Deterministic Event-Graph Substrates as World Models for Counterfactual Reasoning

• URL: http://arxiv.org/abs/2605.15967v1
• Date: Fri, 15 May 2026 13:58:31 GMT
• Title: Deterministic Event-Graph Substrates as World Models for Counterfactual Reasoning
• Abstract summary: We study a class of world models that represent agent state as an append-only log of typed RDF triples and answer counterfactual queries by forking the log.<n>Substrates are inspectable at the triple level, support exact counterfactuals, and transfer across domains without learned components.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We study event-graph substrates: a class of world models that represent agent state as an append-only log of typed RDF triples and answer counterfactual queries by forking the log under a structured intervention vocabulary. Substrates are inspectable at the triple level, support exact counterfactuals, and transfer across domains without learned components. We formalize the class, prove a duality between explanatory and counterfactual queries that reduces both to the same causal-ancestor traversal, and evaluate a 1,400-line CLEVRER-DSL interpreter atop a domain-agnostic substrate runtime at full CLEVRER validation scale (n=75,618). The substrate exceeds the NS-DR symbolic oracle on all four per-question categories (by 9.89, 20.26, 17.65, and 0.80 percentage points), and exceeds the parametric ALOE baseline on descriptive and explanatory while lagging on predictive and counterfactual. We also introduce twin-EventLog, a 500-specification Park-canonical Smallville counterfactual benchmark on which the substrate exceeds Llama-3.1-8B with full context by 18.80 points joint accuracy.

