# Scope3Trace: Evidence-Based Identification and Extraction of Scope 3 GHG Emissions from Sustainability Reports

arXiv: https://arxiv.org/abs/2607.17122 · HTML: https://mlsanity.com/paper/2607.17122/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 30 of its 72 references that are in the map.
- First posted on arXiv 19 Jul 2026.

## Builds on (most cited first, 30 of 30)

- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [TIP: Token Importance in On-Policy Distillation](https://mlsanity.com/paper/2604.14084/) (2026)
- [PACED: Distillation and On-Policy Self-Distillation at the Frontier of Student Competence](https://mlsanity.com/paper/2603.11178/) (2026)
- [Question Calibration and Multi-Hop Modeling for Temporal Question Answering](https://mlsanity.com/paper/2402.13188/) (2024)
- [A Comprehensive Survey on Trustworthiness in Reasoning with Large Language Models](https://mlsanity.com/paper/2509.03871/) (2025)
- [Dual Path Modeling for Semantic Matching by Perceiving Subtle Conflicts](https://mlsanity.com/paper/2302.12530/) (2023)
- [Beyond the Surface: Enhancing LLM-as-a-Judge Alignment with Human via Internal Representations](https://mlsanity.com/paper/2508.03550/) (2025)
- [ZARA: Training-Free Motion Time-Series Reasoning via Evidence-Grounded LLM Agents](https://mlsanity.com/paper/2508.04038/) (2025)
- [From Points to Coalitions: Hierarchical Contrastive Shapley Values for Prioritizing Data Samples](https://mlsanity.com/paper/2512.19363/) (2025)
- [Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training](https://mlsanity.com/paper/2605.12483/) (2026)
- [DRF: LLM-AGENT Dynamic Reputation Filtering Framework](https://mlsanity.com/paper/2509.05764/) (2025)
- [DSPC: Dual-Stage Progressive Compression Framework for Efficient Long-Context Reasoning](https://mlsanity.com/paper/2509.13723/) (2025)
- [Learning Game-Playing Agents with Generative Code Optimization](https://mlsanity.com/paper/2508.19506/) (2025)
- [StructCoh: Structured Contrastive Learning for Context-Aware Text Semantic Matching](https://mlsanity.com/paper/2509.02033/) (2025)
- [Seeing through the Conflict: Transparent Knowledge Conflict Handling in Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.06842/) (2026)
- [HeLa-Mem: Hebbian Learning and Associative Memory for LLM Agents](https://mlsanity.com/paper/2604.16839/) (2026)
- [Space-aware Socioeconomic Indicator Inference with Heterogeneous Graphs](https://mlsanity.com/paper/2405.14135/) (2024)
- [DRAFT-RL: Multi-Agent Chain-of-Draft Reasoning for Reinforcement Learning-Enhanced LLMs](https://mlsanity.com/paper/2511.20468/) (2025)
- [Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing](https://mlsanity.com/paper/2605.10544/) (2026)
- [Possible or Definite? A Benchmark for Evaluating Diagnostic Uncertainty Preservation in Clinical Text](https://mlsanity.com/paper/2606.18471/) (2026)
- [SP-Mind: An Autonomous Reasoning Agent for Spatial Proteomics Analysis](https://mlsanity.com/paper/2606.24235/) (2026)
- [Statements: Universal Information Extraction from Tables with Large Language Models for ESG KPIs](https://mlsanity.com/paper/2406.19102/) (2024)
- [Over++: Generative Video Compositing for Layer Interaction Effects](https://mlsanity.com/paper/2512.19661/) (2025)
- [Do Deployment Constraints Make LLMs Hallucinate Citations? An Empirical Study across Four Models and Five Prompting Regimes](https://mlsanity.com/paper/2603.07287/) (2026)
- [Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning](https://mlsanity.com/paper/2604.21327/) (2026)
- [Design and Implementation of an Open-Source Security Framework for Cloud Infrastructure](https://mlsanity.com/paper/2604.03331/) (2026)
- [LLM-Oriented Information Retrieval: A Denoising-First Perspective](https://mlsanity.com/paper/2605.00505/) (2026)
- [BoostAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models](https://mlsanity.com/paper/2605.09134/) (2026)
- [GHGbench: A Unified Multi-Entity, Multi-Task Benchmark for Carbon Emission Prediction](https://mlsanity.com/paper/2605.13743/) (2026)
- [TriLens: Per-Layer Logit-Lens Entropy for White-Box Hallucination Detection](https://mlsanity.com/paper/2606.01033/) (2026)

## Abstract (arXiv)

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.