Progress

original paper

Predicting Empirical AI Research Outcomes with Language Models

Research outcome prediction authors · Published 2025-06-01

Read the original document ↗

Evidence from this source

Results and research linked to this document
TypeEvidence
ResultResearch outcome prediction · Fine-tuned GPT-4.1 plus paper retrieval
Source details

PDF Section 4.2, Table 4 and Figure 3; full test 1,585 pairs

ResultResearch outcome prediction · Unadapted GPT-4.1, Table 4 baseline
Source details

PDF Section 4.2, Table 4, GPT-4.1 row, physical page 5

ResultResearch outcome prediction · Fine-tuned GPT-4.1 plus paper retrieval
Source details

PDF Section 4.3, Figure 1, 45 NLP pairs

ResultResearch outcome prediction · Fine-tuned GPT-4.1 plus paper retrieval
Source details

PDF Section 6, 33 eligible unpublished pairs

BenchmarkResearch outcome prediction
Source details

PDF Sections 2–4 and 6; Tables 1–5; Figures 1 and 3

Paper / reportPredicting Empirical AI Research Outcomes with Language Models
Source details

Primary publication source

Document tracking details
Source ID
src-research-outcomes-2025
Source type
Primary
Original URL
https://arxiv.org/abs/2506.00794
Retrieved URL
https://arxiv.org/pdf/2506.00794
Last updated by publisher
Not reported
Access status
available
Retrieved
2026-09-28T17:53:28Z
Document fingerprint
c128ba568c22488160614eb1c3be2ecad88bb17442ff0577c0528bf968f61c3d
Based on original bytes. Used to detect changes to the source.

Availability checks

  • 2026-09-28T17:53:28Z · success: Primary source inspected for this local candidate.