AI RESEARCH
Architecture-Sensitive Supervised Fine-Tuning for Screen-Conditioned Action Prediction: A PiSAR Benchmark
arXiv CS.AI
•
ArXi:2605.29400v1 Announce Type: new We benchmark three supervised fine-tuned models against frontier zero-shot baselines on a 661-row held-out slice of PiSAR (Persona, intent, Screen, Action, Rationale), a 12,929-tuple corpus of screen-anchored behavioural rationales curated from public app- reviews, Pew American Trends Panel graphics, and the OPeRA shopper traces. Every model, frontier or fine-tuned, is evaluated on the same 661-row slice with the same scoring pipeline. Two findings.