Scope3Trace: Evidence-Based Identification and Extraction of Scope 3 GHG Emissions from Sustainability Reports
Scope3Trace: サステナビリティ報告書からのスコープ3 GHG排出量の証拠に基づく識別と抽出 (AI 翻訳)
Si Zheng, Yifan Duan, Chao Xue, F. Salim
🤖 gxceed AI 要約
日本語
本論文は、LLMと証拠に基づく検証を統合し、サステナビリティ報告書からスコープ3 GHG排出量を抽出するフレームワークScope3Traceを提案する。PDF解析、OCR、テーブル復元、ハイブリッドルールLLM抽出を実装し、組織・建物レベルでの排出量を証拠付きで取得する。さらに、二層構成の証拠付きマルチモーダルデータセットを提供し、スコープ1〜3の合計およびカテゴリ別開示の高精度抽出を実現した。
English
This paper proposes Scope3Trace, a framework that extracts Scope 3 GHG emissions from sustainability reports using LLMs with evidence grounding. It integrates PDF parsing, OCR, table reconstruction, and hybrid rule-LLM extraction to obtain organization- and building-level emissions with verification. A dual-level, evidence-grounded multimodal dataset is contributed. The system achieves high accuracy in extracting Scope 1-3 totals and category-level disclosures.
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
日本ではSSBJ基準によりスコープ3開示が義務化されつつあり、本フレームワークは企業が膨大なサプライチェーン排出データを自動的に抽出・検証する手段を提供する。有報や統合報告書への適用が期待される。
In the global GX context
Globally, TCFD, ISSB, and CSRD require Scope 3 disclosures, yet manual extraction is costly. Scope3Trace offers a scalable, evidence-traceable solution that can be integrated into existing ESG reporting workflows, supporting regulatory compliance and investor-grade data quality.
👥 読者別の含意
🔬研究者:Provides a novel dataset and benchmark for AI-driven ESG data extraction, enabling further research in automated carbon accounting.
🏢実務担当者:Offers a deployable pipeline to automate Scope 3 data collection from diverse reports, reducing manual effort and improving auditability.
🏛政策担当者:Demonstrates feasibility of automated verification of sustainability disclosures, informing standard-setting for digital reporting (e.g., XBRL taxonomies).
📄 Abstract（原文）
Scope 3 greenhouse gas (GHG) emissions account for the majority of corporate carbon footprints, yet remain difficult to analyze at scale due to sparse disclosures, heterogeneous report document formats, and limited evidence traceability. Existing approaches typically rely on large language models to extract emissions information from ESG reports, but often lack explicit evidence grounding or depend on costly manual annotation and verification to ensure extraction reliability. To address these challenges, we propose Scope3Trace, an evidence-grounded information extraction framework designed to extract interpretable and traceable Scope 3 emissions information from real-world ESG and sustainability reports. The framework integrates a document information extraction pipeline that performs PDF collection and OCR parsing, LLM-assisted page localization and table reconstruction, and hybrid rule-LLM extraction of organization- and building-level emissions disclosures with evidence-grounded verification. Building upon this framework, we further contribute a dual-level, evidence-grounded, multimodal dataset comprising organization-level Scope 3 disclosures extracted from heterogeneous sustainability reports. Scope3Trace enables reliable extraction and transparent integration of heterogeneous sustainability disclosures, achieving high accuracy in extracting Scope 1-3 totals and category-level disclosures from sustainability reports.
🔗 Provenance — このレコードを発見したソース
- semanticscholar https://www.semanticscholar.org/paper/0f73fe8e18afc0458c795ffb27cee241874455c0first seen 2026-07-22 05:53:03
🔔 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。