Loading
Life sciences · Preprint
arXiv · September 4, 2026
Posted before peer review. The findings may change or fail to hold.
This is an unrefereed preprint introducing GLASS, a machine learning framework for graph-level anomaly detection using graph-language alignment on a hypersphere. The work reports computational validation across twelve benchmarks with claimed superior average AUROC and rank relative to baselines, but has not undergone peer review and does not present clinical validation, prospective testing, or outcome data relevant to medical practice.
Preprint. Graph datasets across twelve computational benchmarks; no human or patient population studied.. Intervention: GLASS framework: graph-language alignment on unit hypersphere using multi-slice soft cosine objective, Graph Descriptor Prompt (GraphDP), Matryoshka representation slices, and Spherical Multi-Modal Scoring (SMS) with von Mises-Fisher kerne…. Compared with: Recent advanced GLAD (graph-level anomaly detection) baselines..
GLASS obtains best average AUROC and rank compared with recent advanced GLAD baselines across twelve benchmarks Framework enables zero-shot anomaly detection via text embedding space without target-domain training data Few-shot adaptation via reference-set calibration demonstrated with only a handful of normal examples
Safety was not reported in the material analysed. Check the source before drawing any conclusion about harm.
The source did not state who this applies to in practice.
An unrefereed arXiv preprint describing a novel machine learning framework for graph anomaly detection with computational validation across benchmarks, but lacking peer review and clinical or real-world outcome data.
As stated by the source record.
Quoted from the source exactly as published.
Graded across the dimensions that decide whether you should act, each from what the source actually supports. There is no single score, and where a dimension was not assessed it says so.
We introduce GLASS, a framework for graph-level anomaly detection (GLAD) that achieves robust cross-domain transferability through graph-language alignment on the unit hypersphere. GLASS builds a unified representation space by aligning a structure-aware graph encoder with an instruction-aware text embedding via a multi-slice soft cosine objective. Our framework serializes local, global, and semantic graph properties into a compact Graph Descriptor Prompt (GraphDP), creating a text bridge that enables domain-agnostic anomaly scoring. By enforcing multi-scale consistency through Matryoshka representation slices, the model captures anomalous deviations at multiple levels of granularity. For scoring, we formulate anomaly detection as density estimation on the aligned hypersphere and introduce Spherical Multi-Modal Scoring (SMS), which instantiates von Mises-Fisher kernel density estimators in both graph and text embedding spaces. This probabilistic formulation recovers angular k-nearest-neighbor scoring as a high-concentration limiting case and provides a principled fusion of structural and semantic anomaly signals. The shared text embedding space further serves as a cross-domain bridge: by encoding a target domain's GraphDP without target-domain training data, GLASS performs zero-shot anomaly detection, and with only a handful of normal examples, few-shot adaptation via reference-set calibration. Across twelve benchmarks and three meta-domains, GLASS obtains the best average AUROC and rank compared with recent advanced GLAD baselines and enables effective cross-domain transfer.
Taken from the source record, never inferred. Follow any of these and new work involving them reaches your briefing.