mlsanityData to 7 Oct 2026

TRACTA: Benchmarking Temporal Reasoning over Semantic Trajectories

arXiv 2607.22365 ↗First posted 24 Jul 2026cs.AIcited by 0

On the map: LLM reasoning → Knowledge- and tool-augmented reasoning

Abstract (arXiv)

High-complexity operational environments require methods that characterize temporally distributed patterns rather than classify isolated events. This paper introduces TRACTA (Temporal Reasoning and Capability-Trajectory Analysis), a knowledge-aligned synthetic benchmark for temporal structural reasoning, instantiated through Multi-Domain Operations (MDO)-like scenarios. TRACTA defines offline structural annotations over contextual direct-impact and accumulated capability trajectories and evaluates three tasks: early_warning, pattern_detection, and run_classification. The frozen comparison includes raw-event neural references, a contract-lite rule comparator, and a recurrent semantic-input reference. The semantic-input recurrent reference has the highest aggregate macro-F1 point estimates, with the largest margins on the two temporal tasks, while raw-event references remain predictive and lead in four individual early-warning target--lead settings. Component-zeroing diagnostics show that both semantic trajectory blocks contain useful signal within the evaluated recurrent configuration. Run-local aliasing removes stable cross-run target and location identities from the primary raw input, although executed diagnostics retain shallow predictivity. These results are configuration-level: semantic inputs are aligned with the benchmark's target-generation space, and the evaluated systems also differ in architecture, training, and available information. TRACTA therefore provides a reproducible testbed for examining knowledge-aligned temporal prediction, not evidence of a causal representation advantage, statistically resolved superiority, or operational readiness.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Knowledge- and tool-augmented reasoning, one of 17 directions in LLM reasoning. Builds on 17 of its 31 references that are in the map. First posted on arXiv 24 Jul 2026.

Builds on

17 of 31 references.

References · 17

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  4. 2019Can You Trust Your Model's Uncertainty? Evaluating Predictive Uncertainty Under Dataset Shiftcited by 1,274
  5. 2018Deep learning for time series classification: a reviewcited by 575
  6. 2020A Transformer-based Framework for Multivariate Time Series Representation Learningcited by 449
  7. 2019InceptionTime: Finding AlexNet for Time Series Classificationcited by 386
  8. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 318
  9. 2020Data and its (dis)contents: A survey of dataset development and use in machine learning researchcited by 259
  10. 2020Neurosymbolic AI: The 3rd Wavecited by 253
  11. 2020Logic Tensor Networkscited by 197
  12. 2021Accounting for Variance in Machine Learning Benchmarkscited by 195
5 more
  1. 2016Theory-guided Data Science: A New Paradigm for Scientific Discovery from Datacited by 169
  2. 2020Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systemscited by 160
  3. 2019Synthetic Data for Deep Learningcited by 113
  4. 2021Incorporating Domain Knowledge into Deep Neural Networkscited by 56
  5. 2021Neuro-Symbolic Artificial Intelligence: Current Trendscited by 54

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026From Prompts to Pavement Through Time: Temporal Grounding in Agentic Scene-to-Plan Reasoning
  2. 2023Can Large Language Models be Good Path Planners? A Benchmark and Investigation on Spatial-temporal Reasoning
  3. 2025TIME: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios
  4. 2025Temporal Reasoning in AI systems
  5. 2023TimeBench: A Comprehensive Evaluation of Temporal Reasoning Abilities in Large Language Models
  6. 2026The Complexity Ceiling Benchmark: A Multi-Domain Evaluation of Sequential Reasoning Under Depth Scaling
  7. 2026Directional Reasoning Trajectory Change (DRTC): Identifying Critical Trace Segments in Reasoning Models
  8. 2026TemporalBench: A Benchmark for Evaluating LLM-Based Agents on Contextual and Event-Informed Time Series Tasks