arXiv cs.AI· Qiwei Yan, Zhiqiang Yuan, Zexi Jia, Nanxing Hu, Kailin Lyu, Jie Zhou, Jinchao Zhang·· 3 小时前AI 评分33
PAL-Bench：基于证据的纵向个人相册画像重建基准
PAL-Bench: Evidence-Grounded Profile Reconstruction from Longitudinal Personal Albums
AI 导读
PAL-Bench 是一个基于公开记录契约、用于证据锚定画像重建的受控基准，包含 50 个合成用户、36,659 条公开照片记录和 2,799 个目标，涉及所有者事实、身份与关系。
正文 · 原文
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.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.16175 [cs.AI] |
| (or arXiv:2606.16175v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.16175 arXiv-issued DOI via DataCite |
Submission history
From: Zhiqiang Yuan [view email]
[v1]
Mon, 15 Jun 2026 03:42:59 UTC (4,671 KB)
[v2]
Wed, 11 Nov 2026 10:05:00 UTC (4,671 KB)
来源：arXiv cs.AI · arxiv.org