Research on quality control in crowdsourcing, consensus protocol design for proof-of-stake networks, tooling for AI coding agents, and the software and datasets that came out of all three.

Protocols & technical reports

The Proof of Reputation protocol

A validator-selection algorithm that weights blockchain validators by earned, context-dependent reputation rather than stake alone. Designed on Cosmos SDK/Tendermint.

Ki Foundation technical report, 2019 (with J. Guyomard and R. Berrehili)

Assessing decentralization in DPoS environments

A quantitative look at how decentralized delegated proof-of-stake networks actually are.

Ki Foundation technical report, 2019 (with J. Guyomard and R. Berrehili)

Publications

CrowdED and CREX: Towards Easy Crowdsourcing Quality Control Evaluation

ADBIS 2019, Bled, Slovenia (with N. Bennani, V. Rehn-Sonigo, L. Brunie, H. Kosch)

Efficient Worker Selection Through History-Based Learning in Crowdsourcing

COMPSAC 2017, Turin, Italy (with N. Bennani, K. Ziegler, V. Rehn-Sonigo, L. Brunie, H. Kosch)

Task Characterization for an Effective Worker Targeting in Crowdsourcing

HASE 2016, Orlando, USA (with N. Bennani, L. Brunie, D. Coquil, H. Kosch, V. Rehn-Sonigo)

Context-aware worker selection for efficient quality control in crowdsourcing

PhD thesis, INSA de Lyon, 2018

Software & datasets

Check Your Agent

Source-available forensics for AI coding-agent spend. Analyzes Claude Code sessions for usage patterns, errors, and token costs (late compaction, oversized tool results, redundant re-reads), free for personal and internal use. Source on GitHub.

claude-ux-framework

A Claude Code skill that makes coding agents do the UX work before writing UI code: an enforced process with sourced rules, validated by scoring with-skill and without-skill builds of the same prompt against a 30-check audit. MIT licensed.

CrowdED

A crowdsourcing evaluation dataset: 300K+ contributions from 400 workers over 1,000+ questions and 500+ tasks, with declarative worker profiles and self-evaluations across knowledge domains.

CREX

CReate, Enrich, eXtend: a framework for building and extending crowdsourcing datasets, with clustering-based task selection and campaign-site generation.

WSP (Worker Selection Platform)

Learns offline which worker profiles are reliable for which task types, then selects workers online from the available crowd.

Talks

Conference talks at HASE 2016 (Orlando), COMPSAC 2017 (Turin), and ADBIS 2019 (Bled), and a series of IRIXYS workshop talks (2014–2018, France/Germany/Italy) on quality control in crowd computing.