Quantum machine learning researcher working on error-mitigation for quantum reinforcement learning on NISQ hardware
1
papers here
1
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—
Not yet scoreable: the catalog holds a single first-author arXiv preprint and no aggregated publication, venue, or productivity counts are available. This axis would measure total research output, such as publication volume across venues and years.
Impact—
No citation or influence metrics are available yet — the single reviewed paper is a recent arXiv preprint. This axis would measure citation counts, citations per paper, and uptake of the proposed error-mitigation approach by other researchers.
Focus100/100
The focus score is 100, and the underlying field distribution confirms why: all reviewed output sits in a single field, quantum machine learning (one paper in the Evolve catalog). The work combines quantum reinforcement learning, variational quantum circuits, error mitigation, and combinatorial optimization on a vehicle-routing case study, so the specialization is real but rests on a very small sample — one paper — and may broaden as more output is reviewed.
Collaboration22/100
The collaboration score is 22, based on only 2 distinct coauthors in the available record — Bisma Majid and Mir Mohammad Yousuf, the recurring partners on the reviewed work. The single first-author paper was written within this small team, indicating a compact, stable collaboration pattern rather than a large network; the score should be read against a one-paper sample and will likely change as more output is indexed.
Activity—
No activity signal is scoreable yet: with one 2026 preprint and no multi-year publication records available, recent-output cadence cannot be computed. This axis would measure publishing pace, year-over-year output, and sustained research engagement over time.
Reproducibility20/100
The reproducibility score is 20 (reproMean 20 across 1 paper assessed), and Evolve rates the APGEM preprint's reproducibility readiness as low. The review points to concrete obstacles: a tiny problem instance, contradictory evaluation metrics, and a missing key baseline — factors that would make independent replication of the quantum reinforcement learning results difficult as the work stands.
Research summary
Shabir Ahmad Sofi is an early-stage researcher in quantum machine learning whose reviewed work to date centers on making variational quantum algorithms usable on noisy, NISQ-era hardware. The Evolve catalog currently contains one paper authored by him — the 2026 arXiv preprint 'APGEM: Adaptive Policy-Guided Error Mitigation for Quantum Reinforcement Learning on a Real-World CVRP Case Study' — with Sofi in the first-author position. The paper proposes a controller that adaptively selects among established error-mitigation techniques (zero-noise extrapolation, probabilistic error cancellation, Clifford data regression, and readout-error mitigation) during quantum reinforcement learning training, evaluated on a capacitated vehicle routing problem instance. Evolve's review judges the adaptive controller promising, while noting a tiny problem instance, contradictory evaluation metrics, and a missing key baseline; reproducibility readiness is rated low. Bibliometric signals are narrow but coherent: the field distribution contains a single field, quantum machine learning (focus score 100), with 2 distinct coauthors — Bisma Majid and Mir Mohammad Yousuf — yielding a collaboration score of 22. Output, impact, and activity scores are not yet computable from the available data, so this profile should be read as an early-stage snapshot rather than a mature record.
Collaboration pattern
The available record shows a compact collaboration pattern: 2 distinct coauthors, with Bisma Majid and Mir Mohammad Yousuf as the recurring partners. The single reviewed paper is first-authored, suggesting Sofi leads the writing and technical direction within this small team. The collaboration score of 22 reflects this small network size; with only one indexed paper, it says more about sample size than about an established collaboration style.
Research keywords
Highlights
Adaptive error-mitigation controller for quantum reinforcement learning
Real-world case study on capacitated vehicle routing
Review flags evaluation weaknesses and low reproducibility
Timeline
- 2026First-author arXiv preprint APGEM appears, proposing adaptive policy-guided error mitigation for quantum reinforcement learning evaluated on a real-world CVRP case study.
- 2026The paper enters the Evolve catalog classified under quantum machine learning, indexed with keywords spanning error mitigation, NISQ, variational quantum circuits, and combinatorial optimization.
- 2026Evolve review is recorded: the adaptive controller is judged promising, with a tiny instance, contradictory metrics, a missing key baseline, and low reproducibility readiness (score 20) noted as weaknesses.
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.
- Bibliometric scores are computed from an OpenAlex-based snapshot only; no publisher, citation, or institutional records were used.
- The profile rests on a single reviewed paper (2026 arXiv preprint); output, impact, and activity axes have insufficient data and are not scored.
- Institution and country are absent from the source data; identity is name-resolved from public bibliographic data under ORCID 0000-0002-8740-2875.
- Reproducibility and collaboration scores derive from one paper and two distinct coauthors, so they may shift substantially as more output is indexed.