Auditable Climate Risk Intelligence from Fragmented ESG Data: Deterministic Orchestration and Imbalance-Aware Learning for Scope 1-3 Validation
断片的なESGデータからの監査可能な気候リスクインテリジェンス：スコープ1-3検証のための決定論的オーケストレーションと不均衡認識学習 (AI 翻訳)
Sehgal, Karan, Bhatti, Khawar Naveed
🤖 gxceed AI 要約
日本語
本論文は、スコープ1-3のESGデータ検証のための合成ベンチマークを提案する。ガバナンス障害モード（情報源の矛盾、報告の遅れ、気候ミスマッチなど）を注入したデータ生成器を提供し、不均衡学習と監査可能性を重視する。GHGプロトコルやISSB基準に準拠した特性を持ち、再現可能な研究を支援する。
English
This paper introduces a synthetic benchmark for Scope 1-3 ESG data validation with injected governance failure modes (provenance conflict, stale reporting, climate mismatch, etc.). It provides a deterministic generator for reproducible research, focusing on imbalance-aware anomaly detection and auditability. The benchmark is calibrated to characteristics of GHG Protocol, PCAF, and ISSB standards.
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基準の導入によりスコープ3開示の重要性が高まっている。本ベンチマークは、ESGデータの品質検証と監査可能性を向上させる手法を提供し、日本の開示実務に貢献する可能性がある。
In the global GX context
With the rise of ISSB standards and regulatory demands for Scope 3 disclosure, this benchmark addresses the critical need for auditable ESG data validation. The synthetic data generator allows researchers and practitioners to test provenance-aware validation methods, which is directly relevant to global climate disclosure frameworks.
👥 読者別の含意
🔬研究者:Provides a reproducible benchmark for testing ESG validation algorithms, useful for researchers focusing on Scope 3 data quality.
🏢実務担当者:Can be used by corporate sustainability teams to validate internal Scope 1-3 data systems and test anomaly detection methods before real-world deployment.
📄 Abstract（原文）
This record accompanies the preprint "Auditable Climate Risk Intelligence from Fragmented ESG Data: Deterministic Orchestration and Imbalance-Aware Learning for Scope 1-3 Validation" by Karan Sehgal and Khawar Naveed Bhatti (2026). It provides the synthetic ESG validation benchmark and deterministic generation script described in the paper. The benchmark models heterogeneous Scope 1-3 disclosure records with injected governance failure modes (provenance conflict, stale reporting, climate mismatch, null inflation, transition divergence, audit inconsistency). Marginal distributions, anomaly prevalence (4.7%), and missingness structure (12.3%) are calibrated against publicly reported characteristics of the GHG Protocol, PCAF, and ISSB reporting standards. The benchmark is released as a deterministic generator rather than as a frozen CSV dump. A single seed-controlled script produces the dataset bit-for-bit identically across runs and machines, together with a SHA-256-hashed manifest. Researchers can regenerate at any size from a few hundred records to the full ~68,000 used in the paper. Contents: generate_benchmark.py (generator), README.md (schema, failure modes, reproducibility instructions), LICENSE (CC BY 4.0), and the companion paper PDF. Materials are released to support reproducible research into provenance-aware ESG validation, imbalance-aware anomaly detection, and governance-oriented auditability under fragmented Scope 1-3 reporting conditions.
🔗 Provenance — このレコードを発見したソース
- Zenodo https://zenodo.org/records/20453252first seen 2026-05-30 04:24:02 · last seen 2026-06-03 04:22:42
🔔 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。