Human Capital, Not Model Benchmarks, Predicts Hybrid Intelligence in Forecasting

Source

• Source name: arXiv
• Source kind: paper
• Authors / organization: Vivienne Ming
• Venue: arXiv: cs.CY
• Published: 2026-07-02
• Collected: 2026-07-03
• URL: http://arxiv.org/abs/2607.02467v1
• PDF: https://arxiv.org/pdf/2607.02467v1
• DOI: UNKNOWN

Plain-Language Brief

The study examines the performance of human-AI collaboration in forecasting using real-money prediction markets as a benchmark. It finds that the effectiveness of this collaboration is dependent on a specific type of human capital, namely collaborative traits like perspective-taking, intellectual humility, and curiosity. The results suggest that these individuals can reach accuracy levels matching or even exceeding the market itself.

What the Document Says

• The performance of human-AI collaboration in forecasting is analyzed using a real-money prediction market as a benchmark.
• The study finds that the value of human-AI collaboration depends on a specific, measurable form of human capital.
• Hybrid performance among individual forecasters is found to be trimodal: most defer to the model, some use it to rubber-stamp prior guesses (performing worse), while a minority engage in complementary reasoning and reach accuracy equal to or better than the market.
• Collaborative traits (perspective-taking, intellectual humility, and curiosity) distinguish those who reach the mode of genuine complementary reasoning.
• The results are preliminary but statistically robust.

Key Concepts Mentioned

• human-AI collaboration
• forecasting
• real-money prediction market
• hybrid performance
• collaborative traits
• perspective-taking
• intellectual humility
• curiosity

Claims Made by the Document

• The value of human-AI collaboration depends on a specific, measurable form of human capital.
• Individuals with collaborative traits can reach accuracy levels matching or exceeding the market in hybrid forecasting.

Evidence Used

• Analysis of individual forecasters' performance using real-money prediction markets as a benchmark

Methods / Approach

• Analyzing individual forecasters' performance in a real-money prediction market

Limitations Stated by the Authors

The results are preliminary

Limitations Noted by the Agent

Agent interpretation — not from the source.

The study is a pilot, and the results need to be replicated for confirmation.

Open Questions

• What is the specific, measurable form of human capital that leads to successful human-AI collaboration in forecasting?

Notes for Future Q&A

May include interpretation. Labeled where it does.

The text does not provide information on what the specific, measurable form of human capital might be.

Raw Abstract / Excerpt

Whether pairing people with AI helps or hurts is usually reported as a single average effect. Using a real-money prediction market (Polymarket) as an objective, externally resolved benchmark, this pilot shows that the value of human-AI collaboration depends on a specific, measurable form of human capital. Analyzed at the level of the individual forecaster, hybrid performance is trimodal: most people either deferred to the model (matching it) or used it to rubber-stamp a prior guess (performing worse than the model alone), while a minority engaged in genuine complementary reasoning and reached accuracy matching or even exceeding (i.e., lower error than) the market itself. Collaborative traits (perspective-taking, intellectual humility, and curiosity) rather than raw cognitive ability or model benchmarks, distinguished who reached that mode. The results are preliminary but statistically robust, and motivate a pre-registered replication now in preparation.