학술

PhoneValue-Bench: A Dual-Ground-Truth Scorecard Benchmark for Smartphone Recommerce Inspection

arXiv CS.AI
CC BY
이 매체는 공공·자유 라이선스로 본문을 직접 표시합니다.

Abstract

Remote smartphone recommerce is scaling quickly, and locking a repurchase offer from seller photos and diagnostic screens before the handset arrives has become a central operational task.

Existing multimodal resources mainly target defect localization, catalog attributes, or screen reading.

They overlook payout-facing scorecards with dual cosmetic and operational ground truth under a declared input contract.

This gap stems from two challenges: (1) the lack of a large weakly labeled trade-in corpus kept separate from a compact audited ranking cut, and (2) architectures that either flatten unordered photo bags into one prompt or collapse evaluation into a single price scalar.

To address these challenges, we propose PhoneValue-Bench, a dual-ground-truth recommerce framework with PhoneValue-Corpus for weak training on 21,550 orders and 278,748 images, and PV-Rank as the only leaderboard on 335 quality-gated orders.

Systems are ranked by CardScore under LeadGate, with Cosmetic Fill and Operational Fill as diagnostics, while grade and price stay off the board.

Notably, ValueAgent is a six-stage perception-fusion reference that canonicalizes views, detects regional defects, reads screenshots, and fuses evidence under warehouse-style rules, so bag-of-images prompting is not the only evaluation unit.

On the same PV-Rank cut and frozen scorer, this full-system and input-contract comparison finds ValueAgent at 84.1 CardScore against the strongest Flat Vision-Language Model at 69.9, with the largest reported gap in CosFill, while OpsFill remains limited under the two declared contracts.

CardScore measures field-fill completeness, not quote accuracy.

관련 뉴스