Benchmark archaeology: investigate Docvqa score discrepancy for Qwen2.5 — reported 14.1\%–94.3\% (spread 80.3pp) across 3

Abstract

Abstract: This report synthesises findings from 4 peer-reviewed papers addressing the following research question: Benchmark archaeology: investigate Docvqa score discrepancy for Qwen2.5 — reported 14.1\%–94.3\% (spread 80.3pp) across 3 papers. Sources: 'VisionSelector: End-to-End Learnable Vis' (94.3\%);. 10 claims were extracted from source literature; 0 were independently verified against retrieved documents. An automated multi-reviewer quality assessment produced a score of 3.8/10. This report is a machine-generated literature synthesis and does not constitute original research.

Research Question

Benchmark archaeology: investigate Docvqa score discrepancy for Qwen2.5 — reported 14.1%–94.3% (spread 80.3pp) across 3 papers. Sources: 'VisionSelector: End-to-End Learnable Vis' (94.3%); 'VisionSelector: End-to-End Learnable Vis' (94.3%); 'DocHop-QA: Towards Multi-Hop Reasoning o' (14.1%). Identify evaluation protocol differences (few-shot, prompting, preprocessing).

Verification Level

Descriptive public verification status only; aggregate claim counts are public, but individual claim records are not exposed here.

Quality Tier

Descriptive public triage only; this tier does not alter current publication or DOI behavior.

Quality Dimensions

Automated triage signals derived from public fields; not human peer review or independent validation.

Correction Record

Public corrections are additive records. Current status does not claim the synthesis is error-free.

Provenance