Counted as completed checks in the claim sentence numerator.
Paper Integrity Record · LEDGER
Benchmarks Are Not Monolithic: Sample-Level Auditing and Orchestration for LLM Evaluation
As of 5 August 2026, Pith completed 4 of 6 listed checks against arXiv:2607.28801. The completed checks produced no public findings within their stated scope. 2 checks were skipped and produced no result.
This is a record of named checks, not a clean-status claim or a paper verdict.
Coverage vector
Skipped checks produced no result and say nothing about absence.
Listed checks
claim_evidence
completedv1.0.0, observed 2026-08-05 10:48:13.040593+00:00
- Scope
- Recorded paper claims checked for the evidence artifacts they name.
- Completed surface
- Completed within the stated scope.
doi_title_agreement
completedv1.0.0, observed 2026-08-05 02:08:36.031967+00:00
- Scope
- Cited titles compared with titles resolved from their DOI or arXiv identifier.
- Completed surface
- Completed within the stated scope.
doi_compliance
completedv1.1.0, observed 2026-08-05 00:48:58.056508+00:00
- Scope
- DOI and arXiv identifiers listed in the bibliography checked against named registries.
- Completed surface
- Checked 6 references.
citation_quote_validity
skippedv0.1.0, observed 2026-08-03 01:08:39.009235+00:00
- Scope
- Specific factual attributions checked against cited-paper text available in Pith.
- Reason
- Paper body text was unavailable.
ai_meta_artifact
skippedv1.0.0, observed 2026-08-03 01:08:37.255525+00:00
- Scope
- Paper body text scanned for literal AI-assistant artifacts.
- Reason
- Paper body text was unavailable.
cited_work_retraction
completedv1.0.0, observed 2026-08-03 00:38:21.287619+00:00
- Scope
- Cited references checked for source-reported retractions or expressions of concern.
- Completed surface
- Checked 1 reference.
Observations
The completed checks produced no public findings within their stated scope.
Methods and limits
Each listed check names the surface it examined. A skipped, failed, partial, unavailable, not collected, not requested, or withheld check says nothing about what a completed check would have returned.
- Only checks with status completed enter the claim sentence numerator.
- Findings appear only from completed checks and only within the scope printed for that check.
- Severity labels describe one observation row. They do not roll up into a paper judgment.