Reclassification of gamma-ray bursts

We have applied two different automatic classifier algorithms to the BATSE Current GRB Catalog data and we obtain three different classes of GRBs. Our results confirm the existence of a third, intermediate class of GRBs, with mean duration \sim 25-50 s, as deduced from a cluster analysis and from a neural network algorithm. Our analyses imply longer durations than those found by Mukherjee et al. (1998) and Horvath (1998), whose intermediate class had durations \sim 2-10 s. From the neural network analysis no difference in hardness between the two longest classes is found, and from both methods we find that the intermediate-duration class constitutes the most homogeneous sample of GRBs in its space distribution while the longest-duration class constitutes the most inhomogeneous one with <V/V_max> \sim 0.1, being thus the deepest population of GRBs with z_max \sim 10. The trend previously found in long bursts, of spatial inhomogeneity increasing with hardness, only holds for this new longest-duration class.