PASS Is a Claim, Not an Observation: Mechanical Re-verification of Self-Asserted Fix Claims in a Live Multi-Agent Audit Layer

Abstract When agents claim to have fixed their own defects, how do we know the fix is real?We mechanically re-verified 10 self-asserted code-level fix claims from a privileged coordina-tion agent (azone god) operating in AITRAP, a live multi-agent knowledge-tree platform. These 10 claims were extracted from a corpus of 179 coordination broadcasts (28 containing structured fix assertions, 31 unique fix-ID/message pairs, 18 distinct fix identifiers). Fix claims use mixed English/Chinese formats (PASS, checkmarks, and “verification passed” declarations). Each code-level claim was checked against three criteria: (1) file modification timestamp (mtime) consistency — 70% pass; (2) presence of the claimed defensive pattern at the specified identifier and call site — 60% pass in the claimed file (80% anywhere in the codebase); (3) deterministic rule-based re-verification from the broadcast announcement alone — 80% pass. The critical finding: among claims that provide sufficient information for re-verification (C3-pass), 50% fail the identifier+call-site check (C2-fail) — the fix ei-ther does not exist at the claimed location or does not exist at all. This demonstrates that self-asserted fix claims cannot be trusted without independent mechanical verification. Our central claim: a PASS declaration is a claim requiring independent verification, not an observation of fix completion.

Authors

Institutions

Publication Details

Journal
Research Square
Published
2026-11-03
DOI
https://doi.org/10.21203/rs.3.rs-11570046/v1
Primary Topic
Software Engineering Research
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
preprint

PASS Is a Claim, Not an Observation: Mechanical Re-verification of Self-Asserted Fix Claims in a Live Multi-Agent Audit Layer

Lei Zhenbing, Lei Chang
3 links
Research Square
Software Engineering Research
preprint

PASS Is a Claim, Not an Observation: Mechanical Re-verification of Self-Asserted Fix Claims in a Live Multi-Agent Audit Layer

Lei Zhenbing, Lei Chang
preprint en

Abstract

Abstract When agents claim to have fixed their own defects, how do we know the fix is real?We mechanically re-verified 10 self-asserted code-level fix claims from a privileged coordina-tion agent (azone god) operating in AITRAP, a live multi-agent knowledge-tree platform. These 10 claims were extracted from a corpus of 179 coordination broadcasts (28 containing structured fix assertions, 31 unique fix-ID/message pairs, 18 distinct fix identifiers). Fix claims use mixed English/Chinese formats (PASS, checkmarks, and “verification passed” declarations). Each code-level claim was checked against three criteria: (1) file modification timestamp (mtime) consistency — 70% pass; (2) presence of the claimed defensive pattern at the specified identifier and call site — 60% pass in the claimed file (80% anywhere in the codebase); (3) deterministic rule-based re-verification from the broadcast announcement alone — 80% pass. The critical finding: among claims that provide sufficient information for re-verification (C3-pass), 50% fail the identifier+call-site check (C2-fail) — the fix ei-ther does not exist at the claimed location or does not exist at all. This demonstrates that self-asserted fix claims cannot be trusted without independent mechanical verification. Our central claim: a PASS declaration is a claim requiring independent verification, not an observation of fix completion.

Research Square
University of Chinese Academy of Social Sciences (CN)
Software Engineering Research
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon