Lists (1)
Stars
Estimating willingness to pay for Vaastu compliance in Indian residential real estate.
Use Kalman Filters for Event Study Designs
Estimating the wrong pairameter. Numbers may differ in the blog because of seed.
Dynamic E2E Agentic Simulation and Evaluation with Cypress
Calibrating pairwise rankings with accomodations for non-transitivity
slosizer: Right-size reserved LLM capacity Based on SLO
From Scores to Signs: Pairwise Win-Rate Estimation with Calibrated LLM Judges
Missing Women On the Streets: Evidence from Mumbai
A Python library for extracting structured information from unstructured text using LLMs with precise source grounding and interactive visualization.
A follow-up to https://github.com/geosensing/streetsense We use Google Street View to assess quality of public infra. and missing women
An open-source Text2SQL tool that transforms natural language into SQL using graph-powered schema understanding. Ask your database questions in plain English, QueryWeaver handles the weaving.
A collection of my favorite custom Claude Code resources to make life easier.
Opinionated Python Package Checklist and Helper. Devtools for Python
A small, well-typed LLM-based reranker for semantic search.
Official repository for "Action-Based Conversations Dataset: A Corpus for Building More In-Depth Task-Oriented Dialogue Systems"
Context layer platform in your infrastructure
A GitHub Action that automatically synchronizes Citation File Format (CFF) files with PEP 621 metadata from pyproject.toml.
Build two-stage models when your features arrive in two batches at different times.
Minimal keys and row-wise value-of-information for disambiguating tabular records
Agent for cleaning your mac, e.g., cleaning up cache, etc.
Polling station location, some metadata, and photos for Bihar 2025
codebase to detect and OCR pdfs of variable quality and generate embeddings for downstream research tasks
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Open-source library for scalable, reproducible evaluation of AI models and benchmarks.