PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums

2026-06-14

AI Summary

This work addresses the lack of a unified benchmark for user profile reconstruction in longitudinal personal photo albums, particularly the shortcomings in social identity binding and evidential traceability. To this end, the authors propose PAL-Bench, a privacy-preserving synthetic benchmark that introduces a novel construction mechanism grounded in publicly available record contracts. This approach simulates realistic album structures while safeguarding user privacy and incorporates a joint evaluation framework for identity binding and evidence traceability. Leveraging synthetic data generation, multimodal temporal evidence aggregation, and auditable public-private view exportation, the benchmark comprises 50 users, 36,659 photos, and 2,799 entities. Experimental results reveal that existing methods perform poorly in repeated identity recognition and evidence citation, while the proposed PAL-TRACE framework achieves the best results yet still faces significant challenges.

Abstract

Longitudinal personal albums are weak-schema multimodal databases: noisy perceptual records whose key facts require joins across faces, text, timestamps, locations, and repeated events. Existing visual, video, document, and lifelog benchmarks test sub-problems, but not album-scale profile reconstruction with social identity binding and evidence citation. Benchmarking this task is difficult because the ground truth needed for evaluation--owner profiles, social graphs, face-name maps, and evidence provenance--is private state that real albums cannot safely release. We introduce PAL-Bench, a controlled benchmark for evidence-grounded reconstruction under a public-record contract. Its Evidence Compiler builds latent private worlds, programs target-level evidence paths, renders album pixels, re-measures them through perception pipelines, and exports audited public/private views. Agents receive only perception-derived public records; targets, identifier maps, and evidence paths remain hidden. PAL-Bench contains 50 synthetic users, 36,659 public photo records, and 2,799 targets over owner facts, identities, and relations. A privacy-preserving audit with 10 participants confirms that PAL-Bench evidence structures match real private albums, though equivalent releases remain privacy-prohibitive. Across seven systems and two compute-matched diagnostics, a seven-metric protocol reveals a gap between plausible profile summarization and faithful social reconstruction: systems recover some owner facts but struggle with recurring identities and evidence citation. PAL-TRACE, a reference framework that freezes identity bindings before owner-fact mining, performs best but leaves hard identity resolution far from solved. PAL-Bench provides a testbed for perceptual entity resolution, multimodal data integration, temporal evidence aggregation, and provenance-aware structured prediction.

Problem

• profile reconstruction
• longitudinal personal albums
• evidence grounding
• social identity binding
• privacy-preserving benchmarking

Innovation

• evidence-grounded reconstruction
• longitudinal personal albums
• privacy-preserving benchmarking
• multimodal entity resolution
• social identity binding