Tootfinder

Real-World Summarization: When Evaluation Reaches Its Limits
Patr\'icia Schmidtov\'a, Ond\v{r}ej Du\v{s}ek, Saad Mahamood
https://arxiv.org/abs/2507.11508

Real-World Summarization: When Evaluation Reaches Its Limits
We examine evaluation of faithfulness to input data in the context of hotel highlights: brief LLM-generated summaries that capture unique features of accommodations. Through human evaluation campaigns involving categorical error assessment and span-level annotation, we compare traditional metrics, trainable methods, and LLM-as-a-judge approaches. Our findings reveal that simpler metrics like word overlap correlate surprisingly well with human judgments (Spearman correlation rank of 0.63), often…

Evidence for an intrinsic luminosity-decay correlation in GRB radio afterglows
S. P. R. Shilling, S. R. Oates, D. A. Kann, J. Patel, J. L. Racusin, B. Cenko, R. Gupta, M. Smith, L. Rhodes, K. R. Hinds, M. Nicholl, A. Breeveld, M. Page, M. De Pasquale, B. Gompertz
https://arxiv.org/abs/2508.07276

Evidence for an intrinsic luminosity-decay correlation in GRB radio afterglows
We present the discovery of a correlation, in a sample of 16 gamma-ray burst 8.5 GHz radio afterglows, between the intrinsic luminosity measured at 10 days in the rest frame, $L_{\mathrm{Radio,10d}}$, and the average rate of decay past this time, $α_{>10d}$. The correlation has a Spearman's rank coefficient of $-0.70 \pm 0.13$ at a significance of $>3σ$ and a linear regression fit of $α_{>10d} = -0.29^{+0.19}_{-0.28} \log \left(L_{\mathrm{Radio,10d}} \right) + 8.12^{+8.86}_{-5.88}$. This fin…

On the exact region between Chatterjee's rank correlation and Spearman's footrule
Marcus Rockel
https://arxiv.org/abs/2509.07232 https://arxiv.org/…

On the exact region between Chatterjee's rank correlation and Spearman's footrule
Chatterjee's rank correlation \(ξ\) has emerged as a popular measure quantifying the strength of directed functional dependence between random variables $X$ and $Y$. If $X$ and $Y$ are continuous, $ξ$ equals Spearman's footrule~\(ψ\) for the Markov product of the copula induced by $(X,Y)$ and its transpose. We analyze the relationship between these two measures more in depth by studying the attainable region of possible pairs \((ξ, ψ)\) over all bivariate copulas. In particular, we show th…

The exact region and an inequality between Chatterjee's and Spearman's rank correlations
Jonathan Ansari, Marcus Rockel
https://arxiv.org/abs/2506.15897

The exact region and an inequality between Chatterjee's and Spearman's rank correlations
The rank correlation xi(X,Y), recently introduced by Chatterjee [12] and already popular in the statistics literature, takes values in [0,1], where 0 characterizes independence of X and Y, and 1 characterizes perfect dependence of Y on X. Unlike classical concordance measures such as Spearman's rho, which capture the degree of positive or negative dependence, xi quantifies the strength of functional dependence. In this paper, we determine, for each fixed value of xi, the full range of possible …