Early-career graph ML researcher formalizing echo-chamber detection as set-function optimization on signed networks
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—
Output data is insufficient to score this axis. It would measure publication volume and productivity over time — counts of papers by year and venue. The current record contains only one reviewed paper, so no reliable score exists yet.
Impact—
Impact data is insufficient to score this axis. It would measure citation-based reach — citations accumulated by published work and the attention it draws. No citation metrics are available in this profile's data, so no score is reported.
Focus100/100
The focus score is 100, the maximum. Every reviewed output in the catalog — one paper, "Revisiting the Objective of Echo Chamber Detection" — falls within a single field, graph machine learning / computational social network analysis, which holds the entire field distribution. A one-paper profile makes this concentration easy to over-read: it says the record is perfectly homogeneous so far, not that a long-term agenda is proven.
Collaboration28/100
The collaboration score is 28, computed from 3 distinct coauthors across the reviewed record. Kushani Perera and Shanika Karunasekera recur as frequent coauthors, alongside Jean Honorio, and the single cataloged paper is first-authored but not corresponding. A small coauthor set on a one-paper profile yields a modest score; it indicates a compact working circle rather than an established network.
Activity—
Activity data is insufficient to score this axis. It would measure recent research cadence — papers and preprints in the most recent years. The record contains a single 2026 paper, too thin to estimate sustained activity.
Reproducibility55/100
The reproducibility score is 55, a mean over 1 paper with medium reproducibility readiness. Evolve's review of "Revisiting the Objective of Echo Chamber Detection" notes that no code is released and that real-world validation is partly circular — both weigh on reproducibility even though the SDP heuristic itself is described as scalable. With only one scored paper, this number is a single data point, not a track record.
Research summary
Abylaikhan Bexeit is an early-stage researcher in graph machine learning and computational social network analysis, profiled here from public bibliographic data; no institution, country, or ORCID is available in the input. The Evolve catalog contains one reviewed paper, "Revisiting the Objective of Echo Chamber Detection" (arXiv, 2026), on which Bexeit is first author. That work formalizes echo-chamber detection as an explicit quadratic set-function objective derived through Fourier analysis of set functions, and approaches it through a semidefinite programming relaxation solved with an interior point method; the resulting scalable SDP heuristic outperforms community-detection baselines on recovery and internal cohesion. Evolve's review credits the formalization while noting that real-world validation is partly circular and that no code is released, yielding a medium reproducibility readiness and a reproducibility score of 55 averaged over one paper. The radar shows perfect focus (100), since all observed output sits in a single field, and a collaboration score of 28 based on 3 distinct coauthors, with Kushani Perera, Shanika Karunasekera, and Jean Honorio as frequent coauthors. Output, impact, and activity scores remain unavailable pending more bibliometric data.
Collaboration pattern
The observed collaboration footprint is compact: 3 distinct coauthors and a collaboration score of 28. Kushani Perera and Shanika Karunasekera recur as frequent coauthors, with Jean Honorio also in the frequent set, suggesting a small stable working group. The single cataloged paper is first-authored but not corresponding. With only one reviewed output, coauthor counts likely understate the true network; the pattern should be re-read as more papers enter the catalog.
Research keywords
Highlights
Echo chamber detection reframed as quadratic set-function optimization
Scalable SDP heuristic outperforms community-detection baselines
Validation and code release flagged as open gaps
Timeline
- 2026First cataloged paper, "Revisiting the Objective of Echo Chamber Detection", appears on arXiv with Bexeit as first author (not corresponding).
- 2026The paper formalizes echo-chamber detection as an explicit quadratic set-function objective via Fourier analysis of set functions, solved through a semidefinite programming relaxation.
- 2026Evolve reviews the work: the scalable SDP heuristic beats community-detection baselines on recovery and internal cohesion, but real-world validation is partly circular and no code is released (reproducibility 55, medium readiness).
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.
- Identity is name-resolved from public bibliographic data; no institution, country, or ORCID was available to confirm it.
- Output, impact, and activity dimensions are unscored because citation and productivity data are not yet available for this profile.
- Reproducibility (55) and the field distribution rest on a single reviewed paper; all scores are one-paper snapshots, not career-level statistics.
- The reviewed paper is sourced from arXiv; peer-reviewed venue status is not established in the available data.