Related papers

• SAM3-LoRA: Parameter-Efficient Adaptation of a Concept-Promptable Foundation Model for Multi-Class Structural Defect Segmentation [0.0]
  This study applies Low-Rank Adaptation (LoRA) to SAM3 for multi-class structural defect segmentation.<n>We describe a supervision procedure that trains a concept-promptable model directly from COCO-style class-labeled instance segmentation.
  arXiv  Detail & Related papers  (2026-08-31T23:19:59Z)
• From Diagnosis to Correction: Benchmarking and Improving Real-World Table Parsing [50.70862449978062]
  Recent documents achieve table TEDS scores above 93 on OmniDocBench v1.6, yet community feedback and our audit reveal persistent failures on complex real-world tables.<n>To quantify this gap, we introduce TableParseMap, a diagnostic benchmark of 916 real-world tables organized into five challenging scenarios and nine failure types.
  arXiv  Detail & Related papers  (2026-08-10T16:59:30Z)
• An Explicit World Model Based on Data-First Ontology: DaoQL Multimodal Storage Validation and Counterfactual Reasoning Evaluation [1.9674271425998944]
  Large language models encode world models implicitly in neural weights, which exposes four structural risks in high-precision domains such as medicine and finance.<n>We formalize an explicit world model and show that, under rule independence, explicit models provide a sufficient condition for composable counterfactual decomposability.<n>The implemented system focuses on DaoQL's verified storage layer and explicit Eval path, integrating graph, column, vector, and full-text engines within one process.
  arXiv  Detail & Related papers  (2026-07-19T14:20:22Z)
• Efficient Visual Pointing for Embodied AI:Agent-Driven Data Synthesis, Cross-Block Attention, and Iterative Correction [55.11480729304395]
  We describe our PointArena 2026 solution, which achieves 77.2% overall accuracy and ranks second on the benchmark.<n>The ap proach targets three failure modes. First, agent-driven syn thesis builds large semantic and anchor-relative candidate pools.<n>Second, a determinis tic steerable-data pipeline creates a verified 10,000-sample main set, plus reserve samples, using masks, templates, and path verification.
  arXiv  Detail & Related papers  (2026-06-29T06:39:03Z)
• Querit-Reranker: Training Compact Multilingual Rerankers via Efficient Label-Free Distribution Adaptation [43.66118282567413]
  We present Querit-Reranker, a family of multilingual cross-encoder rerankers trained with a data-centric pipeline.<n>Our pipeline first learns general relevance modeling from large-scale ranking-oriented data, then adapts to target distributions.<n>Querit-Reranker-A0.4B improves average nDCG@10 from 54.11 to 59.28 on BEIR and from 59.87 to 67.70 on MIRACL.
  arXiv  Detail & Related papers  (2026-06-17T13:06:47Z)
• FailureScope: Cross-Regime Behavioral Diagnosis of Language Model Weaknesses [0.0]
  FailureScope is a behavioral-diagnosis method that clusters evaluation probes by their cross-model pass/fail patterns.<n>We show it yields stable, interpretable failure across three regimes usually studied separately: single-turn benchmarks, multi-turn dialogue, and adversarial agent attacks.
  arXiv  Detail & Related papers  (2026-06-03T01:28:00Z)
• AXIOM: A Trust-First Neuro-Symbolic Execution Architecture for Verifiable Mathematical Reasoning [0.0]
  AXIOM is a trust-first neuro-symbolic execution architecture for natural-language mathematical reasoning.<n>We report empirical results on 4 MATH categories with a cumulative correctness of 94.36% (2,592/2,747)<n>The architecture has served 30,000 production queries through a public deployment.
  arXiv  Detail & Related papers  (2026-05-30T10:55:24Z)
• A Hybrid Vision-Language Architecture for Automated Defect Reasoning and Report Generation in Industrial Inspection [0.42970700836450487]
  This paper describes a decoupled, edge-deployable pipeline for wind turbine blade inspection.<n>The Eyes a Y26-x-obb oriented bounding-box localizes defects at dataset-native resolution.<n>The Bridge a deterministic, parameter-free encoding module maps each detected bounding box to grid-referenced tokens.
  arXiv  Detail & Related papers  (2026-05-26T04:27:38Z)
• RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases [49.47033473074821]
  We propose RelPrism, a multi-faceted self-supervised learning framework for RDBs.<n>RDB tasks often require multi-faceted information across different perspectives and granularities.<n>Our experiments show that RelPrism improves ROC-AUC by 4.15% for classification and reduces MAE by 10.75% for regression over state-of-the-art baselines.
  arXiv  Detail & Related papers  (2026-05-22T05:19:58Z)
• LLMEval-Logic: A Solver-Verified Chinese Benchmark for Logical Reasoning of LLMs with Adversarial Hardening [69.1037790901185]
  We present LLMEval-Logic, a Chinese logical reasoning benchmark built from realistic situational scenarios.<n>Its pipeline forward-authors and expert-audits natural-language items together with their reference formalizations, verifies annotated answers with Z3, constructs expert rubrics for natural-to-formal grading, and hardens selected items through a closed-loop adversarial workflow.
  arXiv  Detail & Related papers  (2026-05-19T09:40:29Z)
• MCPShield: Content-Aware Attack Detection for LLM Agent Tool-Call Traffic [1.827510863075184]
  The Model Context Protocol (MCP) has become a widely adopted interface for agents to invoke external tools.<n> MCP is presented as an attack framework for MCP tool-call traffic that encodes each agent session as a graph.
  arXiv  Detail & Related papers  (2026-05-11T14:55:48Z)
• Deployment-Relevant Alignment Cannot Be Inferred from Model-Level Evaluation Alone [11.663456969895462]
  Alignment evaluation in machine learning has largely become evaluation of models.<n>This paper argues that deployment-relevant alignment cannot be inferred from model-level evaluation alone.
  arXiv  Detail & Related papers  (2026-05-06T03:28:30Z)
• TADI: Tool-Augmented Drilling Intelligence via Agentic LLM Orchestration over Heterogeneous Wellsite Data [0.0]
  TADI (Tool-Augmented Drilling Intelligence) is an agentic AI system that transforms drilling operational data into evidence-based analytical intelligence.<n>TADI integrates 1,759 daily drilling reports, selected WIT real-time objects, 15,634 production records, formation tops, and perforations into a dual-store architecture.
  arXiv  Detail & Related papers  (2026-04-30T03:19:39Z)
• Benchmarking Small Language Models and Small Reasoning Language Models on System Log Severity Classification [3.192782465393035]
  We argue that severity classification is more informative when treated as a benchmark for probing runtime log comprehension rather than as an end task.<n>We evaluate nine small language models (SLMs) and small reasoning language models (SRLMs) under zero-shot, few-shot, and retrieval-augmented generation (RAG) prompting.
  arXiv  Detail & Related papers  (2026-01-12T18:02:33Z)
• Towards a Science of Scaling Agent Systems [79.64446272302287]
  We formalize a definition for agent evaluation and characterize scaling laws as the interplay between agent quantity, coordination structure, modelic, and task properties.<n>We derive a predictive model using coordination metrics, that cross-validated R2=0, enabling prediction on unseen task domains.<n>We identify three effects: (1) a tool-coordination trade-off: under fixed computational budgets, tool-heavy tasks suffer disproportionately from multi-agent overhead, and (2) a capability saturation: coordination yields diminishing or negative returns once single-agent baselines exceed 45%.
  arXiv  Detail & Related papers  (2025-12-09T06:52:21Z)
• Towards Global Retrieval Augmented Generation: A Benchmark for Corpus-Level Reasoning [50.27838512822097]
  We introduce GlobalQA, the first benchmark specifically designed to evaluate global RAG capabilities.<n>We propose GlobalRAG, a multi-tool collaborative framework that preserves structural coherence through chunk-level retrieval.<n>On the Qwen2.5-14B model, GlobalRAG achieves 6.63 F1 compared to the strongest baseline's 1.51 F1.
  arXiv  Detail & Related papers  (2025-10-30T07:29:14Z)
• vCache: Verified Semantic Prompt Caching [95.16654660556975]
  This paper proposes vCache, the first verified semantic cache with user-defined error rate guarantees.<n>It employs an online learning algorithm to estimate an optimal threshold for each cached prompt, enabling reliable cache responses without additional training.<n>Our experiments show that vCache consistently meets the specified error bounds while outperforming state-of-the-art static-threshold and fine-tuned embedding baselines.
  arXiv  Detail & Related papers  (2025-02-06T04:16:20Z)
• Text Classification via Large Language Models [63.1874290788797]
  We introduce Clue And Reasoning Prompting (CARP) to address complex linguistic phenomena involved in text classification. Remarkably, CARP yields new SOTA performances on 4 out of 5 widely-used text-classification benchmarks. More importantly, we find that CARP delivers impressive abilities on low-resource and domain-adaptation setups.
  arXiv  Detail & Related papers  (2023-05-15T06:24:45Z)
• Active Learning++: Incorporating Annotator's Rationale using Local Model Explanation [84.10721065676913]
  Annotators can provide their rationale for choosing a label by ranking input features based on their importance for a given query. Instead of weighing all committee models equally to select the next instance, we assign higher weight to the committee model with higher agreement with the annotator's ranking. This approach is applicable to any kind of ML model using model-agnostic techniques to generate local explanation such as LIME.
  arXiv  Detail & Related papers  (2020-09-06T08:07:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.