Pith. sign in

Paper Integrity Record · LEDGER

PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks

As of 3 August 2026, Pith completed 5 of 8 listed checks against arXiv:2607.28587. The completed checks produced 2 public findings within their stated scope. 3 checks were skipped and produced no result.

This is a record of named checks, not a clean-status claim or a paper verdict.

pith.integrity.v1
2607.28587 v1
pith:2026:MULX42CSHAP2VXPBWXGHXBJPYX

Coverage vector

completed 5 of 8 listed checks

Counted as completed checks in the claim sentence numerator.

skipped 3 of 8 listed checks

Skipped checks produced no result and say nothing about absence.

Listed checks

doi_title_agreement

completed

v1.0.0, observed 2026-08-03 04:38:31.212971+00:00

Scope
Cited titles compared with titles resolved from their DOI or arXiv identifier.
Completed surface
Completed within the stated scope.

doi_compliance

completed

v1.1.0, observed 2026-08-03 03:18:37.210101+00:00

Scope
DOI and arXiv identifiers listed in the bibliography checked against named registries.
Completed surface
Checked 23 references. Recorded 2 findings from this run.

claim_evidence

completed

v1.0.0, observed 2026-08-03 02:53:16.469973+00:00

Scope
Recorded paper claims checked for the evidence artifacts they name.
Completed surface
Completed within the stated scope.

external_links

completed

v1.0.0, observed 2026-08-02 21:08:42.234063+00:00

Scope
External URLs extracted from paper text checked at the stated time.
Completed surface
Completed within the stated scope.

citation_quote_validity

skipped

v0.1.0, observed 2026-08-02 05:08:39.896605+00:00

Scope
Specific factual attributions checked against cited-paper text available in Pith.
Reason
Paper body text was unavailable.

shingle_duplication

skipped

v0.1.0, observed 2026-07-31 03:51:17.989999+00:00

Scope
Available paper body text compared for identical 40-token sequences under the detector's stated exclusions.
Reason
Usable body text was absent or too short for this check.

cited_work_retraction

completed

v1.0.0, observed 2026-07-31 02:21:11.117668+00:00

Scope
Cited references checked for source-reported retractions or expressions of concern.
Completed surface
Completed within the stated scope.

ai_meta_artifact

skipped

v1.0.0, observed 2026-07-31 01:51:26.984697+00:00

Scope
Paper body text scanned for literal AI-assistant artifacts.
Reason
Paper body text was unavailable.

Observations

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.