Research map / Time series / Causal and generative time series
Solving Temporal Puzzles
Check 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 |
|---|---|---|---|
| Use the proposed dynamics-based simplicity method instead of [9] | Video decryption sequences · Video decryption dataset | Kendall distance: 10% better on the javelin sequence | Helped |
| Use the proposed method instead of [9] | Video decryption sequences · Video decryption dataset | runtime: at least 2x faster; on the average 6x faster | Helped |
| Use the proposed method instead of [9] | Video decryption sequences · Video decryption dataset | sorting accuracy | Helped |
| Use the proposed method instead of [9] | Crowd photography sequences · Crowd photography datasets | normalized Kendall distance | Helped |
| Use the proposed method as the number of image sources increases and partial-order information decreases | Crowd photography sorting · Crowd photography datasets | normalized Kendall distance | Helped |
| Increase the amount of dynamic information spread across frames | The proposed method · Video decryption sequences | sorting accuracy | Helped |
| Use the proposed method instead of [9] | Paper sequence · Video decryption dataset | incorrectly sorted pairs: 48% of possible pairs sorted incorrectly by [9] | Helped |
Closest papers by meaning
- Discovering Sequential Patterns with Predictable Inter-event Delays (AAAI 2024 · similarity 0.80)
- Resolving Inconsistencies in Simple Temporal Problems: A Parameterized Approach (AAAI 2022 · similarity 0.79)
- AmortizedPeriod: Attention-based Amortized Inference for Periodicity Identification (ICLR 2024 · similarity 0.79)
- Segment, Shuffle, and Stitch: A Simple Layer for Improving Time-Series Representations (NeurIPS 2024 · similarity 0.78)
- LAST SToP for Modeling Asynchronous Time Series (ICML 2025 · similarity 0.78)
- HARDMath2: A Benchmark for Applied Mathematics Built by Students as Part of a Graduate Class (NeurIPS 2025 · similarity 0.78)
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.