title: Rishabh Patil
emoji: 馃攷
colorFrom: indigo
colorTo: blue
sdk: static
pinned: true
short_description: AI engineer and researcher. Models, data, papers.
tags:
- portfolio
- claim-verification
- text-to-sql
AI engineer and researcher in London. Co-founder and CEO of Valuren, which gives fashion and luxury brands digital product passports. I work on verification for AI: checking claims against evidence, evaluating LLM systems, and planning safely in learned latent spaces.
The page at the top of this Space pulls live download numbers from the Hub API.
VeriSci: scientific claim verification
Paste a scientific claim and get SUPPORTS, REFUTES or NOT ENOUGH INFO, with the sentences that justify the label.
| Piece | Repo |
|---|---|
| Live demo | verisci-claim-space (may take a minute to wake if idle) |
| Release verifier | verisci-claim-verifier-retrieval-adapted-seed123 |
| Retriever | verisci-scifact-e5-retriever |
| Ablations | Seeded variants of evidence selection (joint, evidence-gated, hard-negative, contradiction-adapted), each with its own model card |
SchemaSage-SQL: safe text-to-SQL
QLoRA adapters on Qwen3-4B that write read-only SQL grounded in the schema you give them, with a safety layer that refuses destructive requests.
| Piece | Repo |
|---|---|
| Release baseline | schemasage-sql-qwen3-4b-clean-balanced-200 |
| Larger candidate | schemasage-sql-qwen3-4b-clean-balanced-8k-600-v2: better exact match and execution accuracy, missed one blocked refusal, so not shipped |
| Dataset | schemasage-sql-clean-text2sql |
| Code | github.com/MrRobotop/schemasage-sql |
Research code
| Project | What it is | Links |
|---|---|---|
| toploss | Five optimiser-free PyTorch regularisers that rebuild SAM-style flat-minima effects as loss penalties |  Preprint |
| clap-family | Conservative Lapse-Action Planning for safe latent trajectory optimisation, 72 tests |  Preprint |
| micro-world-model | Hierarchical JEPA world model that plans in latent space without reconstruction or reward | Preprint |
| ariadne-eval | Tracing and scoring for multi-step LLM agents, 285 tests |  |
| evalforge | LLM evaluation with bootstrapped confidence intervals and a CI regression gate, 538 tests |  |
Background
MSc Artificial Intelligence, University of St Andrews (dissertation on dependent types for machine learning, supervised by Dr Edwin Brady). BSc Artificial Intelligence, VU Amsterdam.