Intuitive physics learning in a deep-learning model inspired by developmental psychology.

Journal Information

Full Title: Nat Hum Behav

Abbreviation: Nat Hum Behav

Country: Unknown

Publisher: Unknown

Language: N/A

Publication Details

Subject Category: Behavioral Sciences

Available in Europe PMC: Yes

Available in PMC: Yes

PDF Available: No

Transparency Score
5/6
83.3% Transparent
Transparency Indicators
Click on green indicators to view evidence text
Core Indicators
Evidence found in paper:

"data availability instructions on accessing the physical concepts dataset are available at https://github com/deepmind/physical_concepts code availability our implementation of plato is not externally viable but the corresponding author may be contacted for any clarifying questions on implementation details for building plato."

Evidence found in paper:

"data availability instructions on accessing the physical concepts dataset are available at https://github com/deepmind/physical_concepts code availability our implementation of plato is not externally viable but the corresponding author may be contacted for any clarifying questions on implementation details for building plato."

Evidence found in paper:

"Competing interests The authors declare no competing interests."

Evidence found in paper:

"We thank C. Lew-Williams and K. Norman for input throughout this project; M. Shanahan, C. Burgess, M. Overlan and K. Allen for feedback on earlier versions of this manuscript. The authors received no specific funding for this work."

Protocol Registration
Open Access
Paper is freely available to read
Additional Indicators
Replication
Novelty Statement
Assessment Info

Tool: rtransparent

OST Version: N/A

Last Updated: Aug 05, 2025