Auto-Research PipelineA durable, human-gated pipeline for computational research

Interactive demonstration

A durable, human-gated auto-research pipeline

Pose a research question. The pipeline reviews the literature with live search, proposes testable ideas and pauses for you to choose one; it then writes and executes an experiment, analyses the results, drafts a manuscript, reviews it, and pauses again for your sign-off. Every stage is checkpointed, and a run may wait at a gate for as long as you like.

How it works

  1. 01

    Literature review

    A Google-Search-grounded review with real sources: key papers, methods in use and open gaps.

  2. 02

    Ideation

    Human gate

    Ranked candidate studies, each with a falsifiable hypothesis and a small computational test plan.

  3. 03

    Experimentation

    The model writes a self-contained Python experiment; it runs in an isolated sandbox, with a repair loop on failure.

  4. 04

    Analysis

    An honest results section — verdict, key numbers, caveats. A failed run is reported as failed.

  5. 05

    Paper writing

    A workshop-style manuscript that cites only retrieved sources and reports only executed configurations.

  6. 06

    Review

    Human gate

    A strict automated review with 1–5 scores and required changes.

Why the gates matter

In the archived run below, the first manuscript draft reported 10,000 Monte Carlo trials while the executed script ran 200. The reviewer at the gate sent it back; the pipeline now hands the executed script to the writer and reviewer as ground truth, and the revised paper came back correct. The pipeline is designed to surface exactly that kind of discrepancy, not hide it.

Completed runs

Archived runs with every artifact: sources, ideas, code, results, manuscript and review.

  1. e8905fccdf4b1 September 2026Complete

    Does simple majority voting over a few noisy weak classifiers reliably beat the best single classifier?

    Paper: On the Fallacy of Instance Difficulty as a Necessary Boundary for Voter Dilution in Majority Ensembles

    Review: Accept · Novelty 3/5 · Rigor 5/5 · Clarity 5/5 · Reproducibility 5/5

Live demonstration

Start a live run

A research question that a small computational experiment could inform. The run pauses at two human gates: you pick the idea, and you sign off on the reviewed manuscript.

Questions in English work best with the current prompts.

Examples
Literature review and ideation take about a minute before the first gate.