Evaluate Research Ideas with AI Precision

Four fine-tuned models. Calibrated assessments. Actionable feedback.

Idea Gatekeeper harnesses four fine-tuned AI models -- GPT-4.1, GPT-4.1-nano, OB-30B, and OB-4B -- trained on 10,000+ editorial decisions, to evaluate your research concepts on Novelty and Usefulness, delivering calibrated tier ratings and actionable improvement suggestions.

Begin Evaluation

Trusted by researchers to evaluate ideas before committing resources

4
Fine-Tuned Models
83%
High Confidence Accuracy
10K+
Training Papers

How It Works

01

Describe

Present your research idea in natural language, at any stage. You can even work with AI to refine it.

02

Evaluate

Four fine-tuned AI models independently assess Novelty and Usefulness.

03

Synthesize

Receive calibrated tier ratings with detailed probability analysis and improvement suggestions.

Calibrated Tier Ratings

Every idea is placed on a four-tier scale anchored to real-world journal standards.

Top

Premier journals such as AMJ, AMR, ASQ, JAP, Org Science, SMJ. Exceptional research potential with high novelty and usefulness.

Top-

Near-premier journals such as JOM, OBHDP, PPsych. Strong foundations with clear merit and minor refinements needed.

Good

Mid-tier field journals. Solid concept with identifiable strengths that benefits from targeted iteration.

Fair

Lower-tier journals. Early-stage idea requiring further development, with feedback highlighting key areas for improvement.

“The gap between a good idea and a great one is often just the right feedback at the right time.”

Latest Updates

What we have been building

April 1, 2026
Economics 30B Model & Mobile Updates

Added Econ-30B local model (Qwen3-30B A3B) for economics evaluation. Economics domain now uses 2-model ensemble (GPT-4.1-nano + Econ-30B). Mobile chat reliability improved with timeout handling and error recovery. Admin analytics dashboard launched with live confidence distribution charts.

Feature
March 29, 2026
3-Model Probability Ensemble

Ensemble tier prediction now uses 3-model probability averaging (GPT-4.1, GPT-4.1-nano, OB-30B). OB-4B retains the best individual accuracy (59.2%) and participates in consensus voting, but its probability distributions are excluded from the ensemble average due to overconfidence -- improving calibration by +9.1pp at high confidence thresholds.

Update
March 28, 2026
UI Overhaul & Mobile Responsive

Full UI redesign with login animation, navigation restructure, Idea Lab 3-tab layout, chat split panel, and mobile-responsive breakpoints.

Update
March 28, 2026
Economics Model Added

A new SFT model trained on economics editorial decisions is now available. Select Management or Economics before submitting an evaluation.

Feature
March 27, 2026
Idea Lab Launched

Blind-rate AI-generated research ideas, earn credits for accuracy, and compete on the leaderboard. 200 ideas seeded at launch.

Launch

About the Platform

Built at Tsinghua University

Idea Gatekeeper is developed by Professor LI Ning and the research group at Tsinghua University, focused on the intersection of artificial intelligence and scientific evaluation. Our work demonstrates that AI can learn the tacit evaluative judgment -- "scientific taste" -- that guides editorial decisions.

LN
Prof. LI Ning
Principal Investigator

Mission

Advance AI for science by building tools that facilitate and accelerate the research process. We aim to democratize access to evaluative feedback that was previously available only through lengthy peer review cycles.

Research Foundation

The underlying methodology is detailed in our paper "Machines acquire scientific taste from institutional traces" which benchmarks SFT models against 48 expert journal editors and 174 doctoral researchers, using 120 held-out papers with known publication outcomes.

Read the full paper