Beyond Readability: Evaluating Task Information Recoverability

2026-09-29

AI Summary

This study addresses the prevalent conflation of visual legibility with task-level information recoverability in existing research, which remains largely confined to pixel-level evaluation. To overcome this limitation, we propose a dual-pathway framework that distinguishes between direct optical reading and knowledge graph-based entity retrieval. Through controlled experiments using book cover images, we integrate vision-language models (VLMs) with deterministic lookup techniques to quantify the overlap in success rates across both pathways, systematically evaluating multi-path information acquisition under varying degrees of image degradation. Our findings demonstrate that even when optical performance degrades substantially, external knowledge can effectively facilitate information recovery via entity linking. This work reveals the potential for information access beyond direct visibility, thereby transcending the constraints of conventional evaluation paradigms.

Abstract

Direct visual readability and task-information recoverability are different quantities. Failure to decode a target from a fixed observation need not eliminate access to that target through another recovery route. We develop an evaluation perspective that makes the observation, query, target, and available knowledge explicit and measures the overlap between routes' success sets. For information available on the original visible surface under suitable imaging conditions, direct optical recovery reads the target from the image, optionally after restoration; entity-linked recovery uses residual visual evidence to identify the depicted entity and accesses its target through an entity--attribute relation in a specified knowledge resource. Such access can draw on stored knowledge or an external source. A controlled book-cover study instantiates external access with a fixed title--author catalog, comparing optical author recovery with visual title resolution and deterministic lookup under resolution degradation. Entity-linked successes persist across the tested vision--language models, revealing information access beyond the tested direct visual frontier despite substantial differences in absolute performance. A substantial optical-only region remains. These complementary outcomes show why visual degradation should be evaluated through the task information accessible along specified routes and knowledge resources, alongside direct readability.

Problem

• task information recoverability
• visual readability
• entity-linked recovery
• visual degradation
• information access

Innovation

• Task Information Recoverability
• Entity-linked Recovery
• Visual Degradation Evaluation
• Vision-Language Models
• Knowledge Resource Access