{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/forward-prediction-for-physical-reasoning","title":"Forward Prediction for Physical Reasoning","arxiv_id":"2006.10734","date":"2020-06-18","proceeding":null,"authors":["Rohit Girdhar","Laura Gustafson","Aaron Adcock","Laurens van der Maaten"],"abstract":"Physical reasoning requires forward prediction: the ability to forecast what will happen next given some initial world state. We study the performance of state-of-the-art forward-prediction models in the complex physical-reasoning tasks of the PHYRE benchmark. We do so by incorporating models that operate on object or pixel-based representations of the world into simple physical-reasoning agents. We find that forward-prediction models can improve physical-reasoning performance, particularly on complex tasks that involve many objects. However, we also find that these improvements are contingent on the test tasks being small variations of train tasks, and that generalization to completely new task templates is challenging. Surprisingly, we observe that forward predictors with better pixel accuracy do not necessarily lead to better physical-reasoning performance.Nevertheless, our best models set a new state-of-the-art on the PHYRE benchmark.","url_abs":"https://arxiv.org/abs/2006.10734v2","url_pdf":"https://arxiv.org/pdf/2006.10734v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"forward-prediction-for-physical-reasoning","repo_url":"https://github.com/facebookresearch/phyre-fwd","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"prediction","task_name":"Prediction"},{"task_slug":"visual-reasoning","task_name":"Visual Reasoning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/visual-reasoning-on-phyre-1b-cross","task":"Visual Reasoning","dataset":"PHYRE-1B-Cross","model":"Dec[Joint]1f","rank_in_archive_order":2,"of":4,"metrics":{"AUCCESS":"40.3"},"uses_additional_data":false},{"leaderboard":"/sota/visual-reasoning-on-phyre-1b-within","task":"Visual Reasoning","dataset":"PHYRE-1B-Within","model":"Dec[Joint]1f","rank_in_archive_order":3,"of":4,"metrics":{"AUCCESS":"80.0"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2006.10734","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2006.10734"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/facebookresearch/phyre-fwd","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":3},"by_repo_kind":{"official":{"samples":3,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"9ab97c79210ce676","entry":"compute_power_of_solutions","repo":"facebookresearch/phyre-fwd","repo_kind":"official","path":"src/python/phyre/diversity.py","file_url":"https://github.com/facebookresearch/phyre-fwd/blob/HEAD/src/python/phyre/diversity.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"9ab97c79210ce676"}},{"code_sha256_prefix":"6f441f2f7d8dce0f","entry":"get_action_mapper","repo":"facebookresearch/phyre-fwd","repo_kind":"official","path":"src/python/phyre/action_mappers.py","file_url":"https://github.com/facebookresearch/phyre-fwd/blob/HEAD/src/python/phyre/action_mappers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"6f441f2f7d8dce0f"}},{"code_sha256_prefix":"883326c758e1bab7","entry":"get_num_workers","repo":"facebookresearch/phyre-fwd","repo_kind":"official","path":"agents/im_fwd_agent.py","file_url":"https://github.com/facebookresearch/phyre-fwd/blob/HEAD/agents/im_fwd_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"883326c758e1bab7"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}