers"},"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":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 2 inbound Pith citation observations for arXiv:2505.04842."}