{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:7O2GVQSZNXD5QIB4SCCS5VTLRB","short_pith_number":"pith:7O2GVQSZ","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"},"canonical_sha256":"fbb46ac2596dc7d8203c90852ed66b885fd16ece2e9bdce759298beec841671c","source":{"kind":"arxiv","id":"2305.14879","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14879","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14879v2","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14879","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_12","alias_value":"7O2GVQSZNXD5","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_16","alias_value":"7O2GVQSZNXD5QIB4","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_8","alias_value":"7O2GVQSZ","created_at":"2026-07-05T07:04:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:7O2GVQSZNXD5QIB4SCCS5VTLRB","target":"record","payload":{"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"},"canonical_sha256":"fbb46ac2596dc7d8203c90852ed66b885fd16ece2e9bdce759298beec841671c","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"},"source_kind":"arxiv","source_id":"2305.14879","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:04:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BxCTEm/vBRbevZoAQkcEP9nA4z0vNRylPDWYlwMAfrt007ucQ4jkXmkR6ZZ1h7SBA4ujMH4u42NLFK3Ieb36CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:20:44.127304Z"},"content_sha256":"087a2c958d000c6e64d2802e6e5d11fb6c73232c00abbee25452526a71e2b10d","schema_version":"1.0","event_id":"sha256:087a2c958d000c6e64d2802e6e5d11fb6c73232c00abbee25452526a71e2b10d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:7O2GVQSZNXD5QIB4SCCS5VTLRB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:04:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IMfVoIVyNkaAGnrttRZgdUbEmjeWtwlkxaP2Q5WzR0Ti1LRTgjl5EKkncGYDwLNmNZ6gf1l9dZ8FFSDoQs/VBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:20:44.127958Z"},"content_sha256":"848752b5591b049998243a83c972151681ea75d1a7e435c197266dcc56fb6d42","schema_version":"1.0","event_id":"sha256:848752b5591b049998243a83c972151681ea75d1a7e435c197266dcc56fb6d42"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB/bundle.json","state_url":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-09T06:20:44Z","links":{"resolver":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB","bundle":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB/bundle.json","state":"https://pith.science/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7O2GVQSZNXD5QIB4SCCS5VTLRB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7O2GVQSZNXD5QIB4SCCS5VTLRB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0958a1fac64784a86a610d8d70643aaccdb6584dad8eefa5a74fa47d7d87bd39","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T08:31:30Z","title_canon_sha256":"99fe9b974f21151d75e83c664523f9ea52a60a6128274ced4f8f5574e8e96321"},"schema_version":"1.0","source":{"id":"2305.14879","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14879","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14879v2","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14879","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_12","alias_value":"7O2GVQSZNXD5","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_16","alias_value":"7O2GVQSZNXD5QIB4","created_at":"2026-07-05T07:04:16Z"},{"alias_kind":"pith_short_8","alias_value":"7O2GVQSZ","created_at":"2026-07-05T07:04:16Z"}],"graph_snapshots":[{"event_id":"sha256:848752b5591b049998243a83c972151681ea75d1a7e435c197266dcc56fb6d42","target":"graph","created_at":"2026-07-05T07:04:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.14879/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Eric Yuan, Graham Todd, Marc-Alexandre C\\^ot\\'e, Peter Jansen, Ruoyao Wang, Ziang Xiao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T08:31:30Z","title":"ByteSized32: A Corpus and Challenge Task for Generating Task-Specific World Models Expressed as Text Games"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14879","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:087a2c958d000c6e64d2802e6e5d11fb6c73232c00abbee25452526a71e2b10d","target":"record","created_at":"2026-07-05T07:04:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0958a1fac64784a86a610d8d70643aaccdb6584dad8eefa5a74fa47d7d87bd39","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T08:31:30Z","title_canon_sha256":"99fe9b974f21151d75e83c664523f9ea52a60a6128274ced4f8f5574e8e96321"},"schema_version":"1.0","source":{"id":"2305.14879","kind":"arxiv","version":2}},"canonical_sha256":"fbb46ac2596dc7d8203c90852ed66b885fd16ece2e9bdce759298beec841671c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbb46ac2596dc7d8203c90852ed66b885fd16ece2e9bdce759298beec841671c","first_computed_at":"2026-07-05T07:04:16.274078Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:16.274078Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WyzNwvPiuudsxwshWnpl7YKskU3HIbdesQAVhxFaP9tHjRzIxdeRoB3vmIZCLT65Ff/KUmruajw2hO+Xl9T7Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:16.274456Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14879","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:087a2c958d000c6e64d2802e6e5d11fb6c73232c00abbee25452526a71e2b10d","sha256:848752b5591b049998243a83c972151681ea75d1a7e435c197266dcc56fb6d42"],"state_sha256":"fae05212d8b2c90470ac6351d4b2bc2941277b32e1f211f373e4c5cea9f66df4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oiA0zaKXfb+eGfWaIyBHkY1GpW/F+aOX9kgMVxlSTYI7WihZ9tmHqeyxLDA4EbhYe7wV/1A6BU+Bljcng4J/BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:20:44.131204Z","bundle_sha256":"877532df6296bc071b87a7af8c0e8333a813cf85ab12af559e0a7d02dc21041a"}}