{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KWHW6JX3JR3XOYQPWYOMLKEZ5K","short_pith_number":"pith:KWHW6JX3","schema_version":"1.0","canonical_sha256":"558f6f26fb4c7777620fb61cc5a899eab05f7a6c2eecec6d559cd4b562d88421","source":{"kind":"arxiv","id":"2503.04094","version":1},"attestation_state":"computed","paper":{"title":"Pok\\'eChamp: an Expert-level Minimax Language Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Andy Luu Nguyen, Chi Jin, Seth Karten","submitted_at":"2025-03-06T05:06:27Z","abstract_excerpt":"We introduce Pok\\'eChamp, a minimax agent powered by Large Language Models (LLMs) for Pok\\'emon battles. Built on a general framework for two-player competitive games, Pok\\'eChamp leverages the generalist capabilities of LLMs to enhance minimax tree search. Specifically, LLMs replace three key modules: (1) player action sampling, (2) opponent modeling, and (3) value function estimation, enabling the agent to effectively utilize gameplay history and human knowledge to reduce the search space and address partial observability. Notably, our framework requires no additional LLM training. We evalua"},"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":"2503.04094","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-06T05:06:27Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"5e34f993d192f8ae2b043271374b3866b45a98d152725f13d8bfab878f3a263f","abstract_canon_sha256":"c660bccd24ebe104efe23a63860083fec1ff4da075aecb5ae4b312c484f8318c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:25:28.797223Z","signature_b64":"QaRY+Paa2eQN62JmocvmA4PalHqcF0QsT2u/AHTNMxoN4PBZrtxY4fc1rQ385fK7TBnZKxxA84Ph/wD6O2ChDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"558f6f26fb4c7777620fb61cc5a899eab05f7a6c2eecec6d559cd4b562d88421","last_reissued_at":"2026-07-05T10:25:28.796487Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:25:28.796487Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pok\\'eChamp: an Expert-level Minimax Language Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.LG","authors_text":"Andy Luu Nguyen, Chi Jin, Seth Karten","submitted_at":"2025-03-06T05:06:27Z","abstract_excerpt":"We introduce Pok\\'eChamp, a minimax agent powered by Large Language Models (LLMs) for Pok\\'emon battles. Built on a general framework for two-player competitive games, Pok\\'eChamp leverages the generalist capabilities of LLMs to enhance minimax tree search. Specifically, LLMs replace three key modules: (1) player action sampling, (2) opponent modeling, and (3) value function estimation, enabling the agent to effectively utilize gameplay history and human knowledge to reduce the search space and address partial observability. Notably, our framework requires no additional LLM training. We evalua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.04094","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/2503.04094/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":"2503.04094","created_at":"2026-07-05T10:25:28.796593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.04094v1","created_at":"2026-07-05T10:25:28.796593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.04094","created_at":"2026-07-05T10:25:28.796593+00:00"},{"alias_kind":"pith_short_12","alias_value":"KWHW6JX3JR3X","created_at":"2026-07-05T10:25:28.796593+00:00"},{"alias_kind":"pith_short_16","alias_value":"KWHW6JX3JR3XOYQP","created_at":"2026-07-05T10:25:28.796593+00:00"},{"alias_kind":"pith_short_8","alias_value":"KWHW6JX3","created_at":"2026-07-05T10:25:28.796593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.12145","citing_title":"Automatic Generation of High-Performance RL Environments","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09998","citing_title":"Continual Harness: Online Adaptation for Self-Improving Foundation Agents","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18394","citing_title":"OpenGame: Open Agentic Coding for Games","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KWHW6JX3JR3XOYQPWYOMLKEZ5K","json":"https://pith.science/pith/KWHW6JX3JR3XOYQPWYOMLKEZ5K.json","graph_json":"https://pith.science/api/pith-number/KWHW6JX3JR3XOYQPWYOMLKEZ5K/graph.json","events_json":"https://pith.science/api/pith-number/KWHW6JX3JR3XOYQPWYOMLKEZ5K/events.json","paper":"https://pith.science/paper/KWHW6JX3"},"agent_actions":{"view_html":"https://pith.science/pith/KWHW6JX3JR3XOYQPWYOMLKEZ5K","download_json":"https://pith.science/pith/KWHW6JX3JR3XOYQPWYOMLKEZ5K.json","view_paper":"https://pith.science/paper/KWHW6JX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.04094&json=true","fetch_graph":"https://pith.science/api/pith-number/KWHW6JX3JR3XOYQPWYOMLKEZ5K/graph.json","fetch_events":"https://pith.science/api/pith-number/KWHW6JX3JR3XOYQPWYOMLKEZ5K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KWHW6JX3JR3XOYQPWYOMLKEZ5K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KWHW6JX3JR3XOYQPWYOMLKEZ5K/action/storage_attestation","attest_author":"https://pith.science/pith/KWHW6JX3JR3XOYQPWYOMLKEZ5K/action/author_attestation","sign_citation":"https://pith.science/pith/KWHW6JX3JR3XOYQPWYOMLKEZ5K/action/citation_signature","submit_replication":"https://pith.science/pith/KWHW6JX3JR3XOYQPWYOMLKEZ5K/action/replication_record"}},"created_at":"2026-07-05T10:25:28.796593+00:00","updated_at":"2026-07-05T10:25:28.796593+00:00"}