Machine-learning researcher bridging graph anomaly detection and benchmark-driven quantum error mitigation
2
papers here
2
reviewed by Evolve
1
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-09-20) and cover the author's entire public record, not just the papers listed here. Reproducibility signal comes from Evolve's own reviews.
Research profile
Output—
No output-volume metrics are available yet: the snapshot does not include total publication counts or productivity rates beyond the two cataloged 2026 papers. This axis would measure output volume, venue spread, and authorship role over time.
Impact—
Citation counts, h-index, and citation-based influence are absent from the available data, so no impact score can be reported. This axis would measure citation uptake and the scholarly reach of the two indexed papers.
Focus0/100
Evolve scores focus at 0, reflecting an even 50/50 split in the field distribution between graph learning for anomaly detection and quantum error mitigation benchmarking. The two cataloged papers sit one in each area and share a methodological thread of applying machine learning with careful evaluation, but no single specialization yet dominates. As the catalog grows, this axis will show whether the split persists or consolidates.
Collaboration44/100
The collaboration dimension scores 44, based on 8 distinct coauthors in the indexed record. The pool spans names including Suprim Nakarmi, Chahana Dahal, Junggab Son, Zuobin Xiong, Huayue Gu, Yushun Dong, and Xiyang Hu. With only two cataloged papers, one first-authored, this indicates a small-to-moderate network typical of an early-stage researcher; the score will firm up as more records resolve.
Activity—
No activity data exists beyond both cataloged papers being dated 2026; publication cadence by year is not available. This axis would measure publishing rhythm, preprint-to-venue conversion, and sustained engagement across years.
Reproducibility78/100
Reproducibility is this profile's strongest present axis at 78, the mean readiness across 2 papers. QEMScore is rated high — a rigorous benchmark with capacity-matched controls, honestly reported — while FoundAna is rated medium, with few-shot gains but weak evidence against graph foundation model baselines. The pattern suggests genuine attention to controls and reporting, though on a still-small paper base.
Research summary
Yue Zhao is an early-stage machine-learning researcher whose publicly indexed output sits at the intersection of two distinct areas: graph learning for anomaly detection, and benchmarking of learned quantum error mitigation (QEM). Evolve's catalog currently holds two 2026 arXiv papers tied to this name, split evenly in the field distribution (50% graph learning/anomaly detection; 50% quantum error mitigation/ML benchmarking). The first-authored QEMScore asks how much the measurement itself contributes to learned QEM; its capacity-matched controls show descriptor-only baselines matching most learned-QEM gains, and Evolve rates the instrument rigorous, honestly reported, and highly reproducible (repro readiness: high). The middle-authored FoundAna combines GNNs and transformers with four positional encodings for cross-graph anomaly detection; Evolve notes few-shot averages lead but evidence against graph foundation model baselines remains weak (repro readiness: medium). The reproducibility dimension scores 78 (mean across 2 papers), collaboration scores 44 from 8 distinct coauthors, and focus scores 0 reflecting the even field split. Output, impact, and activity dimensions lack sufficient data. No institution or ORCID is on record; 'Yue Zhao' is a common name, so this profile is name-resolved from public bibliographic data.
Collaboration pattern
The indexed record shows 8 distinct coauthors around two 2026 papers, including Suprim Nakarmi, Chahana Dahal, Junggab Son, Zuobin Xiong, Huayue Gu, Yushun Dong, and Xiyang Hu; the list also contains 'Yue Zhao' itself, likely a self-match artifact of name resolution. One paper is first-authored and the other middle-authored, so the record mixes leading and supporting roles. No institutional affiliation is available to anchor these collaborations geographically.
Research keywords
Highlights
QEMScore: descriptor-only controls match most learned-QEM gains
FoundAna: GNN-assisted foundation model for cross-graph anomaly detection
A record so far built on rigorous, reproducible evaluation
The reproducibility dimension scores 78 (mean across 2 papers), with one high-readiness benchmark and one medium-readiness method paper — a small but methodologically careful record where controls and honest reporting recur across both fields.
Timeline
- 2026First-authored QEMScore arXiv preprint benchmarks learned quantum error mitigation, earning Evolve's high repro-readiness rating.
- 2026Middle-authored FoundAna arXiv preprint proposes a GNN-assisted foundation model for graph anomaly detection.
- 2026Both papers enter the Evolve catalog, yielding a 50/50 field split and a reproducibility mean of 78 across 2 papers.
Papers in the Evolve catalog
Frequent co-authors
About this profile
This profile is AI-structured by Evolve.Pub from public bibliographic data (OpenAlex) and Evolve's own paper reviews. It is not written or endorsed by the researcher unless the profile is claimed. Radar dimensions are computed from real bibliometrics with fixed formulas — raw figures are shown alongside; missing dimensions mean insufficient data, never zero. Errors? Claim the profile to correct or hide it.
- Bibliometrics (coauthors, field distribution, dimension scores) derive from Evolve's OpenAlex-based snapshot; no citation counts or h-index are included.
- 'Yue Zhao' is a common name with no ORCID or affiliation on record; the profile is name-resolved from public bibliographic data and may merge or split identities.
- Output, impact, and activity dimensions are unscored due to insufficient data; only 2 papers are in scope for this profile.
- Both cataloged papers are 2026 arXiv preprints; peer-reviewed venue status is unknown.