{"as_of":"2026-07-17T09:32:00Z","canonical_paper_id":"YEBJHSTM","canonical_url":"https://pith.science/paper/YEBJHSTM/integrity","context_digest":"sha256:10eea7d2ff14cc22a55f8309bd88d1c779f5ed86f3970b3d3c0a9aff015f63fe","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/1906.01444","bundle_json":"/pith/YEBJHSTMEGVUJPH32PX2VEVRNW/bundle.json","citation_record":"/paper/YEBJHSTM/citation-record","evidence":"/evidence","html":"/paper/YEBJHSTM/integrity","integrity_json":"/paper/YEBJHSTM/integrity.json","json":"/paper/YEBJHSTM/integrity.json","legacy_integrity_json":"/pith/YEBJHSTM/integrity.json","paper":"/paper/YEBJHSTM","reference_changes":"/flags?citing=YEBJHSTM"},"paper":{"arxiv_id":"1906.01444","latest_version":1,"primary_cat":"cs.CR","title":"Heterogeneous Gaussian Mechanism: Preserving Differential Privacy in Deep Learning with Provable Robustness"},"pith_number":"pith:2019:YEBJHSTMEGVUJPH32PX2VEVRNW","pith_short":"YEBJHSTMEGVUJPH32PX2VEVRNW","record":{"arxiv_id":"1906.01444","claim":"As of an unrecorded date, Pith completed 0 of 0 listed checks against arXiv:1906.01444. 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"}