Jeenal Chaudhary

Indian Institute of Technology Jodhpur · India

Unclaimed · AI-structured profileOpenAlex

AIOps researcher at IIT Jodhpur building reproducible on-premise LLM pipelines for root cause analysis in cloud systems

papers here

reviewed by Evolve

first-author

corresponding

—

works · OpenAlex

h-index · OpenAlex

Bibliometric figures come from OpenAlex (2026-10-15) 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: OpenAlex reports h-index 0 and i10-index 0 with only 3 recent works, so cumulative publication volume is too thin to measure. This axis would track total output and its year-over-year growth across the indexed record.

Impact—

Not yet scored: no citation data is available (h-index 0, i10-index 0) and both catalog papers are recent 2026 preprints. This axis would measure citation counts, downstream uptake, and influence on subsequent research.

Focus0/100

The radar focus score is 0, reflecting an indexed record too small to establish a stable topical signature: only 3 works in the last 3 years. What exists is nonetheless coherent — OpenAlex field distribution splits evenly (0.5/0.5) between two adjacent AIOps subfields, and topics cluster on topic modeling, software engineering research, and software system performance and reliability.

Collaboration22/100

Collaboration scores 22, consistent with a small-team working mode: OpenAlex records only 2 distinct coauthors, with Rohit Patel and Susil Kumar Mohanty as recurring partners. On both reviewed papers the researcher appears in the last author position (non-corresponding), a pattern typical of a senior supervising role within a compact group rather than a large distributed consortium.

Activity40/100

Activity scores 40 on a young record: OpenAlex countsByYear shows 3 works, all in 2026, and recent3yWorks is 3. There is no indexed activity before 2026, so the score reflects a short but current publication window rather than sustained multi-year output; both catalog papers appeared as 2026 arXiv preprints.

Reproducibility100/100

Reproducibility scores 100 — the strongest signal in this profile. Both cataloged papers carry high reproducibility readiness and a reproMean of 100 across 2 repro-scored papers. Evolve's verdicts describe the TriFleetRCA evaluation as reproducible with honest small-scale statistics (n=100, wide confidence intervals), and TriCalRAG as including good calibration analysis, indicating transparent artifact and evaluation practice.

Research summary

Jeenal Chaudhary is a researcher at the Indian Institute of Technology Jodhpur (India) whose indexed work centers on AI for IT operations (AIOps), specifically root cause analysis powered by on-premise large language models. The Evolve catalog contains two 2026 arXiv papers, both with the researcher in the last author position: TriFleetRCA, which performs single-GPU on-premise LLM root cause analysis for Kubernetes and scores 0.85–0.95 across 4 injected faults (n=100), and TriCalRAG, a three-strategy retrieval-augmented benchmark showing that RAG stabilizes LLM log-anomaly detection that degenerates zero-shot, with good calibration analysis. OpenAlex topics — topic modeling, software engineering research, software system performance and reliability, cloud computing and resource management, and security and verification in computing — reinforce this systems-and-AIOps orientation, and the field distribution splits evenly between AIOps/systems-and-security and AIOps/machine-learning-for-systems. The record is early-stage: h-index and i10-index are 0, only 3 works are indexed (all in 2026), and 2 distinct coauthors appear. Its clearest strength is reproducibility, with a perfect 100 score across both reviewed papers. This profile is name-resolved from public bibliographic data.

Collaboration pattern

The pattern is compact-team: OpenAlex records only 2 distinct coauthors, with Rohit Patel and Susil Kumar Mohanty as the recurring collaborators, and a collaboration dimension score of 22. On both reviewed papers Chaudhary sits in the last author position (non-corresponding), consistent with a supervising senior role on small, focused AIOps projects rather than large multi-institution consortia.

Research keywords

root cause analysisKuberneteson-premise LLM inferenceretrieval-augmented generationAIOpslog anomaly detectionLLM benchmarkingprompt injectioncloud computing and resource managementsoftware system reliability

Highlights

TriFleetRCA: single-GPU on-premise LLM root cause analysis for Kubernetes
The 2026 arXiv paper reports fault-injection evaluation over 4 injected faults with n=100 runs, scoring 0.85–0.95 on a single GPU without cloud dependency; Evolve notes an honest small-scale evaluation with wide confidence intervals and one toy attack scenario, rated reproducible.
TriCalRAG: three-strategy RAG benchmark for on-premise LLM-based AIOps RCA
The companion 2026 benchmark compares three retrieval-augmented strategies for root cause analysis, showing that RAG stabilizes LLM log-anomaly detection that otherwise degenerates zero-shot on a single GPU; Evolve highlights solid calibration analysis while cautioning on small scale and same-pool retrieval inflation risk.
Perfect reproducibility score across the reviewed record
Evolve rates reproducibility readiness as high for both cataloged papers, yielding a reproMean of 100 over 2 scored papers and a reproducibility dimension score of 100 — the profile's strongest quantitative signal.

Timeline

2026TriCalRAG appears on arXiv: a three-strategy, retrieval-augmented benchmark for on-premise LLM-based root cause analysis in AIOps.
2026TriFleetRCA appears on arXiv: on-premise LLM root cause analysis for Kubernetes, evaluated over 4 injected faults (n=100).
2026OpenAlex indexes 3 works for this researcher in 2026, with 2 distinct coauthors, establishing an early-stage bibliometric record.

Papers in the Evolve catalog

Frequent co-authors

Rohit Patel×2 Susil Kumar Mohanty×2

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 drawn from OpenAlex only; no ORCID is linked, so identity is name-resolved from public bibliographic data.
Citation impact is not yet measurable (h-index 0, i10-index 0); the output and impact radar axes are unscored.
Only two Evolve-reviewed papers exist, both 2026 arXiv preprints; this early-stage profile may not reflect the complete publication record.
Dimension scores come from a small indexed snapshot (3 works, 2 distinct coauthors) and should not be read as peer evaluation.