Situation Graph Prediction for User Perspective Modeling

[Submitted on 10 Feb 2026 (v1), last revised 11 Aug 2026 (this version, v2)]

View PDF HTML (experimental)

Abstract:Perspective-aware AI requires modeling evolving internal states—goals, emotions, contexts—not merely preferences. Progress is limited by a data bottleneck: digital footprints are privacy-sensitive and perspective states are rarely labeled. We propose Situation Graph Prediction (SGP), a task that frames user perspective modeling as an inverse inference problem: reconstructing structured, ontology-aligned representations of perspective from observable multimodal artifacts, suitable as long-horizon memory for personal agents. To enable grounding without real labels, we use a structure-first synthetic generation strategy that aligns latent labels and observable traces by design. As a pilot, we construct a dataset and run a diagnostic study using retrieval-augmented in-context learning as a proxy for supervision. In our diagnostic study across three frontier foundation models (GPT-4o, Gemini 2.5 Flash, Claude Sonnet 4), we observe a consistent positive gap between surface-level extraction and latent perspective inference—indicating that latent-state inference is consistently harder than surface extraction under our controlled setting. Results suggest SGP is non-trivial and provide evidence for the structure-first data synthesis strategy. For reproducibility and transparency, our code, data, and supplementary resources are available here: this https URL.

Submission history

From: Daniel Platnick [view email]
[v1] Tue, 10 Feb 2026 20:58:15 UTC (86 KB)
[v2] Tue, 11 Aug 2026 15:52:51 UTC (87 KB)