PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums
2026-06-15 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors created PAL-Bench, a new test system to help computers better understand personal photo albums, which mix faces, text, times, and places in a complicated way. Because real albums are private, they made a synthetic, privacy-safe dataset that mimics real albums’ complexity with known answers hidden from the test systems. They tested several computer programs and found that while some owner details can be guessed, identifying recurring people and linking proof reliably is still hard. Their work provides a safe way to measure progress in recognizing people, combining different types of data, and tracking evidence over time in photo collections.
multimodal dataentity resolutionprofile reconstructionsocial graphevidence citationprivacy-preserving benchmarklifeloggingface recognitionstructured predictiontemporal data integration
Authors
Qiwei Yan, Zhiqiang Yuan, Zexi Jia, Nanxing Hu, Kailin Lyu, Jie Zhou, Jinchao Zhang
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.