{"url":"/task/physical-intuition","name":"Physical Intuition","slug":"physical-intuition","description_markdown":null,"categories":[{"name":"Methodology","url":"/area/methodology"},{"name":"Miscellaneous","url":"/area/miscellaneous"},{"name":"Reasoning","url":"/area/reasoning"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":35,"papers_with_code":15,"benchmarks":1,"benchmark_tables_in_archive":1,"benchmark_tables_shown":1,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":1,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/physical-intuition-on-big-bench","slug":"physical-intuition-on-big-bench","dataset":"BIG-bench","dataset_url":"/dataset/big-bench","rows_in_archive":2,"metrics":["Accuracy"],"first_row_in_archive_order":{"model":"Chinchilla-70B (few-shot, k=5)","paper_title":"Training Compute-Optimal Large Language Models","paper_url":"/paper/training-compute-optimal-large-language","paper_date":"2022-03-29","arxiv_id":"2203.15556","code_links":[{"title":"karpathy/llama2.c","url":"https://github.com/karpathy/llama2.c"},{"title":"nkluge-correa/teenytinyllama","url":"https://github.com/nkluge-correa/teenytinyllama"}],"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":4}}}],"datasets":[{"url":"/dataset/big-bench","name":"BIG-bench","full_name":"Beyond the Imitation Game Benchmark","num_papers_in_archive":349}],"subtasks":[],"parent_tasks":[{"url":"/task/logical-reasoning","name":"Logical Reasoning"}],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":15,"of":15,"tagged_in_all":35,"items":[{"url":"/paper/scaling-language-models-methods-analysis-1","title":"Scaling Language Models: Methods, Analysis & Insights from Training Gopher","date":"2021-12-08","arxiv_id":"2112.11446","repositories_listed":3,"syntology":null},{"url":"/paper/learning-physical-intuition-of-block-towers","title":"Learning Physical Intuition of Block Towers by Example","date":"2016-03-03","arxiv_id":"1603.01312","repositories_listed":3,"syntology":null},{"url":"/paper/training-compute-optimal-large-language","title":"Training Compute-Optimal Large Language Models","date":"2022-03-29","arxiv_id":"2203.15556","repositories_listed":2,"syntology":{"n":11,"n_ran":8,"n_unverified":3,"n_pointer_only":4}},{"url":"/paper/examining-the-source-of-defects-from-a","title":"Examining the Source of Defects from a Mechanical Perspective for 3D Anomaly Detection","date":"2025-05-09","arxiv_id":"2505.05901","repositories_listed":1,"syntology":null},{"url":"/paper/physics-inspired-distributed-radio-map","title":"Physics-Inspired Distributed Radio Map Estimation","date":"2025-02-01","arxiv_id":"2502.00319","repositories_listed":1,"syntology":null},{"url":"/paper/ai-accelerated-discovery-of-high-critical","title":"InvDesFlow: An AI-driven materials inverse design workflow to explore possible high-temperature superconductors","date":"2024-09-12","arxiv_id":"2409.08065","repositories_listed":1,"syntology":null},{"url":"/paper/mechagents-large-language-model-multi-agent","title":"MechAgents: Large language model multi-agent collaborations can solve mechanics problems, generate new data, and integrate knowledge","date":"2023-11-14","arxiv_id":"2311.08166","repositories_listed":1,"syntology":null},{"url":"/paper/learning-force-laws-in-many-body-systems","title":"Physics-tailored machine learning reveals unexpected physics in dusty plasmas","date":"2023-10-08","arxiv_id":"2310.05273","repositories_listed":1,"syntology":null},{"url":"/paper/constructing-custom-thermodynamics-using-deep","title":"Constructing Custom Thermodynamics Using Deep Learning","date":"2023-08-08","arxiv_id":"2308.04119","repositories_listed":1,"syntology":null},{"url":"/paper/generalizing-adam-to-manifolds-for","title":"Generalizing Adam to Manifolds for Efficiently Training Transformers","date":"2023-05-26","arxiv_id":"2305.16901","repositories_listed":1,"syntology":null},{"url":"/paper/automated-optical-multi-layer-design-via-deep","title":"Automated Optical Multi-layer Design via Deep Reinforcement Learning","date":"2020-06-21","arxiv_id":"2006.11940","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-2d-data-to-learn-textured-3d-mesh","title":"Leveraging 2D Data to Learn Textured 3D Mesh Generation","date":"2020-04-08","arxiv_id":"2004.04180","repositories_listed":1,"syntology":null},{"url":"/paper/interpretable-embeddings-from-molecular","title":"Interpretable Embeddings From Molecular Simulations Using Gaussian Mixture Variational Autoencoders","date":"2019-12-22","arxiv_id":"1912.12175","repositories_listed":1,"syntology":null},{"url":"/paper/meta-learning-for-stochastic-gradient-mcmc","title":"Meta-Learning for Stochastic Gradient MCMC","date":"2018-06-12","arxiv_id":"1806.04522","repositories_listed":1,"syntology":null},{"url":"/paper/shapestacks-learning-vision-based-physical","title":"ShapeStacks: Learning Vision-Based Physical Intuition for Generalised Object Stacking","date":"2018-04-21","arxiv_id":"1804.08018","repositories_listed":1,"syntology":null}],"syntology_records":1,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}