{"as_of":"2026-07-16T23:32:00Z","canonical_paper_id":"G4F5OO4Y","canonical_url":"https://pith.science/paper/G4F5OO4Y/integrity","context_digest":"sha256:e96107ae66134bf1c7ef3c4cb864ff7a8b58d530d997e1a7ad6e712e0c45c82d","coverage_summary":[],"findings":[],"findings_empty_copy":"No checks are listed for this paper yet.","findings_observation_state":"no_listed_checks","links":{"arxiv":"https://arxiv.org/abs/2606.21943","bundle_json":"/pith/G4F5OO4YXFUCNXVAQRTIGUDQAC/bundle.json","citation_record":"/paper/G4F5OO4Y/citation-record","evidence":"/evidence","html":"/paper/G4F5OO4Y/integrity","integrity_json":"/paper/G4F5OO4Y/integrity.json","json":"/paper/G4F5OO4Y/integrity.json","legacy_integrity_json":"/pith/G4F5OO4Y/integrity.json","paper":"/paper/G4F5OO4Y","reference_changes":"/flags?citing=G4F5OO4Y"},"paper":{"arxiv_id":"2606.21943","latest_version":1,"primary_cat":"cs.LG","title":"Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning"},"pith_number":"pith:2026:G4F5OO4YXFUCNXVAQRTIGUDQAC","pith_short":"G4F5OO4YXFUCNXVAQRTIGUDQAC","record":{"arxiv_id":"2606.21943","claim":"As of an unrecorded date, Pith completed 0 of 0 listed checks against arXiv:2606.21943. No listed check completed, so this record makes no findings claim.","counts":{"completed":0,"failed":0,"listed":0,"not_collected":0,"not_requested":0,"partial":0,"public_findings_from_completed":0,"skipped":0,"unavailable":0,"withheld":0},"coverage":[],"observed_at":null,"refusal":"This is a record of named checks, not a clean-status claim or a paper verdict.","schema":"pith.integrity.v1"},"schema":"pith.paper-integrity-record.v1","species":"LEDGER"}