NLP researcher in governed document AI: versioning, deduplication and LLM artifact generation for enterprises
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-09-21) 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—
Insufficient data: no verified publication count or productivity record is available yet. This axis would measure total research output — number of papers, venues and authorship roles over time — and cannot be scored from the current two-paper snapshot.
Impact—
No citation or influence data is available, so impact cannot be scored. This axis would measure citations, referencing works and scholarly reach of the two 2026 preprints once they accumulate citation records in public bibliographic sources.
Focus0/100
The focus score is 0/100. The underlying field distribution splits evenly — 50% natural language processing and 50% natural language processing (document AI / applied LLM systems) — across the two catalog papers. Read literally the score is low, but the two labels are adjacent: both papers target governed document processing in enterprise settings (versioning and deduplication in GVD; guideline-to-artifact generation in SAGE), so topical scope appears narrow even though the platform records no concentrated single-field weight.
Collaboration44/100
Collaboration scores 32/100, based on 4 distinct coauthors in the snapshot. Both catalog papers are middle-author, non-corresponding contributions, and the same small cluster recurs: Mohammadreza Sediqin, Shivali Dalmia, Abhishek Mukherji and Srinivasa Karthikeya Reddy Kovvuri. This is a compact, stable team pattern — work done within one close group rather than across a wide network — leaving substantial room to grow co-author diversity and independent leadership.
Activity—
The snapshot lacks year-by-year publication records, so research activity cannot be scored. This axis would measure publishing cadence and consistency over time; only two papers, both dated 2026, are visible, which is not enough to establish a trend.
Reproducibility20/100
Reproducibility scores 20/100, the mean across 2 reviewed papers, both rated low readiness. GVD reports strong F1 but on a private enterprise corpus, and SAGE evaluates on proprietary data using proxy metrics, so neither pipeline can currently be re-run from public artifacts; Evolve flags independent replication as not yet possible for either paper.
Research summary
Sumukha Thoppanahalli is an early-stage researcher in natural language processing whose visible work centers on document AI and applied LLM systems for enterprise settings. The Evolve catalog holds two 2026 arXiv papers: GVD, which unifies version-family linking and rule-level conflict governance for document repositories without using LLMs, and SAGE, a governed LLM pipeline that turns enterprise guidelines into artifacts, cutting guideline-to-artifact work from days to roughly one hour at a reported 3.2% hallucination rate. On both papers this researcher is a middle author and not the corresponding author, indicating contribution within a small team: the snapshot records 4 distinct coauthors and a collaboration score of 32/100, with Mohammadreza Sediqin, Shivali Dalmia, Abhishek Mukherji and Srinivasa Karthikeya Reddy Kovvuri as recurring collaborators. The focus score is 0/100, reflecting a field distribution split evenly between natural language processing and its document AI / applied LLM systems subfield. Evolve rates reproducibility at 20/100 across 2 reviewed papers, since both evaluations rest on proprietary enterprise data. Output, impact and activity axes are not yet scored for lack of data.
Collaboration pattern
Collaboration is compact: the snapshot records 4 distinct coauthors and a collaboration score of 32/100. The same group recurs across both 2026 papers — Mohammadreza Sediqin, Shivali Dalmia, Abhishek Mukherji and Srinivasa Karthikeya Reddy Kovvuri. On each paper this researcher is a middle author and not the corresponding author, so the current pattern is steady contribution inside a small team rather than network-wide collaboration or independent project leadership.
Research keywords
Highlights
GVD: rule-level governance for document versioning and deduplication
SAGE: governed LLM pipeline turns enterprise guidelines into artifacts
Timeline
- 2026GVD posted to arXiv, introducing governed versioning and deduplication for enterprise document repositories.
- 2026SAGE posted to arXiv, a governed LLM pipeline for generating artifacts from enterprise guidelines.
- 2026Both papers reviewed into the Evolve catalog with low reproducibility readiness (reproMean 20 across 2 papers).
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 are derived from OpenAlex-based public bibliographic data only; output, impact and activity axes lack sufficient data and are not scored.
- Institution, country and ORCID are unconfirmed; the profile is name-resolved from public bibliographic records.
- Both catalog papers are 2026 arXiv preprints evaluated on proprietary enterprise corpora, which limits independent verification of reported results.
- Reproducibility (reproMean 20) and collaboration (4 distinct coauthors) rest on only 2 reviewed papers — a very small evidence base.