Citation Analysis

Inverse Reinforcement Learning Using\\Just Classification and a Few Regressions
Lars van der Laan, Nathan Kallus, Aurélien Bibaut
https://arxiv.org/abs/2509.21172

Citation mentions

Cited references

Sections

1,685

Words (approx)

References by Citation Intensity

Ordered by composite index (descending). Higher values indicate more intensive citation.

#	Mentions	Breadth	Sec. Wtd	Share	Composite	Main %
1	5	3	5.5	0.082	1.000	100%
2	5	3	5.5	0.082	1.000	100%
3	4	3	6.5	0.066	0.928	100%
4	2	2	1.5	0.033	0.644	100%
5	2	2	1.5	0.033	0.644	100%
6	2	2	1.5	0.033	0.644	100%
7	2	2	1.5	0.033	0.644	100%
8	2	2	2.5	0.033	0.644	100%
9	2	2	2.5	0.033	0.644	100%
10	2	2	1.5	0.033	0.644	100%
11	1	1	1.0	0.016	0.406	100%
12	1	1	1.0	0.016	0.406	100%
13	1	1	2.0	0.016	0.406	100%
14	1	1	2.0	0.016	0.406	100%
15	1	1	2.0	0.016	0.406	100%
16	1	1	2.0	0.016	0.406	100%
17	1	1	0.5	0.016	0.406	100%
18	1	1	0.5	0.016	0.406	100%
19	1	1	0.5	0.016	0.406	100%
20	1	1	0.5	0.016	0.406	100%
21	1	1	0.5	0.016	0.406	100%
22	1	1	0.5	0.016	0.406	100%
23	1	1	0.5	0.016	0.406	100%
24	1	1	0.5	0.016	0.406	100%
25	1	1	0.5	0.016	0.406	100%
26	1	1	0.5	0.016	0.406	100%
27	1	1	0.5	0.016	0.406	100%
28	1	1	0.5	0.016	0.406	100%
29	1	1	0.5	0.016	0.406	100%
30	1	1	0.5	0.016	0.406	100%
31	1	1	0.5	0.016	0.406	100%
32	1	1	0.5	0.016	0.406	100%
33	1	1	0.5	0.016	0.406	100%
34	1	1	0.5	0.016	0.406	100%
35	1	1	0.5	0.016	0.406	100%
36	1	1	0.5	0.016	0.406	100%
37	1	1	0.5	0.016	0.406	100%
38	1	1	0.5	0.016	0.406	100%
39	1	1	0.5	0.016	0.406	100%
40	1	1	0.5	0.016	0.406	100%
41	1	1	0.5	0.016	0.406	100%
42	2	1	1.0	0.033	0.110	0%

Measures: Mentions = total in-text citations; Breadth = distinct sections; Sec. Wtd = section-weighted count (body ×2, lit review/appendix ×0.5); Share = mentions / total citations in paper; Composite = geometric mean of normalised count, breadth, and main-text ratio; Main % = fraction of mentions in main text (excl. appendix). (self) = self-citation.