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

Examples

Example research

Each study below was run through the pipeline on real data and written to the conventions of a leading journal in its field. Every artifact is kept: sources, ideas, executed code, results, manuscript and referee report.

Stages
6
Human gates
2
Disciplines
9
Example papers
10

Example research by discipline

One complete study per discipline, each analysing a real public dataset and written to the conventions of the field's leading journal, with every artifact preserved: sources, ideas, executed code, results, manuscript and referee report.

Social Sciences & Business

  1. Finance

    Modelled on Journal of Finance

    963f889ffb6824 October 2026Complete

    Volatility Management from Monthly Returns versus Factor Momentum: The Fama-French Market, Size, and Value Factors, 1926–2026

    Do volatility-managed factor portfolios survive real-time implementation and a horse race against time-series factor momentum? A century of US market, size and value factors

    Review: Accept · Novelty 3/5 · Rigor 4/5 · Clarity 4/5 · Reproducibility 5/5

  2. Economics

    Modelled on American Economic Review

    ad07220e3e3724 October 2026Complete

    Where Proximity Bites: Margin Weighting and the IV–OLS Gap in the Return to Schooling

    Why is the college-proximity IV estimate of the return to schooling nearly twice the OLS estimate? Testing whether the gap is an Angrist-Imbens margin-weighting artefact

    Review: Accept · Novelty 3/5 · Rigor 4/5 · Clarity 4/5 · Reproducibility 5/5

  3. Psychology

    Modelled on Psychological Science

    d0124d4c52b024 October 2026Complete

    Four Big Five Domains Do Not Carry All of Their Items' Age Differences: A Loading-Based Test in 25 IPIP Items

    Are age differences in personality domain-general or nuance-specific? Testing whether Big Five domain scores capture the age-related information carried by their own items

    Review: Accept · Novelty 3/5 · Rigor 4/5 · Clarity 4/5 · Reproducibility 5/5

  4. Management Science & Operations

    Modelled on Management Science

    eae11b02ad5224 October 2026Complete

    Contact Fatigue or Dynamic Selection? Decomposing the Declining Conversion Hazard in Repeated Telemarketing and Designing Client-Specific Stopping Rules

    Contact fatigue or dynamic selection? Decomposing the declining conversion hazard across repeated telemarketing contacts and designing client-specific stopping rules

    Review: Accept · Novelty 3/5 · Rigor 4/5 · Clarity 4/5 · Reproducibility 5/5

Health Sciences

  1. Biostatistics

    Modelled on Statistics in Medicine

    418fc309f9c124 October 2026Complete

    Does prespecified Cox adjustment really buy power over the log-rank test? A real-data resampling study of the NCCTG adjuvant colon cancer trial

    Does prespecified covariate adjustment in the Cox model really increase power over the unadjusted log-rank test in a randomised survival trial? A real-data resampling study of the NCCTG adjuvant colon cancer trial

    Review: Accept · Novelty 4/5 · Rigor 4/5 · Clarity 4/5 · Reproducibility 4/5

  2. Epidemiology & Public Health

    Modelled on American Journal of Epidemiology

    10fc99e0506824 October 2026Complete

    Infant–Adult Differences in SARS-CoV-2 Cycle Threshold Values and the Limits of Deidentified Testing Records: A Cross-Sectional Analysis

    Do children under 5 years have higher SARS-CoV-2 upper-respiratory viral loads (lower RT-PCR cycle threshold values) than adults, once testing setting and calendar time are accounted for?

    Review: Accept · Novelty 3/5 · Rigor 4/5 · Clarity 4/5 · Reproducibility 4/5

Physical Sciences & Engineering

  1. Physics

    Modelled on Physical Review Letters

    ce7d9f52749224 October 2026Complete

    Phase Diffusion, Not a Clock: A Calibrated Likelihood Test of the Sunspot-Cycle Phase

    Does the solar activity cycle keep time like a clock, or does its phase perform a random walk? A likelihood test on sunspot-cycle minima epochs in the SILSO v2.0 record with propagated measurement uncertainty

    Review: Accept · Novelty 3/5 · Rigor 4/5 · Clarity 4/5 · Reproducibility 4/5

  2. Computer Science — Machine Learning

    Modelled on NeurIPS

    4689bab459a324 October 2026Complete

    Calibrate or Tune? Cost-Sensitive Decision Thresholds as Estimators on Spambase

    Under asymmetric misclassification costs, does post-hoc probability calibration with the theoretical cost-optimal threshold beat directly tuning the decision threshold on the same held-out validation data?

    Review: Accept · Novelty 3/5 · Rigor 4/5 · Clarity 4/5 · Reproducibility 5/5

From the user's own data

A study that began with a data file instead of a question. The pipeline profiled the file, the owner confirmed what each column means, and the pipeline proposed the question and wrote the paper, pausing for the owner where needed. The data are reported as the user supplied them, not independently verified.