# Evidence-Aware MapReduce for Forkable Compute

arXiv: https://arxiv.org/abs/2607.09689 · HTML: https://mlsanity.com/paper/2607.09689/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 5 of its 24 references that are in the map.
- First posted on arXiv 17 Jun 2026.

## Builds on (most cited first, 5 of 5)

- [Self-Consistency Improves Chain of Thought Reasoning in Language Models](https://mlsanity.com/paper/2203.11171/) (2022)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Benchmarking, Analysis, and Optimization of Serverless Function Snapshots](https://mlsanity.com/paper/2101.09355/) (2021)
- [Faasm: Lightweight Isolation for Efficient Stateful Serverless Computing](https://mlsanity.com/paper/2002.09344/) (2020)
- [Scalable and Efficient Statistical Inference with Estimating Functions in the MapReduce Paradigm for Big Data](https://mlsanity.com/paper/1709.04389/) (2017)

## Abstract (arXiv)

Snapshot-backed sandboxes make branching cheap while leaving evidence dependence unchanged. Branches can reuse a model, prompt, repository, tests, observations, or execution ancestor, so counting outputs can amplify one repeated error into high-confidence consensus. We introduce an evidence-aware reduction contract: each worker reports an estimate, estimated information, evidence identifiers, fork lineage, and execution metadata. For independent workers estimating one common parameter, we use standard inverse-information pooling in its Gaussian/Wald form. The fixed-dimensional numeric summary can merge in any tree order; evidence IDs and lineage follow separate rules. The residual Delta measures disagreement, becomes Cochran's Q in the scalar inverse-variance case, and appears in the product integral. A reference implementation validates serialized records, rejects repeated nonempty evidence identifiers, carries evidence and lineage through tree reduction, and uses Cholesky-based numerical linear algebra. Unit tests and seeded synthetic checks exercise the algebra, unequal information, and forged precision; one four-worker named-snapshot trace exercises the end-to-end path. Platform logs document the exercised execution paths. A central open systems challenge is to turn evidence identity and fork lineage into a dependence model for correlated and adaptively selected AI branches.