Abhishek Mukherji
—
Language-technology researcher spanning Southeast Asian audio reasoning benchmarks and enterprise document versioning
2
papers here
2
reviewed by Evolve
0
first-author
0
corresponding
—
works · OpenAlex
—
h-index · OpenAlex
Bibliometric figures come from OpenAlex (2026-10-12) 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—
Not yet scored: the snapshot contains only two cataloged 2026 preprints, with no publication counts, venue history, or yearly output volume. This axis would measure total and per-year production once a fuller bibliographic record is linked.
Impact—
Insufficient data to score: no citation counts, h-index, or downstream usage are present in this snapshot. This axis would measure citation influence and uptake of the two preprints once citation records become available.
Focus0/100
Focus scores 0/100, the lowest band on the radar. The raw field distribution is an even 0.5/0.5 split between natural language processing and speech/NLP (audio-language models), matching the two cataloged 2026 papers - one on document versioning, one on an audio reasoning benchmark. The profile is therefore dual-track rather than concentrated, though only two papers underlie the measure.
Collaboration50/100
Collaboration scores 50/100 with 11 distinct co-authors recorded across the two cataloged papers. The pattern is a compact, recurring core team - Mohammadreza Sediqin, Shivali Dalmia, and Sumukha Thoppanahalli appear most frequently, joined by Harshit Rajgarhia, Asif Shaik, Rachuri Lokesh, and Sushanta Kumar Pani - with Mukherji in the last-author position on both preprints.
Activity—
Not scored: the snapshot lacks publication timestamps beyond two 2026 preprints, so yearly cadence and recent-activity trends cannot be computed. This axis would measure publishing frequency and research momentum over time once a longer publication history is available.
Reproducibility38/100
Reproducibility scores 38/100, the mean across two scored papers. SEABED is rated medium: rigorous ablations support it, but gold answers are LLM-authored without human validation. GVD is rated low: results come from a private enterprise corpus and are not independently reproducible.
Research summary
Abhishek Mukherji is a researcher working across two complementary strands of language technology: natural language processing for enterprise document management, and speech and audio-language modeling with a focus on low-resource Southeast Asian languages. Evolve's catalog lists him as last author on two 2026 arXiv preprints. The first, GVD, unifies version-family linking and rule-level conflict governance for document repositories without relying on large language models, reporting strong F1 on a private enterprise corpus; Evolve notes it is not independently reproducible. The second, SEABED, is a reasoning-first benchmark for evaluating audio reasoning across Southeast Asian languages, where the best evaluated model reaches 50.3%; Evolve credits its rigorous ablations while cautioning that LLM-authored gold answers and the absence of human validation temper its conclusions. Bibliometrically, his cataloged output splits evenly (0.5/0.5) between natural language processing and speech/NLP (audio-language models), and he works within a compact, recurring team: 11 distinct co-authors, with Mohammadreza Sediqin, Shivali Dalmia, and Sumukha Thoppanahalli appearing most frequently. Radar assigns mid-range collaboration (50/100) and low reproducibility (38/100, the mean across two scored papers), while output, impact, and activity axes remain unscored for lack of data. This is an early-stage, name-resolved profile built from a small public bibliometric snapshot; no institution, country, or citation data were available.
Collaboration pattern
Mukherji's cataloged papers share a compact, recurring author core: Mohammadreza Sediqin, Shivali Dalmia, and Sumukha Thoppanahalli head the frequent-coauthor list, alongside Harshit Rajgarhia, Asif Shaik, Rachuri Lokesh, and Sushanta Kumar Pani. The radar records 11 distinct co-authors and scores collaboration at 50/100. He sits in the last-author position on both 2026 preprints, consistent with a senior or supervisory seat within a small, stable team rather than a wide external network.
Research keywords
Highlights
SEABED: a reasoning-first audio benchmark for Southeast Asian languages
GVD: governed versioning and deduplication without LLMs
Timeline
- 2026Published GVD on arXiv as last author - a governed versioning and deduplication framework for enterprise document repositories.
- 2026Released SEABED on arXiv as last author - a reasoning-first benchmark for evaluating audio reasoning in Southeast Asian languages.
- 2026Appeared as last author on two arXiv preprints in the same year, split evenly between natural language processing and audio-language modeling, with 11 distinct co-authors recorded.
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.
- Profile is name-resolved from public bibliographic data; no institution, country, or ORCID was available, and the name Abhishek Mukherji is common, so identity confidence is limited.
- Coverage is limited to two 2026 arXiv preprints reviewed by Evolve; earlier, venue-published, or other work is not represented in this snapshot.
- Output, impact, and activity radar axes are unscored because publication counts, citations, and activity history are absent from the input data.
- Reproducibility (38/100) and collaboration (50/100) scores come from Evolve's bibliometric radar over this small snapshot and may shift as more papers are added.