← 論文一覧に戻る

Unfit for stranding assessment: a panel-scale multimodal-LLM audit of building-decarbonisation disclosure (BeDA)

座礁評価に不適合：パネルスケールのマルチモーダルLLMによる建築脱炭素開示（BeDA）監査 (AI 翻訳)

Jingyi Xu, Minghui Cheng, Anchen Sun

arXivプレプリント2026-07-24#AI×ESGOrigin: Global経営インパクト: 資金調達対象セクター: real_estate
原典: https://arxiv.org/abs/2607.22006
📄 PDF

🤖 gxceed AI 要約

日本語

建築物の炭素強度開示を評価するマルチモーダル大規模言語モデル「BeDA」を開発し、2,246社のグローバルパネル（2003-2023年）に適用。開示の大半が座礁リスク評価に不適合であり、企業報告書の約5分の1しか面積当たりの運用炭素強度を開示していないことが判明。欧州は米国の約2倍の開示率を示し、一部の不動産企業は既にCRREM 1.5°C経路の強度上限を超過している。

English

This paper introduces BeDA, a multimodal large-language-model instrument, to audit corporate building-decarbonization disclosure. Applied to a global panel of 2,246 firms (2003-2023), it finds that only about one in five firm-reports disclose operational carbon intensity per m², and 39% of 215 real-estate firm-reports already exceed the CRREM 1.5°C pathway intensity limit. The disclosure gap is measurable and jurisdiction-specific, with European firms disclosing at roughly twice the rate of US firms. The results demonstrate that targeted disclosure mandates can close this gap, and BeDA can monitor progress.

Unofficial AI-generated summary based on the public title and abstract. Not an official translation.

📝 gxceed 編集解説 — Why this matters

日本のGX文脈において

本論文は、ビルディングセクターの脱炭素開示の質を定量評価する手法を提供。日本ではSSBJや有報でのGHG開示が進む中、不動産・建設業界のScope1・2開示の実態把握や、グリーンビルディング認証との連携に示唆を与える。特に東京の建築物環境計画書制度との比較が可能。

In the global GX context

This paper introduces a scalable, AI-powered audit method for building decarbonization disclosure, directly relevant to global stranding regulations like NYC Local Law 97 and the EU EPBD recast. It provides empirical evidence that current disclosure is largely unfit for science-based pathway comparison, with significant regional variation. The BeDA tool offers regulators and investors a transparent benchmark to monitor disclosure quality and enforce mandates, contributing to the broader ISSB and TCFD framework implementation.

👥 読者別の含意

🔬研究者:Researchers gain a validated methodology for large-scale disclosure audit using multimodal LLMs, with open-source potential for replication across sectors.

🏢実務担当者:Corporate sustainability teams in real estate can benchmark their disclosure against regional peers and identify gaps for regulatory compliance.

🏛政策担当者:Policymakers can use the evidence to design targeted disclosure mandates, especially for building carbon intensity, and monitor effectiveness with BeDA.

📄 Abstract（原文）

Buildings account for roughly 34% of global final energy use and 37% of energy- and process-related CO$_2$ emissions. Stranding regulation now being enacted (New York City Local Law 97, the EU Energy Performance of Buildings Directive recast) presupposes that a building portfolio's carbon intensity can be measured per square metre and compared against a science-based pathway. Whether corporate disclosure is actually fit for that comparison has not, to our knowledge, been measured at scale. We introduce BeDA (the Built-environment Decarbonisation-disclosure Auditor), a multimodal large-language-model instrument, and apply it to a global firm panel (2,246 firms, 2003-2023). Its standards-compliance score is reliable across models and model families and convergent with three independent external criteria. Most disclosure is unfit: only about one built-environment firm-report in five discloses operational carbon intensity per $m^2$ (21.5% in a region-stratified sample of 200 firm-reports, Wilson 95% CI [16.4%, 27.7%], inter-extractor $κ$=0.95; 45.5% across 519 real-estate firm-reports, $κ$=0.97). The rate is roughly twice as high in Europe as in the United States (64-74% versus 37% for listed real estate). Among the 215 real-estate firm-reports for which an intensity can be constructed, 39% already exceed the Carbon Risk Real Estate Monitor (CRREM) 1.5 °C pathway's intensity limit. Credibility does not predict stranding readiness once portfolio size is controlled; this is a screening tool, not a forecast. The main obstacle to enforceable building-stranding regulation is therefore a measurable, jurisdiction-specific reporting gap, one that a targeted disclosure mandate can close and that BeDA can monitor.

🔗 Provenance — このレコードを発見したソース

🔔 こうした論文の新着を逃したくない方は キーワードアラート に登録（無料・3キーワードまで）。

gxceed は公開メタデータに基づく研究支援データセットです。要約・翻訳・解説は AI 支援で生成されています。 最終的な解釈・検証は利用者が原典資料に基づいて行うことを前提とします。