ConstructCIE is a manually annotated dataset designed for extracting causal information from OSHA construction accident reports. It employs a hierarchical schema that categorizes accident types, causal factors, sub‑causal factors, and the supporting evidence spans. Experiments with supervised sequence taggers and instruction‑tuned large language models show strong performance on accident‑type prediction and broad causal recovery, yet precise span‑level extraction remains challenging, highlighting the need for better domain grounding and evidence extraction.
arXiv:2610.35658v1 Announce Type: new Abstract: Aviation authorities hold decades of accident reports whose narratives record how investigators reconstructed each accident. Computational work on thes...
arXiv:2606. 09892v1 Announce Type: new Abstract: Textual event records, such as alarm logs, have become an increasingly common data source in engineering and manufacturing systems.
Humanitarian reports are long, noisy, and multi-topic, making it difficult to consolidate decision-relevant causal evidence. We present a ReliefWeb study (2000-2024) and a two-stage Large Language Model (LLM) pipeline that extracts structured intervention-outcome records with direction and strength attributes.
The study investigates whether a model trained on construction‑sector occupational accident narratives can accurately classify accident‑process roles in other sectors and reporting environments. Using 42,244 factual units from 6,040 construction narratives, the authors compared TF‑IDF, frozen pretrained representations, and task‑adapted pretrained models, achieving up to 85.7% balanced accuracy without retraining. The models performed consistently across metallurgy, chemistry‑plastics, and an independent company corpus, though performance varied more on the latter due to differing reporting practices.
The paper introduces a pipeline that merges structured disaster records from EM‑DAT with unstructured documents from ReliefWeb and the European Media Monitor to generate source‑grounded disaster storylines and causal knowledge graphs. Using Retrieval‑Augmented Generation, it produces tabular event profiles covering 17 fields and builds causal graphs enriched with citation‑grounded explanatory narratives, allowing traceability to primary sources. Human evaluation across three crisis cases shows high retrieval precision, strong faithfulness of causal relations, and a clear expert preference for citation‑grounded components over ungrounded ones.
ARGUS is a pipeline that builds document-level Event Knowledge Graphs (EKGs) from U.S. employment‑discrimination complaints. It uses a 5W1H-inspired schema, legal-domain models, and LLM‑based structured generation to extract fact‑bearing statements, create chunk‑level event graphs with participant, temporal, and causal structure, and merge them into comprehensive document representations. Evaluation shows that graph‑structured classifiers outperform raw and linearized baselines on claim classification, and EKG‑only retrieval improves document‑scoped QA, though overall open‑retrieval gains are limited by low first‑stage candidate recall.
arXiv:2606. 07525v1 Announce Type: cross Abstract: Causal graphs in text are typically populated by observable, predefined events.
The study evaluates how well accident‑process role classifiers trained on construction‑sector French occupational accident narratives generalize to other sectors. An expert‑annotated corpus classifies factual units into four roles—work situation, unfavourable condition, accident event, and consequence—and the classifiers are tested on unseen metallurgy, chemistry‑plastics, and company corpora without retraining. Task‑specific adaptation consistently outperforms frozen representations, achieving balanced accuracies of 85.6%–85.8% across the target domains.
The paper introduces Multi-Task Anti-Causal learning (MTAC), a framework that estimates latent causes from observed effects by exploiting both task-invariant and task-specific structural dependencies. MTAC constructs a structural equation model that separates a shared backbone mechanism from task-specific deviations, then uses maximum a posteriori inference to reconstruct causes. Applied to urban event reconstruction—parking violations, abandoned properties, and unsanitary conditions—MTAC outperforms strong baselines on real data from Manhattan and Newark, achieving up to a 33.04% reduction in mean absolute error.
PermitGPT is a generative‑AI framework that transforms unstructured construction permit descriptions into structured outputs for safety hazard identification, permit requirement specification, and community impact assessment. It aligns data from the NYC Department of Buildings, OSHA, and NYC 311 to create 90,000 prompt‑response pairs, fine‑tunes three open‑weight language models, and evaluates them on 2,833 test cases, reporting complementary performance across inference speed, lexical overlap, and semantic alignment. The study presents an initial AI‑assisted approach to construction governance and outlines future evaluation and validation directions.
arXiv:2609.39406v1 Announce Type: new Abstract: Causal AI is a branch of Artificial Intelligence which helps understand and reason about cause and effect relationships, not just patterns or correlati...
arXiv:2608. 14746v1 Announce Type: new Abstract: The aviation industry characterized by its stringent safety standards has seen a growing need for innovative approaches to enhance safety measures.