{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:H3SRUWBXVD43JP6QGLJC2S55NB","short_pith_number":"pith:H3SRUWBX","schema_version":"1.0","canonical_sha256":"3ee51a5837a8f9b4bfd032d22d4bbd687a05bf5852c087a39183c9830eac30be","source":{"kind":"arxiv","id":"2605.29653","version":1},"attestation_state":"computed","paper":{"title":"PTCG-Bench: Can LLM Agents Master Pok\\'emon Trading Card Game?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunping Wang, Dongdong Hua, Feng Gao, Renhong Huang, Yang Yang, Yifei Sun","submitted_at":"2026-05-28T09:16:22Z","abstract_excerpt":"Given a strategically complex board game, human players can quickly learn to devise strategies after playing a few rounds. Autonomous agents require similar capabilities in realistic interactive environments, yet existing agent benchmarks often fail to fully capture such strategic and evolving decision-making scenarios. We present PTCG-Bench, a benchmark built on the Pok'{e}mon Trading Card Game (PTCG) that evaluates LLM agents at two complementary levels: (1) their decision-making performance within a single complex environment, and (2) their ability to self-evolving through accumulated exper"},"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":"2605.29653","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T09:16:22Z","cross_cats_sorted":[],"title_canon_sha256":"187057f30d6dc0e47a5201e2a80c49a7060e9ccd70755f3c12cca035d5e965fc","abstract_canon_sha256":"3d3341817bf53a7e26f3b491044a5beda3b10afd09725d9c9ed71a4580ff62e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:53.167131Z","signature_b64":"nrQpN4OJrXxe59SM7mImLNw/92TnvxWxYd3TXr1qkXwVSGxg4vlC8EX2tQwuSnPuCDqTJ977UARAWQtTA5kqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3ee51a5837a8f9b4bfd032d22d4bbd687a05bf5852c087a39183c9830eac30be","last_reissued_at":"2026-05-29T01:05:53.166336Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:53.166336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PTCG-Bench: Can LLM Agents Master Pok\\'emon Trading Card Game?","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunping Wang, Dongdong Hua, Feng Gao, Renhong Huang, Yang Yang, Yifei Sun","submitted_at":"2026-05-28T09:16:22Z","abstract_excerpt":"Given a strategically complex board game, human players can quickly learn to devise strategies after playing a few rounds. Autonomous agents require similar capabilities in realistic interactive environments, yet existing agent benchmarks often fail to fully capture such strategic and evolving decision-making scenarios. We present PTCG-Bench, a benchmark built on the Pok'{e}mon Trading Card Game (PTCG) that evaluates LLM agents at two complementary levels: (1) their decision-making performance within a single complex environment, and (2) their ability to self-evolving through accumulated exper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29653","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/2605.29653/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":"2605.29653","created_at":"2026-05-29T01:05:53.166469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29653v1","created_at":"2026-05-29T01:05:53.166469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29653","created_at":"2026-05-29T01:05:53.166469+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3SRUWBXVD43","created_at":"2026-05-29T01:05:53.166469+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3SRUWBXVD43JP6Q","created_at":"2026-05-29T01:05:53.166469+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3SRUWBX","created_at":"2026-05-29T01:05:53.166469+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/H3SRUWBXVD43JP6QGLJC2S55NB","json":"https://pith.science/pith/H3SRUWBXVD43JP6QGLJC2S55NB.json","graph_json":"https://pith.science/api/pith-number/H3SRUWBXVD43JP6QGLJC2S55NB/graph.json","events_json":"https://pith.science/api/pith-number/H3SRUWBXVD43JP6QGLJC2S55NB/events.json","paper":"https://pith.science/paper/H3SRUWBX"},"agent_actions":{"view_html":"https://pith.science/pith/H3SRUWBXVD43JP6QGLJC2S55NB","download_json":"https://pith.science/pith/H3SRUWBXVD43JP6QGLJC2S55NB.json","view_paper":"https://pith.science/paper/H3SRUWBX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29653&json=true","fetch_graph":"https://pith.science/api/pith-number/H3SRUWBXVD43JP6QGLJC2S55NB/graph.json","fetch_events":"https://pith.science/api/pith-number/H3SRUWBXVD43JP6QGLJC2S55NB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3SRUWBXVD43JP6QGLJC2S55NB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3SRUWBXVD43JP6QGLJC2S55NB/action/storage_attestation","attest_author":"https://pith.science/pith/H3SRUWBXVD43JP6QGLJC2S55NB/action/author_attestation","sign_citation":"https://pith.science/pith/H3SRUWBXVD43JP6QGLJC2S55NB/action/citation_signature","submit_replication":"https://pith.science/pith/H3SRUWBXVD43JP6QGLJC2S55NB/action/replication_record"}},"created_at":"2026-05-29T01:05:53.166469+00:00","updated_at":"2026-05-29T01:05:53.166469+00:00"}