{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7O2GVQSZNXD5QIB4SCCS5VTLRB","short_pith_number":"pith:7O2GVQSZ","schema_version":"1.0","canonical_sha256":"fbb46ac2596dc7d8203c90852ed66b885fd16ece2e9bdce759298beec841671c","source":{"kind":"arxiv","id":"2305.14879","version":2},"attestation_state":"computed","paper":{"title":"ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eric Yuan, Graham Todd, Marc-Alexandre C\\^ot\\'e, Peter Jansen, Ruoyao Wang, Ziang Xiao","submitted_at":"2023-05-24T08:31:30Z","abstract_excerpt":"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 gam"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2305.14879","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T08:31:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"99fe9b974f21151d75e83c664523f9ea52a60a6128274ced4f8f5574e8e96321","abstract_canon_sha256":"0958a1fac64784a86a610d8d70643aaccdb6584dad8eefa5a74fa47d7d87bd39"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:16.274456Z","signature_b64":"WyzNwvPiuudsxwshWnpl7YKskU3HIbdesQAVhxFaP9tHjRzIxdeRoB3vmIZCLT65Ff/KUmruajw2hO+Xl9T7Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbb46ac2596dc7d8203c90852ed66b885fd16ece2e9bdce759298beec841671c","last_reissued_at":"2026-07-05T07:04:16.274078Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:16.274078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eric Yuan, Graham Todd, Marc-Alexandre C\\^ot\\'e, Peter Jansen, Ruoyao Wang, Ziang Xiao","submitted_at":"2023-05-24T08:31:30Z","abstract_excerpt":"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 gam"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14879","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2305.14879/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2305.14879","created_at":"2026-07-05T07:04:16.274135+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.14879v2","created_at":"2026-07-05T07:04:16.274135+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14879","created_at":"2026-07-05T07:04:16.274135+00:00"},{"alias_kind":"pith_short_12","alias_value":"7O2GVQSZNXD5","created_at":"2026-07-05T07:04:16.274135+00:00"},{"alias_kind":"pith_short_16","alias_value":"7O2GVQSZNXD5QIB4","created_at":"2026-07-05T07:04:16.274135+00:00"},{"alias_kind":"pith_short_8","alias_value":"7O2GVQSZ","created_at":"2026-07-05T07:04:16.274135+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB","json":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB.json","graph_json":"https://pith.science/api/pith-number/7O2GVQSZNXD5QIB4SCCS5VTLRB/graph.json","events_json":"https://pith.science/api/pith-number/7O2GVQSZNXD5QIB4SCCS5VTLRB/events.json","paper":"https://pith.science/paper/7O2GVQSZ"},"agent_actions":{"view_html":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB","download_json":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB.json","view_paper":"https://pith.science/paper/7O2GVQSZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.14879&json=true","fetch_graph":"https://pith.science/api/pith-number/7O2GVQSZNXD5QIB4SCCS5VTLRB/graph.json","fetch_events":"https://pith.science/api/pith-number/7O2GVQSZNXD5QIB4SCCS5VTLRB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB/action/storage_attestation","attest_author":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB/action/author_attestation","sign_citation":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB/action/citation_signature","submit_replication":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB/action/replication_record"}},"created_at":"2026-07-05T07:04:16.274135+00:00","updated_at":"2026-07-05T07:04:16.274135+00:00"}