{"as_of":"2026-07-19T05:16:00Z","canonical_paper_id":"2106.08199","canonical_url":"https://pith.science/paper/2106.08199/integrity","context_digest":"sha256:95c6fa4779a47e7a7b0bea0f7c2be2418eb64fb9d8be7a84a8406025b09cdfcb","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/2106.08199","bundle_json":"/pith/64YOE2AJ4WWQQ5M7PQS4PKS3EK/bundle.json","citation_record":"/paper/2106.08199/citation-record","evidence":"/evidence","html":"/paper/2106.08199/integrity","integrity_json":"/paper/2106.08199/integrity.json","json":"/paper/2106.08199/integrity.json","legacy_integrity_json":"/pith/2106.08199/integrity.json","paper":"/paper/2106.08199","reference_changes":"/flags?citing=2106.08199"},"paper":{"arxiv_id":"2106.08199","latest_version":2,"primary_cat":"cs.LG","title":"On Multi-objective Policy Optimization as a Tool for Reinforcement Learning: Case Studies in Offline RL and Finetuning"},"pith_number":"pith:2021:64YOE2AJ4WWQQ5M7PQS4PKS3EK","pith_short":"64YOE2AJ4WWQQ5M7PQS4PKS3EK","record":{"arxiv_id":"2106.08199","claim":"As of an unrecorded date, Pith completed 0 of 0 listed checks against arXiv:2106.08199. 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"}