Analytics Dashboard

Research Insights

Explore trends and patterns in AI safety research with real-time analytics.

Category Trends Over Time

Click legend items to toggle categories on/off. Hover for details.

Alignment Theory trending +6%

Safety-Relevant Papers

1365

Days Tracked

17

Categories Used

10

Avg. Daily Papers

80

Research Velocity

Comparing Dec 24 - Jan 1 vs Dec 12 - Dec 23

Recent Period
↓ 11%
643 papers

vs 722 in previous period

Latest Day
↓ 24%
78 papers

Jan 1

Avg per Day
98 papers/day

across 14 active days

Gaining Momentum

Alignment Theory
270 → 287 ↑6%

Slowing Down

Governance & Policy
31 → 15 ↓52%
AI Control
35 → 19 ↓46%
I/O Classifiers
73 → 49 ↓33%

Papers Over Time

Showing total papers scanned vs. safety-relevant papers

Category Distribution

Relevance Score Distribution

Top arXiv Categories

Detailed Category Breakdown

Category Papers % of Total Distribution
Alignment Theory
557 26.5%
Evaluations & Benchmarks
431 20.5%
Robustness & Security
358 17.0%
Agent Safety
260 12.4%
RLHF
136 6.5%
I/O Classifiers
122 5.8%
Mechanistic Interpretability
93 4.4%
AI Control
54 2.6%
Governance & Policy
46 2.2%
Position Paper
44 2.1%

Frequent Authors

1

Wei Zhang

5 papers

2

Nathan Kallus

5 papers

3

Khaza Anuarul Hoque

4 papers

4

Hao Li

4 papers

5

Lars van der Laan

4 papers

6

Jiacai Liu

4 papers

7

Jiawei Chen

3 papers

8

Istiak Ahmed

3 papers

9

Ripan Kumar Kundu

3 papers

10

Tin Stribor Sohn

3 papers

Daily Statistics

Date Papers Top Categories
Thu, Jan 1 78
Alignment Theory Evaluations & Benchmarks Agent Safety
Wed, Dec 31 103
Alignment Theory Evaluations & Benchmarks Robustness & Security
Tue, Dec 30 145
Alignment Theory Evaluations & Benchmarks Robustness & Security
Mon, Dec 29 61
Alignment Theory Robustness & Security Evaluations & Benchmarks
Sun, Dec 28 71
Alignment Theory Evaluations & Benchmarks Robustness & Security
Thu, Dec 25 70
Alignment Theory Evaluations & Benchmarks Robustness & Security
Wed, Dec 24 115
Alignment Theory Evaluations & Benchmarks Robustness & Security
Tue, Dec 23 173
Alignment Theory Evaluations & Benchmarks Robustness & Security
Mon, Dec 22 127
Alignment Theory Evaluations & Benchmarks Robustness & Security
Sun, Dec 21 272
Alignment Theory Evaluations & Benchmarks Robustness & Security
Thu, Dec 18 0
Wed, Dec 17 0
Tue, Dec 16 0
Mon, Dec 15 31
Evaluations & Benchmarks Robustness & Security Agent Safety
Sun, Dec 14 31
Evaluations & Benchmarks Robustness & Security Agent Safety
Sat, Dec 13 28
Evaluations & Benchmarks Robustness & Security Alignment Theory
Fri, Dec 12 60
Evaluations & Benchmarks Robustness & Security I/O Classifiers