Measuring the Hermeneutic Circle in Explainable AI: A Human-Free Test Based on Data Horizons, Executable Claims, Part–Whole Agreement, and Machine Readers
Machine Learning and Knowledge Extraction · 16.11.2026 · 8 (11) · 381
DOI: 10.3390/make8110381 ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 16.11.2026. Verfasst von Şadi Evren Şeker. Die Arbeit nennt 53 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Explanations of machine learning models are read by people but rarely evaluated with them, and automatic metrics score attribution vectors rather than what a reader receives. We operationalise the horizon, the hermeneutic circle, and the hermeneutics of suspicion as the Hermeneutic Circle Test (HCT), a human-free screen for explanations of tabular classifiers. HCT checks whether an explanation’s evidence lies inside a calibrated data horizon, whether its sentences survive on-horizon interventions, whether its account of a case agrees with the whole model and at which scale, and whether it helps machine readers learn the model. Over seven explainers, four datasets, and two model families (mean ± standard deviation over eight settings), the best explainer, KernelSHAP, verified 0.65 ± 0.15 of its claims, while random attributions verified 0.22 ± 0.08. On the same explanations, established faithfulness, remove-and-retrain, and disagreement metrics missed impossible evidence and narratives contradicting their own attributions, and sign-blind metrics scored sign-flipped explanations like the originals. Claim tests withstood scaffold attacks that adapt to the horizon and to the test itself; a scaffold that memorises the audited records weakened them and deceived every explainer, but part–whole agreement still flagged it. HCT is a reproducible screen to apply before user studies.
Zitieren
APA
Şeker, Ş. E. (2026). Measuring the Hermeneutic Circle in Explainable AI: A Human-Free Test Based on Data Horizons, Executable Claims, Part–Whole Agreement, and Machine Readers. Machine Learning and Knowledge Extraction, 8(11), 381. https://doi.org/10.3390/make8110381
Vancouver
Şeker ŞE. Measuring the Hermeneutic Circle in Explainable AI: A Human-Free Test Based on Data Horizons, Executable Claims, Part–Whole Agreement, and Machine Readers. Machine Learning and Knowledge Extraction. 2026;8(11):381. doi:10.3390/make8110381
BibTeX
@article{eker2026,
author = {Şeker, Şadi Evren},
title = {Measuring the Hermeneutic Circle in Explainable AI: A Human-Free Test Based on Data Horizons, Executable Claims, Part–Whole Agreement, and Machine Readers},
journal = {Machine Learning and Knowledge Extraction},
year = {2026},
volume = {8},
number = {11},
pages = {381},
doi = {10.3390/make8110381}
}
EUVIMED