{"as_of":"2026-07-19T10:06:00Z","canonical_paper_id":"BTZPDJO6","canonical_url":"https://pith.science/paper/BTZPDJO6/integrity","context_digest":"sha256:84f8eec26b9794510010b3c38b18dbca266980866c7bb08b5293709306384393","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/2601.05242","bundle_json":"/pith/BTZPDJO66QJ4W3LPEDJYN5XP7X/bundle.json","citation_record":"/paper/BTZPDJO6/citation-record","evidence":"/evidence","html":"/paper/BTZPDJO6/integrity","integrity_json":"/paper/BTZPDJO6/integrity.json","json":"/paper/BTZPDJO6/integrity.json","legacy_integrity_json":"/pith/BTZPDJO6/integrity.json","paper":"/paper/BTZPDJO6","reference_changes":"/flags?citing=BTZPDJO6"},"paper":{"arxiv_id":"2601.05242","latest_version":1,"primary_cat":"cs.CL","title":"GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization"},"pith_number":"pith:2026:BTZPDJO66QJ4W3LPEDJYN5XP7X","pith_short":"BTZPDJO66QJ4W3LPEDJYN5XP7X","record":{"arxiv_id":"2601.05242","claim":"As of an unrecorded date, Pith completed 0 of 0 listed checks against arXiv:2601.05242. 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"}