Research map / Time series / Causal and generative time series
Temporal Logic Point Processes
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add first-order temporal logic rules as prior knowledge structuring the intensity (Temp Logic vs. data-driven baselines) | temporal logic point process · MIMIC-III survival prediction, small data (50 train) | accuracy: 0.584 vs 0.530 best baseline (BN) | Helped |
| Add temporal logic rules as prior knowledge (Temp Logic vs. RMTPP) | temporal logic point process · MIMIC-III time-to-survival MAE | MAE (days): 0.233 vs 0.464 at 50 train | Helped |
| Add temporal logic rules as prior knowledge (Temp Logic vs. RMTPP) at larger data size | temporal logic point process · MIMIC-III time-to-survival MAE (4000 train) | MAE (days): 0.227 vs 0.399 | Helped |
| Add temporal logic rules as prior knowledge in fraud detection | temporal logic point process · Credit card fraud, 500 train | accuracy: 0.728 vs 0.650 best baseline (LR) | Helped |
| Transfer learned logic weights from a large dataset (fine-tuned warm start) to a small target dataset (ablation) | temporal logic point process · MIMIC-III knowledge transfer | accuracy: 0.659 (Transfer2) vs 0.615 (benchmark) | Helped |
| Freeze transferred logic weights (Transfer1) instead of fine-tuning, relative to no transfer (ablation) | temporal logic point process · MIMIC-III knowledge transfer | accuracy: 0.637 vs 0.615 benchmark | Helped |
Closest papers by meaning
- Neuro-Symbolic Temporal Point Processes (ICML 2024 · similarity 0.87)
- DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding (NeurIPS 2025 · similarity 0.85)
- Evolving Minds: Logic-Informed Inference from Temporal Action Patterns (ICML 2025 · similarity 0.85)
- Latent Logic Tree Extraction for Event Sequence Explanation from LLMs (ICML 2024 · similarity 0.84)
- TEILP: Time Prediction over Knowledge Graphs via Logical Reasoning (AAAI 2024 · similarity 0.84)
- EasyTPP: Towards Open Benchmarking Temporal Point Processes (ICLR 2024 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.