arXiv Machine Learning July 14, 2026 By Seongjin Choi

Training-Free Off-Screen Player Imputation for Broadcast-Based Spatial Football Analytics

Read the original on arXiv Machine Learning →

arXiv:2607. 11548v1 Announce Type: cross Abstract: Spatial football metrics such as pitch control assume access to the positions of all 22 players, yet the most widely available source of positional data -- the broadcast main camera -- shows only 10-16 of them at any moment.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

arXiv Machine Learning

Aug 11

Space-Creating versus Dead Possession: An Off-Ball Possession-Quality Index for Broadcast Football

arXiv:2608. 09887v1 Announce Type: cross Abstract: Ball possession is the most-cited and most-misleading number in football: 60% recycled in one's own half is not 60% spent pinning the opponent back.

By Seongjin Choi

arXiv AI

Jul 17

SportD: Can VLMs Physically Strategize?

arXiv:2607. 14616v1 Announce Type: new Abstract: Vision--language models have become increasingly capable of interpreting visual scenes, but it remains unclear whether they can use information to make strategically effective decisions.

By Jasin Cekinmez, Addison J. Wu, Haotian Xia, Akshaya Bharadhwaj, Anay Putty, Anirudh Ravishankar, Jaewoong Lee, Jinglin Xiao, Kyumin Andrew Shim, Mishika Ahuja, Nisarga Patil, Leo Liu, Zhuohan Liu, Weining Shen

llms benchmarks

arXiv AI

Aug 6

From Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness for Exact-Score Reranking

arXiv:2608. 05030v1 Announce Type: new Abstract: Football score forecasting combines a strong statistical core with a difficult contextual edge.

By Shaopeng Liang

llms rag benchmarks

arXiv Machine Learning

Jul 30

Sim2Win: A Team-Agnostic, Event-Based Pre-Match Outcome Prediction and Tactical Profiling System for Football

arXiv:2607. 26061v1 Announce Type: new Abstract: Pre-match tactical decision-making in professional football relies heavily on subjective expert analysis and identity-based scouting systems that cannot generalize to unseen teams.

By Mouad Zemzoumi, Amine Abouaomar

Hugging Face Trending Papers

Aug 5

From Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness for Exact-Score Reranking

Football score forecasting combines a strong statistical core with a difficult contextual edge. Dynamic Poisson-family models estimate team strength, expected goals, and coherent score probabilities, but do not directly understand roles, tactical matchups, motivation, or how a first goal changes behaviour.

llms rag benchmarks

arXiv AI

1d ago

Do Geometry-Aware Positional Encodings Help Transformers in Spatial Imperfect-Information Games?

arXiv:2608. 14982v1 Announce Type: cross Abstract: Transformers applied to spatial imperfect-information games must represent map geometry while tracking hidden entities through time.

By Wenji Fu

llms benchmarks safety

Related stories

Space-Creating versus Dead Possession: An Off-Ball Possession-Quality Index for Broadcast Football

SportD: Can VLMs Physically Strategize?

From Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness for Exact-Score Reranking

Sim2Win: A Team-Agnostic, Event-Based Pre-Match Outcome Prediction and Tactical Profiling System for Football

From Score Matrices to Football-Aware Match-State Simulation: An Auditable LLM Harness for Exact-Score Reranking

Do Geometry-Aware Positional Encodings Help Transformers in Spatial Imperfect-Information Games?