AI-generated-text detectors are evaluated as classifiers, yet consequential deployments use detector outputs as evidence that people inspect, trust, contest, or use to escalate decisions. We call this mismatch the classification–evidence gap. The gap makes scalar detector scores a weak deployment interface: they hide the basis of a judgment, invite overtrust, and can turn false positives into accusations. We argue that AI-text detection should be evaluated as evidence-grounded decision support rather than as authorship proof. We introduce AGENT-XTrust, a guideline-expert detector that returns direct MetaAgent labels without target-domain scalar-cutoff calibration and converts each document-level judgment into inspectable evidence records containing local labels, rationales, confidence estimates, and linked spans. Across three domains and four generators, AGENT-XTrust preserves strong binary accuracy while producing inspectable, contestable evidence. In a controlled fixed-stimulus user study, participants assigned to the full AGENT-XTrust system-and-interface package achieved 19.8 and 11.3 points higher decision accuracy than those assigned to the score-only and score-plus-explanation packages, respectively; overtrust on each condition’s detector-wrong cases was 17.8 and 18.3 points lower. These results suggest a broader evaluation target for AI-text detection: not only whether a detector is correct, but whether complete detector-and-evidence packages support reliable human decisions under uncertainty.

State-of-the-art NLP models can often be fooled by human-unaware transformations such as synonymous word substitution. For security reasons, it is of critical importance to develop models with certified robustness that can provably guarantee that the prediction is can not be altered by any possible synonymous word substitution. In this work, we propose a certified robust method based on a new randomized smoothing technique, which constructs a stochastic ensemble by applying random word substitutions on the input sentences, and leverage the statistical properties of the ensemble to provably certify the robustness. Our method is simple and structure-free in that it only requires the black-box queries of the model outputs, and hence can be applied to any pre-trained models (such as BERT) and any types of models (world-level or subword-level). Our method significantly outperforms recent state-of-the-art methods for certified robustness on both IMDB and Amazon text classification tasks. To the best of our knowledge, we are the first work to achieve certified robustness on large systems such as BERT with practically meaningful certified accuracy.