Hit papers significantly outperform the citation benchmark for their cohort. A paper qualifies
if it has ≥500 total citations, achieves ≥1.5× the top-1% citation threshold for papers in the
same subfield and year (this is the minimum needed to enter the top 1%, not the average
within it), or reaches the top citation threshold in at least one of its specific research
topics.
The computational complexity of propositional STRIPS planning
This map shows the geographic impact of Tom Bylander's research. It shows the number of citations coming from papers published by authors working in each country. You can also color the map by specialization and compare the number of citations received by Tom Bylander with the expected number of citations based on a country's size and research output (numbers larger than one mean the country cites Tom Bylander more than expected).
This network shows the impact of papers produced by Tom Bylander. Nodes represent research fields, and links connect fields that are likely to share authors. Colored nodes show fields that tend to cite the papers produced by Tom Bylander. The network helps show where Tom Bylander may publish in the future.
Co-authorship network of co-authors of Tom Bylander
This figure shows the co-authorship network connecting the top 25 collaborators of Tom Bylander.
A scholar is included among the top collaborators of Tom Bylander based on the total number of
citations received by their joint publications. Widths of edges
represent the number of papers authors have co-authored together.
Node borders
signify the number of papers an author published with Tom Bylander. Tom Bylander is excluded from
the visualization to improve readability, since they are connected to all nodes in the network.
All Works
20 of 20 papers shown
1.
Bylander, Tom, et al.. (2006). Using Validation Sets to Avoid Overfitting in AdaBoost.. The Florida AI Research Society. 544–549.23 indexed citations
2.
Bylander, Tom, et al.. (1999). Estimating generalization error using out-of-bag estimates. National Conference on Artificial Intelligence. 321–327.7 indexed citations
Bylander, Tom. (1997). Worst-case absolute loss bounds for linear learning algorithms. National Conference on Artificial Intelligence. 485–490.4 indexed citations
5.
Bylander, Tom. (1997). A linear programming heuristic for optimal planning. National Conference on Artificial Intelligence. 694–699.30 indexed citations
Bylander, Tom. (1991). The qualitative difference resolution rule. National Conference on Artificial Intelligence. 824–829.3 indexed citations
13.
Bylander, Tom. (1991). The monotonic abduction problem: a functional characterization on the edge of tractability. Principles of Knowledge Representation and Reasoning. 70–77.9 indexed citations
14.
Bylander, Tom. (1991). Tractability and artificial intelligence. Journal of Experimental & Theoretical Artificial Intelligence. 3(3). 171–178.3 indexed citations
Bylander, Tom, et al.. (1989). QUAWDS: A composite diagnostic system for gait analysis. PubMed Central. 145–151.2 indexed citations
17.
Bylander, Tom, Dean Allemang, Michael C. Tanner, & John R. Josephson. (1989). Some results concerning the computational complexity of abduction. Principles of Knowledge Representation and Reasoning. 44–54.36 indexed citations
18.
Allemang, Dean, Michael C. Tanner, Tom Bylander, & John R. Josephson. (1987). Computational complexity of hypothesis assembly. International Joint Conference on Artificial Intelligence. 1112–1117.31 indexed citations
19.
Bylander, Tom & B. Chandrasekaran. (1985). Understanding behavior using consolidation. International Joint Conference on Artificial Intelligence. 450–454.41 indexed citations
20.
Bylander, Tom, Sanjay Mittal, & Bharath Chandrasekaran. (1983). CSEL: a language for expert systems for diagnosis. International Joint Conference on Artificial Intelligence. 218–221.11 indexed citations
Rankless uses publication and citation data sourced from OpenAlex, an open and comprehensive
bibliographic database. While OpenAlex provides broad and valuable coverage of the global
research landscape, it—like all bibliographic datasets—has inherent limitations. These include
incomplete records, variations in author disambiguation, differences in journal indexing, and
delays in data updates. As a result, some metrics and network relationships displayed in
Rankless may not fully capture the entirety of a scholar's output or impact.