{"as_of":"2026-07-19T23:19:00Z","canonical_paper_id":"2409.12917","canonical_url":"https://pith.science/paper/2409.12917/integrity","context_digest":"sha256:7d725f56e686b21342cf7b3ceed7cabb7ccaac637db04f65b968f58e660e684a","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/2409.12917","bundle_json":"/pith/OQMAWUXNEGORB2TU7H6MP4SDXQ/bundle.json","citation_record":"/paper/2409.12917/citation-record","evidence":"/evidence","html":"/paper/2409.12917/integrity","integrity_json":"/paper/2409.12917/integrity.json","json":"/paper/2409.12917/integrity.json","legacy_integrity_json":"/pith/2409.12917/integrity.json","paper":"/paper/2409.12917","reference_changes":"/flags?citing=2409.12917"},"paper":{"arxiv_id":"2409.12917","latest_version":2,"primary_cat":"cs.LG","title":"Training Language Models to Self-Correct via Reinforcement Learning"},"pith_number":"pith:2024:OQMAWUXNEGORB2TU7H6MP4SDXQ","pith_short":"OQMAWUXNEGORB2TU7H6MP4SDXQ","record":{"arxiv_id":"2409.12917","claim":"As of an unrecorded date, Pith completed 0 of 0 listed checks against arXiv:2409.12917. 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"}