Applied NLP researcher in governed document AI — enterprise version deduplication and LLM-based artifact generation
2
papers here
2
reviewed by Evolve
0
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 data is available yet: the record holds only two 2026 arXiv preprints, with no publication counts or venue history. This axis would measure annual paper volume and venue breadth once a fuller bibliographic record exists.
Impact—
Impact cannot be scored: no citation counts, h-index, or download statistics were provided for either preprint. This axis would measure citation uptake and scholarly influence as the two 2026 papers accumulate readership.
Focus0/100
The computed focus score is 0, driven by the raw field distribution splitting evenly at 0.5/0.5 between 'natural language processing' and 'natural language processing (document AI / applied LLM systems)'. Read substantively, both cataloged 2026 papers target the same enterprise document-governance problem space, so the low score reflects the metric's even split across two overlapping labels rather than genuine topic scattering; with only two papers, this axis remains unstable.
Collaboration32/100
The collaboration score is 32, computed from four distinct coauthors. All four recur as frequent collaborators — Mohammadreza Sediqin, Sumukha Thoppanahalli, Abhishek Mukherji, and Srinivasa Karthikeya Reddy Kovvuri — indicating a small, stable working group. On both 2026 papers Dalmia sits in a middle authorship position without corresponding-author credit, consistent with a contributor role inside a compact team rather than an independent or led effort.
Activity—
Activity data is insufficient: with only two 2026 preprints and no year-by-year publication series, no cadence can be computed. This axis would measure publishing tempo — papers per year and gaps between releases — across a longer observation window.
Reproducibility20/100
Reproducibility scores 20, the mean over two assessed papers, both rated low readiness. GVD reports strong F1 on a private enterprise corpus without independent reproduction, and SAGE's evaluation rests on proprietary data and proxy metrics. Neither paper currently ships the artifacts needed for external verification, so replication depends on future data or code release.
Research summary
Shivali Dalmia is an early-stage profile built from public bibliographic data, centered on natural language processing applied to enterprise document systems. The reviewed record consists of two 2026 arXiv preprints: GVD, on governed versioning and deduplication for document repositories, and SAGE, on governed artifact generation from enterprise guidelines. The field distribution splits evenly (0.5/0.5) between natural language processing and its document AI / applied LLM systems branch, matching a coherent research thread: bringing rule-level governance, conflict handling, and human oversight to LLM-driven document workflows. On both papers Dalmia appears in a middle authorship position without corresponding-author credit, working within a compact circle of four distinct coauthors, including Mohammadreza Sediqin, Sumukha Thoppanahalli, Abhishek Mukherji, and Srinivasa Karthikeya Reddy Kovvuri. Evolve's reproducibility assessment averages 20 across the two papers, with both rated low readiness because evaluations rest on private enterprise corpora and proxy metrics. Output, impact, and activity dimensions currently lack sufficient data for scoring; no citation counts, venue records, affiliation, or ORCID were available, so this profile should be read as an early snapshot of a focused applied-NLP collaborator rather than a mature bibliometric record.
Collaboration pattern
Dalmia works within a compact cluster of four distinct coauthors — Mohammadreza Sediqin, Sumukha Thoppanahalli, Abhishek Mukherji, and Srinivasa Karthikeya Reddy Kovvuri — all recurring as frequent collaborators. Middle authorship on both 2026 papers and no corresponding-author credit suggest a contributor role in a small applied document-AI team; the collaboration score of 32 reflects this narrow but stable pattern.
Research keywords
Highlights
GVD: governed versioning and deduplication without LLMs
SAGE cuts guideline-to-artifact work from days to about an hour
Timeline
- 2026GVD, on governed versioning and deduplication for document repositories, is released as an arXiv preprint.
- 2026SAGE, on governed artifact generation from enterprise guidelines, is released as an arXiv preprint.
- 2026Both preprints enter the Evolve review catalog, each rated low reproducibility readiness with a mean score of 20.
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 indicators come from a limited OpenAlex-based snapshot; no citation counts, h-index, or venue-tier data were available.
- No institutional affiliation, country, or ORCID could be confirmed; the profile is name-resolved from public bibliographic data.
- Only two 2026 arXiv preprints are in the reviewed catalog, so output, impact, and activity axes remain unscored.
- Both papers evaluate on proprietary enterprise corpora, so reported results cannot be independently verified.