Georgia Tech statistician bridging statistical estimation theory with affective computing and perceptual psychophysics
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
13
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-14) 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 score yet: the snapshot gives h-index 13 and i10-index 19 but no verified total publication count, so this axis—which would measure the overall volume of indexed works—cannot be scored honestly.
Impact—
Impact is unscored: citation totals, per-work citation distributions, and uptake measures are absent from this snapshot, so scholarly influence—what this axis would measure—cannot be reported without inventing numbers.
Focus0/100
The focus score of 0/100 matches the raw field distribution: work splits exactly 50/50 between statistics and machine learning theory and affective computing/computational psychophysics, with topics spread across five clusters—statistical methods and inference (22), stochastic gradient optimization (19), sparse and compressive sensing (16), reinforcement learning in robotics (12), and bandit algorithms (11). This reads as deliberate breadth across theory and application rather than an unformed agenda.
Collaboration32/100
The collaboration score of 32/100 is modest: only 4 distinct coauthors appear in the recent window, with recurring partners Xuanzhou Chen, Sankaraleengam Alagapan, Milind Nakul, and Vidya Muthukumar. Both 2026 catalog papers place him in the last-author, senior role, consistent with a small, stable circle rather than large rotating teams.
Activity89/100
Activity is the strongest axis at 89/100: the snapshot lists 20 works in the most recent three years, and 2026 shows 9 indexed works, second only to the 2017 peak of 10, after output held at 4-6 works per year from 2018 through 2025. Productivity is sustained and currently near its record.
Reproducibility78/100
Reproducibility averages 78/100 across the 2 papers Evolve has assessed so far. The next-token functional estimation paper rates high readiness, while the perceptual-adjustment-query study rates medium, with reviewers citing a stage-order confound and missing accuracy data. With only two assessed works, the score should be read as indicative rather than definitive.
Research summary
Ashwin Pananjady is a researcher at the Georgia Institute of Technology whose indexed record splits evenly, 50/50, between statistics and machine learning theory and affective computing / computational psychophysics, per the OpenAlex field distribution in this snapshot. His bibliometric footprint is solid and currently near its peak: an h-index of 13, an i10-index of 19, 20 works in the most recent three years, and 9 indexed works in 2026, second only to the 2017 high of 10. Topic clusters put statistical methods and inference first (22 works), followed by stochastic gradient optimization (19), sparse and compressive sensing (16), reinforcement learning in robotics (12), and bandit algorithms (11). Evolve has reviewed two 2026 arXiv papers on which he is last author: one introducing perceptual adjustment queries to calibrate facial-affect recognition at the individual level, rated medium for reproducibility, and one on next-token functional estimation under beta-mixing, rated high for reproducibility and shown rate-minimax for surprise probability. A collaboration score of 32 reflects a small recurring coauthor set of four. The output and impact axes remain unscored pending citation data.
Collaboration pattern
Collaboration is compact and stable: the recent window lists only 4 distinct coauthors, and both reviewed 2026 papers place him as last (senior) author. Recurring partners include Xuanzhou Chen, Sankaraleengam Alagapan, Milind Nakul, and Vidya Muthukumar. The collaboration dimension scores 32/100, consistent with a small, durable circle typical of theory-leaning work paired with focused psychophysics studies rather than large rotating consortiums.
Research keywords
Highlights
Personalized calibration in facial-affect recognition
Rate-minimax estimation of next-token functionals
Senior-authored 2026 output across two fields
Both 2026 catalog papers carry him as last author, one on each side of the snapshot's 50/50 field split—psychophysical calibration and statistical estimation theory—in a year with 9 indexed works.
Timeline
- 2013The indexed bibliometric record opens with 2 works in this snapshot.
- 2017Annual output reaches its peak of 10 indexed works.
- 2020Six indexed works, within the steady 4-6 annual run that holds from 2018 through 2025.
- 2024The recent three-year window opens: 20 works accumulate across 2024-2026.
- 2026Nine indexed works, second only to 2017; Evolve reviews two last-authored arXiv papers on affect-recognition calibration and next-token functional estimation.
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 figures come from OpenAlex only; citation-based output and impact dimensions are missing from this snapshot and remain unscored.
- Identity is name-resolved from public bibliographic data (OpenAlex record linked to ORCID 0000-0003-0824-9815); biography beyond the snapshot is not independently verified.
- The reproducibility score of 78 rests on only 2 papers assessed by Evolve and should be read as indicative.
- Timeline entries derive from annual indexed-work counts and the two cataloged papers; only these papers have received in-depth Evolve review.