collaborators

14 papers

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…

cs.CL2026

Knowledge-Graph Grounding Helps LLMs Only for Out-of-Training Knowledge: A Controlled Study on Clinical Question Answering

Madhulatha Mandarapu, Sandeep Kunkunuru

A recent Nature Medicine study reports that general-purpose frontier LLMs outperform specialized retrieval-augmented clinical tools on medical benchmarks, and that retrieval can hu…

cs.DB2026

When Is a Columnar Scan Bandwidth-Bound? A Decode-Throughput Law and Its Cross-Hardware Validation

Madhulatha Mandarapu, Sandeep Kunkunuru

A columnar scan that decompresses, filters, and aggregates should be limited only by memory bandwidth (the roofline floor T >= BytesRead/beta), yet real kernels are often compute-b…