most citedOpen Biomedical Knowledge Graphs at Scale: Construction, Federation, and AI Agent Access with Samyama Graph Database

1 citations · 1 across the 15 of their papers we have counts for

collaborators

16 papers

cs.DB2026

Bounded, Indeterminate, or a Bug: A Condition-Aware Oracle for Differential Testing of SQL Aggregates

Madhulatha Mandarapu, Sandeep Kunkunuru

Differential database testing compares results across engines and calls a discrepancy a bug. For floating-point aggregates this is unsound: engines legitimately disagree because fl…

cs.CL2026

Removable and Irreducible: A Token-Cost Ledger for the Multilingual Tokenization Tax

Madhulatha Mandarapu, Sandeep Kunkunuru

Large language models pay a well-documented tax on non-English text: the same content costs several times more tokens, and because attention is quadratic in sequence length, far mo…

cs.DB2026

The Decode-Work Law: Margin-Governed, Provably-Exact Spatial Joins over Compressed Geometry

Madhulatha Mandarapu, Sandeep Kunkunuru

Filter-and-refine spatial joins have always avoided touching exact geometry for certified candidate pairs, but the field never modeled the decompression cost of the pairs that surv…

cs.DB2026

When to Repair a Graph ANN Index: A Matched-Budget Negative Result, and the Interpolated-Baseline Trap That Hid It

Madhulatha Mandarapu, Sandeep Kunkunuru

Graph approximate-nearest-neighbor (ANN) indexes (HNSW, DiskANN/Vamana) lose recall under insert/delete churn, because deletions orphan the greedy-search paths that route through r…

cs.DB2026

Knowledge Graphs as the Missing Data Layer for LLM-Based Industrial Asset Operations

Madhulatha Mandarapu, Sandeep Kunkunuru

LLM-based agents for industrial asset operations show limited accuracy when reasoning over flat document stores. AssetOpsBench (KDD 2026) establishes that GPT-4 agents achieve 65%…

cs.DB2026

One Index for Subsumption and Roll-up across Time, Geography, and Ontology

Madhulatha Mandarapu, Sandeep Kunkunuru

Time-series, geospatial, and ontology systems each maintain a hierarchy -- day <= month <= year, zip <= city, is-a / part-of -- and each indexes it in a separate silo. We observe t…