Jinwen Tang: AI evaluation methodology and equitable, local-first AI for education at University of Missouri.
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
9
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-15) 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—
Output is unscored: the current snapshot lacks the per-work publication data this axis needs. It would measure cumulative work counts, annual production, and the distribution of outputs across venues and author roles over the full career record.
Impact—
Impact is unscored: citation-side data is not available in this snapshot. The axis would measure citation counts and trajectories, influence on follow-up work, and field-weighted reach; the h-index of 9 alone is too thin a basis to score it.
Focus0/100
The radar records a focus score of 0, reflecting a deliberately split profile. The reviewed field distribution divides evenly (0.5 and 0.5) between AI-for-education and AI evaluation methodology, while the broader OpenAlex topic history spans five clusters, led by 'Diverse Aspects of Tourism Research' (8 works) and 'Customer Service Quality and Loyalty' (4 works), which dilutes apparent concentration.
Collaboration39/100
Scored 39 out of 100. Over the last three years the OpenAlex record lists 10 works with only 6 distinct coauthors; recurring names include Xingran Huang, Hung-Yu Lin, Qiming Guo, Yafu Zhong, and Xiatian Zhuang. On both 2026 catalog papers Tang is a non-corresponding coauthor, in middle and last positions, indicating participation within small teams rather than network-broad collaboration.
Activity70/100
Scored 70 out of 100, the strongest axis in the radar. The record shows 10 works in the last three years and a rising annual curve: 2 works indexed in 2023, 2 in 2024, 3 in 2025, and 5 already indexed in 2026 — the highest single-year count in the provided series.
Reproducibility38/100
Scored 38 (reproMean) across the 2 papers Evolve has assessed (reproPapers: 2). The measurement-validity position paper is rated low reproducibility readiness, while the LLMersion framework is rated medium; per the Evolve verdicts, neither yet carries a tested empirical pipeline, so the score rests on an early-stage, two-paper sample.
Research summary
Jinwen Tang is a researcher at the University of Missouri whose current work spans two strands: AI evaluation methodology and AI for education. Evolve has reviewed two 2026 arXiv papers from this record. The first, on which Tang is last author, argues that compliance data such as automated-driving disengagement reports cannot by itself support comparative safety claims about deployed AI systems; Evolve finds the proposed 'evaluation contract' coherent but untested. The second, LLMersion, places Tang in a team building a local-first framework that runs small open models on-device to deliver a free four-skill home language tutor aimed at educational equity; feasibility is argued well while efficacy remains untested. The OpenAlex bibliometric record (h-index 9, i10-index 8) shows a long, uneven history with earliest indexed works in 2002 and accelerating recent production: 10 works in the last three years and 5 works already indexed in 2026. The reviewed field distribution splits evenly between the two strands (0.5 and 0.5), while the broader topic history includes tourism and customer-service clusters, so this profile is name-resolved from public bibliographic data and may reflect more than one same-named author.
Collaboration pattern
Tang's recent collaboration pattern is small-team and modest: 10 works over the last three years with only 6 distinct coauthors, yielding a collaboration score of 39 out of 100. Recurring names include Xingran Huang, Hung-Yu Lin, Qiming Guo, Yafu Zhong, and Xiatian Zhuang. On both 2026 catalog papers Tang is a non-corresponding coauthor — middle author on LLMersion and last author on the measurement-validity paper — suggesting contribution within group projects rather than sole leadership.
Research keywords
Highlights
Challenging compliance data as safety evidence for deployed AI
LLMersion: local-first AI tutoring toward language-learning equity
Timeline
- 2002Earliest works in the OpenAlex record: 2 publications indexed this year.
- 2011A single indexed work appears, marking a sparse stretch in the middle of the record.
- 2020Output resumes: 3 works indexed, the strongest year before the current run.
- 2023A steady run begins: 2 works indexed, the start of consecutive annual output.
- 20253 works indexed; momentum builds toward the current cycle.
- 20265 works indexed so far, the highest count in the provided series; Evolve reviews two Tang papers — the measurement-validity position paper (last author) and LLMersion (middle author).
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 come from an OpenAlex snapshot only (identity: openalex); h-index 9 and i10-index 8 are not cross-checked against Scopus or Google Scholar.
- The output and impact radar axes are unscored because the underlying data is insufficient in this snapshot.
- The topic history (tourism, customer service, consumer behavior) predates and diverges from the 2026 AI work; this profile is name-resolved from public bibliographic data and may mix same-named authors.
- Reproducibility scoring rests on only 2 Evolve-reviewed papers, so conclusions are early-stage.