Search awesome repositories

Emulating the ED global land-ecosystem model for the IEEE BigData Cup 2026: the anchor that beat every trained model, and the measured rejection of H1.

Reliability by construction for long-horizon healthcare agents on χ-Bench (IEEE Big Data Cup 2026, Challenge 07): contract-checklist hooks, critic panel and closure gate on the official Claude Code harness.

ClimX distributional climate emulator adaptation with bounded-memory prediction, upstream attribution and exact numerical-equivalence checks.

Deterministic research core for policy-change review; Codegeist 2026 companion.

Deadline-driven register, GPU capacity simulator and read-only audit tick for a research competition portfolio. By Francisco Angulo de Lafuente.

Structure-to-network developmental neurotoxicity triage agent with calibrated uncertainty (SciencePal AI4Science Hackathon 2026)

NAVAJO privacy gateway for JupyterHealth: reproducible synthetic-data benchmarks, clinical-text masking and explicit residual-risk reporting.

Pseudonymise clinical notes on the clinician's computer before any AI assistant, restore the answer. Pre-registered evaluation on MEDDOCAN (prototype, MIT Solve 2027).

MetFrag-assisted, leader-safe ranking of natural-product structures from MS/MS spectra — Enveda CASMI 2026 (Kaggle) entry with pre-registered experiments and animated figures

Evidence-linked funding-call review with Meterless H-MEM. Submitted 23 Oct 2026; dated Zetaris/Nightshift live-run evidence, synthetic sample mode and explicit operational limitations.

MiniCPM5-2B competition benchmark harness, numerical gates and three fixed experiment directions; official hardware evaluation pending.

Open bus-stop solar exposure application: tested synthetic geometry foundation, reproducible controls and transparent UDC2026 scope.

Holographic Neural Networks: Exploring Optical Raytracing for Efficient Computation

Acceleration of Language Models Through Simulated Holography and Raytracing

Online holographic-reservoir forecasts and gated PI control for the NeurIPS Smart Buildings Challenge; official simulator measurements and frozen prospective validation.

Autonomous, evidence-first engineering system for the BuildArena S02 (Besiege) Human-AI Engineering Challenge: rules-validated scorer, orbit/landing gates, isolated Autopilot agent run, submission packager.

Closed-loop tracking of actionable screening results with NAVAJO privacy for AI drafting. Prototype for the Future Health Digital Innovation Challenge (Challenge 05).

Causal Memecoins audit: frozen negative comparison, exact-source CPU baseline and reproducible source.

Reproducible public-data EEG BCI decoder for Neural Interfaces 2026 Track 02. Cross-subject PROTEUS evaluation, audited inference, official Codabench warmup score.

PLATEAU CityGML LOD2 urban solar irradiance computed the way a 3D engine computes light; validated against a Blender Cycles control under a pre-registered contract.

Rule-compliant Overture Maps coverage-gap estimator for 9,379 US tracts + a provenance bias discovery (Zindi x Humane Intelligence Bias Bounty)

Agent-native research lab: AI agents research, review each other and publish (P2PCLAW), with a pre-registered ablation of whether the peer review helps. Agent-Native Hackathon 2026.

Parallel, recoverable PostgreSQL expansion for the November research challenge.

QESN (Quantum Echo State Network) for MABe 2022 behavior analysis competition - V2

"QuBE: Illuminating the Path to Quantum-Optical Maze Mastery" Abstract This document introduces an innovative approach to solving mazes and complex optimization problems by combining advanced principles of optical and quantum physics within a three-dimensional neural processing system, the Quantum Beam Engine (QuBE).

Reproducible FeMoCo chemistry angle-loader compiler, scientific evidence and source-recovery tools. Francisco Angulo de Lafuente.

Reversible accumulation and qubit resource experiments; original Apache-2.0 research.

Airline satisfaction: stacked GBDT ensembles, Darwin-Cage residual diagnostics, complete experiment records and attributed public prediction sources.

Fold-safe ensembling to the honest ceiling of Kaggle Playground S6E9, and a Darwin-Cage residual search with a power analysis. Nested OOF 0.946420; 47,679 evolved programs, 0 discoveries.

A local Gemma 4 jury reads the first 10 steps of a SWE-agent run, predicts failure, and lets a fixed budget resolve 29% more issues. Pre-registered study, Gemma 4 Paper Track.