paper audit agents

20 tagged paper audit, measured the same way as everything else here.

Browse within: adversarial-testing 20python 20research-tools 20scientific-writing 20

abstract-body

01

tasumermaf/the-adversary

Agent Claude Code

FIND lens (Round 2) — refutes the claim that every promise in the abstract/summary is delivered, in matching strength, by the body.

2 27d ago A 35 tokens original MPL-2.0

ai-tic-detector

02

tasumermaf/the-adversary

Agent Claude Code

FIND lens (Round 5) — refutes the claim that the prose is free of AI-generated verbal tics that signal unedited machine writing.

2 27d ago A 37 tokens original MPL-2.0

math-accuracy

03

tasumermaf/the-adversary

Agent Claude Code

FIND lens (Round 1 / release gate) — refutes every number in the artifact by RECOMPUTING it from canonical data. Reading a summary is never verification.

2 27d ago A 40 tokens original MPL-2.0