{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PZ6DCTDYO3N6MJU7LSQD2F2AES","short_pith_number":"pith:PZ6DCTDY","schema_version":"1.0","canonical_sha256":"7e7c314c7876dbe6269f5ca03d174024840dfb463e07f9c76b306a284727d0d4","source":{"kind":"arxiv","id":"2405.15383","version":2},"attestation_state":"computed","paper":{"title":"Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Matteo Merler, Minttu Alakuijala, Nicola Dainese, Pekka Marttinen","submitted_at":"2024-05-24T09:31:26Z","abstract_excerpt":"In this work we consider Code World Models, world models generated by a Large Language Model (LLM) in the form of Python code for model-based Reinforcement Learning (RL). Calling code instead of LLMs for planning has potential to be more precise, reliable, interpretable, and extremely efficient. However, writing appropriate Code World Models requires the ability to understand complex instructions, to generate exact code with non-trivial logic and to self-debug a long program with feedback from unit tests and environment trajectories. To address these challenges, we propose Generate, Improve an"},"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":"2405.15383","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-05-24T09:31:26Z","cross_cats_sorted":[],"title_canon_sha256":"5e423c0ebdff2e560d0c7b15f710f7ea50523fa17e1ffd98da37db3ea99c328a","abstract_canon_sha256":"70a6a92987bfb22f5fb8c183a89beff163b4f2c95c16351e945a0f0a25fe0504"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:31.172001Z","signature_b64":"hmdOLi0LV/hTl/9tPGuYmOh7KcekEke0d/rFayfleLcluONQF+v+NALYSlJpwsp6Wsh24bHG2KK3bP0w1XpvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e7c314c7876dbe6269f5ca03d174024840dfb463e07f9c76b306a284727d0d4","last_reissued_at":"2026-07-05T09:28:31.171504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:31.171504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Matteo Merler, Minttu Alakuijala, Nicola Dainese, Pekka Marttinen","submitted_at":"2024-05-24T09:31:26Z","abstract_excerpt":"In this work we consider Code World Models, world models generated by a Large Language Model (LLM) in the form of Python code for model-based Reinforcement Learning (RL). Calling code instead of LLMs for planning has potential to be more precise, reliable, interpretable, and extremely efficient. However, writing appropriate Code World Models requires the ability to understand complex instructions, to generate exact code with non-trivial logic and to self-debug a long program with feedback from unit tests and environment trajectories. To address these challenges, we propose Generate, Improve an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15383","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/2405.15383/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":"2405.15383","created_at":"2026-07-05T09:28:31.171562+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15383v2","created_at":"2026-07-05T09:28:31.171562+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15383","created_at":"2026-07-05T09:28:31.171562+00:00"},{"alias_kind":"pith_short_12","alias_value":"PZ6DCTDYO3N6","created_at":"2026-07-05T09:28:31.171562+00:00"},{"alias_kind":"pith_short_16","alias_value":"PZ6DCTDYO3N6MJU7","created_at":"2026-07-05T09:28:31.171562+00:00"},{"alias_kind":"pith_short_8","alias_value":"PZ6DCTDY","created_at":"2026-07-05T09:28:31.171562+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07925","citing_title":"ROSUM-MCTS: Monte Carlo Tree Search-Inspired HDL Code Summarization with Structural Rewards","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24375","citing_title":"Distilling Game Code World Model Generation into Lightweight Large Language Models","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24528","citing_title":"Hypothesis Generation and Inductive Inference in Children and Language Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18004","citing_title":"RL4RLA: Teaching ML to Discover Randomized Linear Algebra Algorithms Through Curriculum Design and Graph-Based Search","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2502.17419","citing_title":"From System 1 to System 2: A Survey of Reasoning Large Language Models","ref_index":130,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PZ6DCTDYO3N6MJU7LSQD2F2AES","json":"https://pith.science/pith/PZ6DCTDYO3N6MJU7LSQD2F2AES.json","graph_json":"https://pith.science/api/pith-number/PZ6DCTDYO3N6MJU7LSQD2F2AES/graph.json","events_json":"https://pith.science/api/pith-number/PZ6DCTDYO3N6MJU7LSQD2F2AES/events.json","paper":"https://pith.science/paper/PZ6DCTDY"},"agent_actions":{"view_html":"https://pith.science/pith/PZ6DCTDYO3N6MJU7LSQD2F2AES","download_json":"https://pith.science/pith/PZ6DCTDYO3N6MJU7LSQD2F2AES.json","view_paper":"https://pith.science/paper/PZ6DCTDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15383&json=true","fetch_graph":"https://pith.science/api/pith-number/PZ6DCTDYO3N6MJU7LSQD2F2AES/graph.json","fetch_events":"https://pith.science/api/pith-number/PZ6DCTDYO3N6MJU7LSQD2F2AES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PZ6DCTDYO3N6MJU7LSQD2F2AES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PZ6DCTDYO3N6MJU7LSQD2F2AES/action/storage_attestation","attest_author":"https://pith.science/pith/PZ6DCTDYO3N6MJU7LSQD2F2AES/action/author_attestation","sign_citation":"https://pith.science/pith/PZ6DCTDYO3N6MJU7LSQD2F2AES/action/citation_signature","submit_replication":"https://pith.science/pith/PZ6DCTDYO3N6MJU7LSQD2F2AES/action/replication_record"}},"created_at":"2026-07-05T09:28:31.171562+00:00","updated_at":"2026-07-05T09:28:31.171562+00:00"}