Integrity report for Mechanistic Interpretability for Neural Networks: Circuits, Sparse Features and Symbolic Reasoning

A machine-verified record of the checks Pith has run against this paper: detector runs, findings, signed bundle events, and canonical identifiers.

arXiv:2607.07316 · pith:2026:NP2VXWY5OQ4H6CIVLFU3M2C2IM

0Critical

2Advisory

6Detectors run

2026-07-10Last checked

Paper page arXiv integrity.json bundle.json

Detector runs

doi_compliance completed v1.0.0 · findings 2 · 2026-07-10 15:08:30.539268+00:00

doi_title_agreement completed v1.0.0 · findings 0 · 2026-07-10 15:01:35.327557+00:00

claim_evidence completed v1.0.0 · findings 0 · 2026-07-10 07:42:25.976519+00:00

citation_quote_validity completed v0.1.0 · findings 0 · 2026-07-09 15:57:42.415816+00:00

cited_work_retraction completed v1.0.0 · findings 0 · 2026-07-09 13:48:28.665388+00:00

ai_meta_artifact skipped v1.0.0 · findings 0 · 2026-07-09 07:54:08.082615+00:00

Findings

No public integrity findings for this paper.

Signed record

The machine-readable record for this paper lives at /pith/NP2VXWY5/integrity.json. Pith Number bundles also include signed pith.integrity.v1 events where a Pith Number exists.