AI Peer Review

Better reviews, better science. Calibrated, citation-grounded reviews with humans in the loop, kept yours to edit, share, and publish.

Get your first reviewSee example reviewPurpose statementData policyRun a pilot

In this work, we model the risk of hospitalization for a large number of drug-disease combinations. Our methodology is akin to genome-wide association studies (GWAS), in which a simple model is used to estimate the effect of a large number of loci in a hypothesis-free manner. As in GWAS, this screen risks spurious relationships and requires further analysis, but complements target-driven repurposing.

observationIntroduction, p.2

The GWAS analogy is one of the clearest framings in the paper. It belongs in the abstract. A short sentence on the broad enumeration step and the multiplicity correction does enough to place the work as a screen, not another pair-specific observational study.

weaknessCox Regression, p.6

§2.5 and the Discussion already concede that dosage, duration, and switching aren't in the data. Even so, the paper keeps calling this a treatment-effect screen. Either tone the language down to a baseline-exposure association screen, or add landmark sensitivity analyses at 1, 3, 5, and 10 years.

Humans in the loop

Our reviews update with your comments. Iterate together until the review completely reflects your read.

EvaluateAnnotateRecommend

Consistent, benchmarked, multi-faceted scores

Publications are graded based on multiple aspects, including the novelty of the work, the quality of the presentation, and experimental rigor.

1,971 graded papers

066.1Median100

Research intelligence

We evaluate thousands of publications every week.
See our reports on

X Bluesky LinkedIn AIPR

See full map

Some of this week's best preprints

More on rankings

#	Paper	Score
1 Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends 84.9 Jiuming Liu et al.Computer Vision	1	Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends Jiuming Liu et al.Computer Vision	84.9
2 On Thin Perfect Matchings up to Polylogarithmic Factors 77.5 Alireza Haqi, Shayan Oveis GharanDiscrete Mathematics	2	On Thin Perfect Matchings up to Polylogarithmic Factors Alireza Haqi, Shayan Oveis GharanDiscrete Mathematics	77.5
3 ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving 77.4 Seokjin Go et al.Computer Architecture	3	ViBE: Co-Optimizing Workload Skew and Hardware Variability for MoE Serving Seokjin Go et al.Computer Architecture	77.4
4 LeAP: Learnable Adaptive Permutation for Feature Selection in Heterogeneous and Sparse Recommender Systems 77.2 Yihong Huang et al.Machine Learning	4	LeAP: Learnable Adaptive Permutation for Feature Selection in Heterogeneous and Sparse Recommender Systems Yihong Huang et al.Machine Learning	77.2
5 PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects 75.3 Sicheng Yang et al.AI	5	PolySpeech-100: A Large-Scale Benchmark for Speech Understanding Across 100+ Languages and Dialects Sicheng Yang et al.AI	75.3
6 HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces 74.6 Nasib Ullah et al.Machine Learning	6	HASTE: Hardware-Aware Dynamic Sparse Training for Large Output Spaces Nasib Ullah et al.Machine Learning	74.6
7 EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates 74.5 Mocheng Li et al.Databases	7	EMA: Approximate Nearest Neighbor Search with General Attribute Filtering and Dynamic Updates Mocheng Li et al.Databases	74.5
8 Hypergraph backboning 74.3 Alec Kirkley et al.Network Science	8	Hypergraph backboning Alec Kirkley et al.Network Science	74.3
9 SCOPE: Cost-Efficient Model Selection for Compound AI Systems under Quality Constraints 74.1 Yiqian Huang et al.AI	9	SCOPE: Cost-Efficient Model Selection for Compound AI Systems under Quality Constraints Yiqian Huang et al.AI	74.1
10 FVSpec: Real-World Property-Based Tests as Lean Challenges 74.0 Quinn Dougherty et al.Software Engineering	10	FVSpec: Real-World Property-Based Tests as Lean Challenges Quinn Dougherty et al.Software Engineering	74.0

Get your work graded

Your first review is free. Pay as you go or subscribe for additional features.

Create free account See plans Contact us