Readers of applied-domain LLM capability evaluations want to know what AI systems can currently do. That literature answers a related, but consequentially different, question: what older, cheaper, less-elicited models could do months or years earlier (a 2026 paper evaluating GPT-3.5 or GPT-4 zero-shot, say, against a frontier of reasoning-capable, tool-using systems like GPT-5.5 Pro and Claude Opus 4.7), often reported with sparse configuration details and abstracted upward into claims about "AI" that propagate through citations, media, and policy. We measure the 'publication elicitation gap' (the gap between these answers) in a pre-registered audit of 112,303 LLM-keyword-matched candidate records (2022-01 to 2026-04; 18,574 admissible, 4,766 full-paper texts retrievable), comparing tested models to the contemporaneous frontier on the Epoch AI Capabilities Index (ECI), reproduced under Arena Elo and Artificial Analysis. The median paper evaluates a model +10.85 ECI (~1.4x the distance between Claude Sonnet 3.7 and Claude Opus 4.5) behind the contemporaneous frontier at evaluation time (H1); an exploratory rational-lag baseline (H8) decomposes this into ~25% peer-review latency, ~75% excess lag. The gap is widening at +5.53 ECI/year (H2; 95% CI [+5.03, +5.83]). Meanwhile, only 3.2% of abstracts (21.2% of full-texts) disclose reasoning-mode status on reasoning-capable models (H4) and 52.5% (95% CI [48.2, 56.9]) state conclusions at the level of "AI" rather than the evaluated model(s), rising at OR = 1.23/year. Proposed remedies include API-access subsidies and editorial enforcement of reporting frameworks mandating configuration-surface disclosure (model snapshot, reasoning mode/effort, tool access, scaffolding, prompting, etc.); VERSIO-AI is a 13-item checklist (Core 3 desk-reject) extending existing frameworks at the elicitation surface, with per-DOI analysis at frontierlag.org.

翻译：应用领域大语言模型能力评估的读者希望了解当前AI系统能做什么。这类文献回答的是一个相关但后果迥异的问题：较旧、较便宜、较少被引导的模型在数月或数年前能做什么（例如，一篇2026年的论文评估GPT-3.5或GPT-4的零样本能力，将其与GPT-5.5 Pro和Claude Opus 4.7等具备推理能力、能使用工具的前沿系统进行比较），且通常仅提供稀疏的配置细节，并抽象上升为关于“AI”的论断，通过引用、媒体和政策传播。我们在一项预注册审计中测量了“发表引导差距”（这些答案之间的差距），该审计覆盖112,303条LLM关键词匹配的候选记录（2022年1月至2026年4月；18,574条可纳入，4,766篇全文可获取），将测试模型与Epoch AI能力指数（ECI）上的同期前沿进行比较，并基于Arena Elo和Artificial Analysis进行了复现。评估时，论文所选模型的中位值落后同期前沿+10.85 ECI（约1.4倍于Claude Sonnet 3.7与Claude Opus 4.5之差）（H1）；一项探索性理性滞后基线（H8）将其分解为约25%的同行评审延迟和约75%的过度滞后。该差距正在以每年+5.53 ECI的速度扩大（H2；95%置信区间[+5.03, +5.83]）。同时，仅3.2%的摘要（21.2%的全文）披露了具备推理能力模型的推理模式状态（H4），且52.5%（95%置信区间[48.2, 56.9]）的结论上升到“AI”层面而非所评估的模型，并以OR=1.23/年的速度增长。拟议的补救措施包括API访问补贴和编辑强制执行报告框架，要求披露配置表面（模型快照、推理模式/努力、工具访问、脚手架、提示等）；VERSIO-AI是一个13项清单（核心3项为直接拒稿），在引导表面扩展了现有框架，详细分析见frontierlag.org。