{"as_of":"2026-07-19T08:20:00Z","canonical_paper_id":"PX2FHZCY","canonical_url":"https://pith.science/paper/PX2FHZCY/integrity","context_digest":"sha256:883391aacb512d75181ace8188b677142041f1f93c14c68cc769390d208b686a","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/2606.20933","bundle_json":"/pith/PX2FHZCYNKJX6S62IHQTJSBSK5/bundle.json","citation_record":"/paper/PX2FHZCY/citation-record","evidence":"/evidence","html":"/paper/PX2FHZCY/integrity","integrity_json":"/paper/PX2FHZCY/integrity.json","json":"/paper/PX2FHZCY/integrity.json","legacy_integrity_json":"/pith/PX2FHZCY/integrity.json","paper":"/paper/PX2FHZCY","reference_changes":"/flags?citing=PX2FHZCY"},"paper":{"arxiv_id":"2606.20933","latest_version":1,"primary_cat":"cs.LG","title":"Towards Robust Training in NNGPT AutoML Pipeline: A Loss-Optimizer Pairing Selection Study"},"pith_number":"pith:2026:PX2FHZCYNKJX6S62IHQTJSBSK5","pith_short":"PX2FHZCYNKJX6S62IHQTJSBSK5","record":{"arxiv_id":"2606.20933","claim":"As of an unrecorded date, Pith completed 0 of 0 listed checks against arXiv:2606.20933. 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"}