{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:DG7R2NX6OXC72PDZ2QQYY3UBAQ","short_pith_number":"pith:DG7R2NX6","schema_version":"1.0","canonical_sha256":"19bf1d36fe75c5fd3c79d4218c6e81043bd3de6b4c01b65fb51a7d9b4b0dda47","source":{"kind":"arxiv","id":"2605.24375","version":1},"attestation_state":"computed","paper":{"title":"Distilling Game Code World Model Generation into Lightweight Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amy Greenwald, Arjun Prakash, Haoyang Xu, Kevin Wang, Tyrone Serapio","submitted_at":"2026-05-23T03:30:36Z","abstract_excerpt":"Large Language Models (LLMs) have shown great ability in generating executable code from natural language, opening the possibility of automatically constructing environments for AI agents. Recent work on Code World Models (CWMs) demonstrates that LLMs can translate game rules into Python implementations compatible with solvers like Monte Carlo Tree Search. We study this problem in game settings, where generated environments must implement rules, legal actions, state transitions, observations, and rewards. We refer to these game-specific executable models as Game Code World Models (GameCWMs). H"},"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":"2605.24375","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T03:30:36Z","cross_cats_sorted":[],"title_canon_sha256":"968a96ace434995d160c1dbb272d27c035e21251fdea63946e819d8820743abe","abstract_canon_sha256":"63a265eb7933d3c84d435e4519e969b58f332b2f9e4c8174db07bb9521201ca9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:02.529894Z","signature_b64":"mrabKXPQMUV5/b34oATj1T9HXi6r5/gakCkdpiq27/vZgRTGe7LAeIVkERTXaSXhYzIqq40sZ5CKqWA8mOXPCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19bf1d36fe75c5fd3c79d4218c6e81043bd3de6b4c01b65fb51a7d9b4b0dda47","last_reissued_at":"2026-05-26T01:03:02.529068Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:02.529068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Distilling Game Code World Model Generation into Lightweight Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Amy Greenwald, Arjun Prakash, Haoyang Xu, Kevin Wang, Tyrone Serapio","submitted_at":"2026-05-23T03:30:36Z","abstract_excerpt":"Large Language Models (LLMs) have shown great ability in generating executable code from natural language, opening the possibility of automatically constructing environments for AI agents. Recent work on Code World Models (CWMs) demonstrates that LLMs can translate game rules into Python implementations compatible with solvers like Monte Carlo Tree Search. We study this problem in game settings, where generated environments must implement rules, legal actions, state transitions, observations, and rewards. We refer to these game-specific executable models as Game Code World Models (GameCWMs). H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24375","kind":"arxiv","version":1},"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/2605.24375/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":"2605.24375","created_at":"2026-05-26T01:03:02.529198+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24375v1","created_at":"2026-05-26T01:03:02.529198+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24375","created_at":"2026-05-26T01:03:02.529198+00:00"},{"alias_kind":"pith_short_12","alias_value":"DG7R2NX6OXC7","created_at":"2026-05-26T01:03:02.529198+00:00"},{"alias_kind":"pith_short_16","alias_value":"DG7R2NX6OXC72PDZ","created_at":"2026-05-26T01:03:02.529198+00:00"},{"alias_kind":"pith_short_8","alias_value":"DG7R2NX6","created_at":"2026-05-26T01:03:02.529198+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/DG7R2NX6OXC72PDZ2QQYY3UBAQ","json":"https://pith.science/pith/DG7R2NX6OXC72PDZ2QQYY3UBAQ.json","graph_json":"https://pith.science/api/pith-number/DG7R2NX6OXC72PDZ2QQYY3UBAQ/graph.json","events_json":"https://pith.science/api/pith-number/DG7R2NX6OXC72PDZ2QQYY3UBAQ/events.json","paper":"https://pith.science/paper/DG7R2NX6"},"agent_actions":{"view_html":"https://pith.science/pith/DG7R2NX6OXC72PDZ2QQYY3UBAQ","download_json":"https://pith.science/pith/DG7R2NX6OXC72PDZ2QQYY3UBAQ.json","view_paper":"https://pith.science/paper/DG7R2NX6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24375&json=true","fetch_graph":"https://pith.science/api/pith-number/DG7R2NX6OXC72PDZ2QQYY3UBAQ/graph.json","fetch_events":"https://pith.science/api/pith-number/DG7R2NX6OXC72PDZ2QQYY3UBAQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DG7R2NX6OXC72PDZ2QQYY3UBAQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DG7R2NX6OXC72PDZ2QQYY3UBAQ/action/storage_attestation","attest_author":"https://pith.science/pith/DG7R2NX6OXC72PDZ2QQYY3UBAQ/action/author_attestation","sign_citation":"https://pith.science/pith/DG7R2NX6OXC72PDZ2QQYY3UBAQ/action/citation_signature","submit_replication":"https://pith.science/pith/DG7R2NX6OXC72PDZ2QQYY3UBAQ/action/replication_record"}},"created_at":"2026-05-26T01:03:02.529198+00:00","updated_at":"2026-05-26T01:03:02.529198+00:00"}