Otto Segersven — early-career researcher in human-AI interaction; first author of a Finnish-language Turing Test study
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—
No output metrics are available yet: the catalog holds a single paper, so counts of publications, venues, and yearly volume cannot be computed. This axis would measure total and per-year research output once more records are indexed.
Impact—
Impact cannot be scored: with one 2026 preprint in the catalog there are no citation counts, h-index, or venue-level signals. This axis would measure citation uptake and scholarly influence once the work has been visible long enough to be cited.
Focus100/100
Focus scores 100 because every cataloged record maps to one field, human-AI interaction (sociology of AI). The signal is real but thin: it derives from a single 2026 arXiv paper, so the perfect concentration reflects an early, undiversified portfolio rather than a demonstrated long-term specialization. Future papers will show whether this narrow scope is a deliberate research agenda.
Collaboration14/100
Collaboration scores 14, reflecting a distinct co-author count of just 1 across the cataloged record. The single frequent collaborator is Pentti Henttonen, and the one cataloged paper is first-authored and not marked as corresponding. This is a strongly solo-weighted pattern, though a one-paper sample means the true collaboration network is likely under-sampled.
Activity—
No activity metrics are available: publication year data covers only 2026, so cadence, per-year output trends, and career-stage activity rhythms cannot be computed. This axis would measure how actively the researcher publishes over time once multiple years of records exist.
Reproducibility55/100
Reproducibility scores 55, the mean readiness across one assessed paper — the Finnish Turing Test study, whose replication readiness Evolve rates medium. The main obstacles are the method's dependence on the specific ChatGPT 5.2 system and a model-generated role-prompting setup, plus a small sample (n=36). With only one paper assessed, this score is a single observation rather than a stable estimate.
Research summary
Otto Segersven is an early-stage researcher whose cataloged work to date sits in human-AI interaction, approached from a sociology-of-AI perspective. The Evolve catalog currently contains one paper, a 2026 arXiv preprint on which Segersven is first author: 'Cultural Competence in Context: A Large Language Model Passes the Turing Test in Finland.' The study reports that ChatGPT 5.2 passes a Finnish-language Turing Test when using model-generated role prompting, framing the result as evidence of cultural and linguistic competence beyond English-centric evaluation. Evolve's review flags the central claim as plausible but statistically fragile: the 'pass' rests on non-significance with a sample of n=36 participants, so the finding is best read as suggestive rather than definitive. Bibliometrically, the profile is narrow but coherent: all cataloged output maps to a single field, giving a focus score of 100, while a distinct co-author count of 1 (Pentti Henttonen) yields a low collaboration score of 14. Reproducibility is rated 55 from one assessed paper, corresponding to medium replication readiness. Output, impact, and activity metrics are not yet computable, so this profile should be treated as a preliminary, single-paper snapshot likely to change as more work is indexed.
Collaboration pattern
The cataloged collaboration pattern is strongly solo-weighted: across the profile there is exactly 1 distinct co-author, Pentti Henttonen, giving a collaboration score of 14. The single cataloged paper is first-authored and not marked corresponding. With only one record, the true network is probably under-sampled, but the evidence so far points to small-team, first-author-driven work rather than large consortium science.
Research keywords
Highlights
A Finnish-language Turing Test pass claimed for ChatGPT 5.2
The 'pass' rests on non-significance with n=36
Cultural competence beyond English-centric evaluation
Timeline
- 2026First-author arXiv preprint 'Cultural Competence in Context: A Large Language Model Passes the Turing Test in Finland' appears — the first record in this profile.
- 2026Collaborates with Pentti Henttonen, the only co-author recorded in the catalog to date.
- 2026Evolve reviews the paper: verdict 'plausible but fragile', with reproducibility readiness rated medium (score 55).
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 dimensions come from a public bibliometric snapshot covering only one cataloged paper; output, impact, and activity are marked missing because the evidence base is too thin to score.
- No institution, country, or ORCID is provided, so this profile is name-resolved from public bibliographic data and may merge or split identities with similar names.
- Reproducibility (55) is the mean over a single assessed paper, so it is a one-observation estimate rather than a stable trend.
- The sole paper is a 2026 arXiv preprint, not a peer-reviewed publication, and the picture may change as more work is indexed.