System record

Fine-tuned GPT-4.1 plus paper retrieval

Organization: Research outcome prediction authors · base model: GPT-4.1

System and setup

Reported system information
Model versionnot reported
Software used to run the modelPaper retrieval agent + label-fine-tuned predictor
Software versionnot reported
Tools available to the modelTwo prediction orders; inconsistent order-swapped answers counted incorrect
Release dateNot reported

Autonomy assessments

No autonomy assessment is published for this system.

Published capability results

Benchmark and indicator evidence
MeasureVersionReported resultDate
Research outcome prediction1,585 later-paper idea pairs77.0%2025-06-01
Research outcome prediction45-pair NLP expert-comparison subset64.4%2025-06-01
Research outcome prediction33 scored unpublished prompting ideas63.6%2025-06-01

Related research

Additional system details
System ID
research-outcome-ft-gpt41
Organization
Research outcome prediction authors
Base model
GPT-4.1
Release date
Not reported
Assessment records
0
Recursive evidence records
0