Machine learning researcher working on provable guarantees for causal discovery and social-network analysis
4
papers here
4
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
16
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-09) 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 metrics are not yet available for this profile: the underlying data includes no publication counts or venue history. This axis would measure the total volume and yearly distribution of the researcher's published work.
Impact—
Impact data is insufficient in the current snapshot: no citation counts or influence indicators are present. This axis would measure citations to the researcher's work and its uptake by follow-up studies.
Focus0/100
The focus score is 0, derived from a raw field distribution that splits cataloged output evenly: 0.5 for graph machine learning / computational social network analysis and 0.5 for causal discovery / statistical machine learning. The profile therefore shows two equally weighted research lines rather than one concentrated specialty, each represented by a 2026 arXiv paper in the Evolve catalog.
Collaboration48/100
The collaboration score is 36, computed from 5 distinct coauthors in the snapshot. Recurring collaborators include Violet Zheng, Abylaikhan Bexeit, Kushani Perera, Shanika Karunasekera, and Weijian Yu. All three 2026 catalog papers list Honorio as last-listed author and none as corresponding, indicating a compact, senior-authored team pattern rather than large multi-institution collaborations.
Activity83/100
Activity data is not yet available: the snapshot contains no publication cadence beyond the three 2026 arXiv postings. This axis would measure recent output tempo and sustained engagement over time.
Reproducibility55/100
Reproducibility scores 55, the mean over 2 scored papers in the catalog, both rated medium reproducibility readiness by Evolve's review. The echo-chamber paper's scalable SDP heuristic comes with no released code, and the structural-equation-model paper is flagged for untestable tuning constants and toy-scale experiments; the score reflects these methodological, not artifact-level, signals.
Research summary
Jean Honorio is a machine learning researcher whose cataloged work splits evenly between two lines: graph machine learning / computational social network analysis and causal discovery / statistical machine learning, each accounting for 50% of the field distribution in the Evolve snapshot. All three papers currently in the catalog are 2026 arXiv postings, and in each Honorio is the last-listed author though none is marked corresponding, a pattern consistent with a small-team senior-author role. The network-analysis line is represented by 'Revisiting the Objective of Echo Chamber Detection': Evolve's review credits it with formalizing echo-chamber detection as an explicit quadratic set-function objective via Fourier analysis, with a scalable SDP heuristic beating community-detection baselines on recovery and internal cohesion, while flagging partly circular real-world validation and no released code. The causal line includes 'Provable Guarantees and Efficient Learning of Structural Equation Models with Latent Confounders', which claims exact recovery of directed edges at n ~ max{s log p, rp} via sparse-plus-low-rank precision estimation and terminal-node peeling; the review notes statement-level errors and toy-scale experiments. A third paper on provable guarantees for spectral structured prediction extends the provable-guarantee agenda and awaits review. Reproducibility averages 55 across the two scored papers, both rated medium readiness.
Collaboration pattern
The bibliometric snapshot records 5 distinct coauthors and a collaboration score of 36, pointing to compact, recurring teams rather than broad networks. Frequent collaborators are Violet Zheng, Abylaikhan Bexeit, Kushani Perera, Shanika Karunasekera, and Weijian Yu. Across all three 2026 catalog papers Honorio appears as last-listed author and none as corresponding author, consistent with a senior-supervisor authorship pattern on small co-authored arXiv submissions.
Research keywords
Highlights
Formalizing echo-chamber detection as a set-function objective
Provable learning of structural equation models with latent confounders
Extending the provable-guarantee agenda to spectral structured prediction
A 2026 arXiv posting with Honorio as last-listed author, this paper on provable guarantees for spectral structured prediction rounds out the catalog's theory-heavy, two-line profile. It has not yet been reviewed by Evolve, so no verdict or reproducibility score is available for it.
Timeline
- 2026Posting of 'Provable Guarantees for Spectral Structured Prediction' on arXiv, with Honorio as last-listed author; the paper is not yet reviewed by Evolve.
- 2026Posting of 'Revisiting the Objective of Echo Chamber Detection' on arXiv; Evolve's review rates its reproducibility readiness as medium.
- 2026Posting of 'Provable Guarantees and Efficient Learning of Structural Equation Models with Latent Confounders' on arXiv; Evolve's review rates its reproducibility readiness as medium.
Papers in the Evolve catalog
Listen Then Reason: Perception-Grounded Test-Time Reinforcement Learning for Large Audio-Language Models
Provable Guarantees for Spectral Structured Prediction
Revisiting the Objective of Echo Chamber Detection
Provable Guarantees and Efficient Learning of Structural Equation Models with Latent Confounders
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 are computed from OpenAlex only; the output, impact, and activity axes currently lack sufficient data and are not scored.
- All three cataloged papers are 2026 arXiv preprints; this snapshot includes no peer-reviewed venue, award, or affiliation information (institution and country fields are null).
- Only two papers carry Evolve review verdicts and reproducibility scores; the spectral structured prediction paper is unreviewed.
- The profile is name-resolved from public bibliographic data anchored to ORCID 0000-0002-6448-0598; identity-related statements should be read with that limitation in mind.