{"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/bytesized32-a-corpus-and-challenge-task-for","title":"ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games","arxiv_id":"2305.14879","date":"2023-05-24","proceeding":null,"authors":["Ruoyao Wang","Graham Todd","Eric Yuan","Ziang Xiao","Marc-Alexandre Côté","Peter Jansen"],"abstract":"In this work, we investigate the capacity of language models to generate explicit, interpretable, and interactive world models of scientific and common-sense reasoning tasks. We operationalize this as a task of generating text games, expressed as hundreds of lines of Python code. To facilitate this task, we introduce ByteSized32 (Code: github.com/cognitiveailab/BYTESIZED32), a corpus of 32 reasoning-focused text games totaling 20k lines of Python code. We empirically demonstrate that GPT-4 can use these games as templates for single-shot in-context learning, successfully producing runnable games on unseen topics in 28% of cases. When allowed to self-reflect on program errors, game runnability substantially increases to 57%. While evaluating simulation fidelity is labor-intensive, we introduce a suite of automated metrics to assess game fidelity, technical validity, adherence to task specifications, and winnability, showing a high degree of agreement with expert human ratings. We pose this as a challenge task to spur further development at the juncture of world modeling and code generation.","url_abs":"https://arxiv.org/abs/2305.14879v2","url_pdf":"https://arxiv.org/pdf/2305.14879v2.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":"bytesized32-a-corpus-and-challenge-task-for","repo_url":"https://github.com/cognitiveailab/bytesized32","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"common-sense-reasoning","task_name":"Common Sense Reasoning"},{"task_slug":"in-context-learning","task_name":"In-Context Learning"},{"task_slug":"text-based-games","task_name":"text-based games"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"gpt-4","method_name":"GPT-4"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2305.14879","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2305.14879"}},"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/cognitiveailab/bytesized32","reach":{"status":"ok","spdx":"Apache-2.0"}},{"provenance":"deterministic:regex_extraction","url":"https://github.com/cognitiveailab/BYTESIZED32","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":8},"by_repo_kind":{"official":{"samples":8,"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":"01a359166103f27a","entry":"build_requirement_text","repo":"cognitiveailab/BYTESIZED32","repo_kind":"official","path":"bytes32/compliance.py","file_url":"https://github.com/cognitiveailab/BYTESIZED32/blob/HEAD/bytes32/compliance.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":"01a359166103f27a"}},{"code_sha256_prefix":"fc7803997d03e484","entry":"check_validity","repo":"cognitiveailab/BYTESIZED32","repo_kind":"official","path":"bytes32/validity.py","file_url":"https://github.com/cognitiveailab/BYTESIZED32/blob/HEAD/bytes32/validity.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":"fc7803997d03e484"}},{"code_sha256_prefix":"4fe1ce1ee1520f46","entry":"clean","repo":"cognitiveailab/BYTESIZED32","repo_kind":"official","path":"bytes32/winnability/language_agent.py","file_url":"https://github.com/cognitiveailab/BYTESIZED32/blob/HEAD/bytes32/winnability/language_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":"4fe1ce1ee1520f46"}},{"code_sha256_prefix":"9e4c4702c63966aa","entry":"count_tokens","repo":"cognitiveailab/BYTESIZED32","repo_kind":"official","path":"bytes32/utils.py","file_url":"https://github.com/cognitiveailab/BYTESIZED32/blob/HEAD/bytes32/utils.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":"9e4c4702c63966aa"}},{"code_sha256_prefix":"f21824b218425eec","entry":"extract_initial_action_token","repo":"cognitiveailab/BYTESIZED32","repo_kind":"official","path":"bytes32/alignment.py","file_url":"https://github.com/cognitiveailab/BYTESIZED32/blob/HEAD/bytes32/alignment.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":"f21824b218425eec"}},{"code_sha256_prefix":"23ee3a98708a8381","entry":"get_tokenizer","repo":"cognitiveailab/BYTESIZED32","repo_kind":"official","path":"bytes32/utils.py","file_url":"https://github.com/cognitiveailab/BYTESIZED32/blob/HEAD/bytes32/utils.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":"23ee3a98708a8381"}},{"code_sha256_prefix":"cb994dc33f763671","entry":"parse_game_file_name","repo":"cognitiveailab/BYTESIZED32","repo_kind":"official","path":"bytes32/compliance.py","file_url":"https://github.com/cognitiveailab/BYTESIZED32/blob/HEAD/bytes32/compliance.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":"cb994dc33f763671"}},{"code_sha256_prefix":"49a58281274253aa","entry":"sample_actions","repo":"cognitiveailab/BYTESIZED32","repo_kind":"official","path":"bytes32/validity.py","file_url":"https://github.com/cognitiveailab/BYTESIZED32/blob/HEAD/bytes32/validity.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":"49a58281274253aa"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}