{"as_of":"2026-08-06T08:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5193c5516d5ad6b5df94e91e8f600df0fbdda57f5ca6dcdf14496eb3e5990902","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":"2026-08-06T06:34:29.942622+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":"2026-06-26T12:15:08.304150Z","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":"2026-07-04T08:09:40.495426Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2403.06754","last_updated":"2024-03-16T12:43:33Z","snapshot_observed_at":"2026-07-06T17:42:37.195473Z","submitted_at":"2024-03-11T14:28:40Z","title":"ALaRM: Align Language Models via Hierarchical Rewards Modeling","version":2},"cited_work":{"arxiv_id":"2403.06754","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2403.06754","snapshot_observed_at":"2026-07-04T08:09:40.495426Z","title":null,"venue":null,"work_id":"d6759eb7-e354-43b0-aec6-ffc3eec0d3a5","year":2024},"citing_paper":{"arxiv_id":"2606.21943","last_updated":"2026-06-20T08:20:41Z","snapshot_observed_at":"2026-07-06T23:56:54.959593Z","submitted_at":"2026-06-20T08:20:41Z","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-06-26T12:15:08.304150Z"},"links":{"cited_paper":"/paper/2403.06754","citing_paper":"/paper/2606.21943"},"observation_digest":"sha256:b87271cb74c8d043d4f479f5e283c5e467f09188ca0afa7c0284bed6587df053","observation_id":"65f1d8ba-b948-4875-bb3e-6ea758884a98","resolution":{"observed_at":"2026-07-04T08:09:40.497165Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2403.06754/citation-record","integrity":"/paper/2403.06754/integrity","json":"/paper/2403.06754/citation-record.json","paper":"/paper/2403.06754"},"outbound":[],"paper":{"arxiv_id":"2403.06754","last_updated":"2024-03-16T12:43:33Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-07-06T17:42:37.195473Z","submitted_at":"2024-03-11T14:28:40Z","title":"ALaRM: Align Language Models via Hierarchical Rewards Modeling"},"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 6 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 1 inbound Pith citation observation for arXiv:2403.06754."}