{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:H3SRUWBXVD43JP6QGLJC2S55NB","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":"3d3341817bf53a7e26f3b491044a5beda3b10afd09725d9c9ed71a4580ff62e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T09:16:22Z","title_canon_sha256":"187057f30d6dc0e47a5201e2a80c49a7060e9ccd70755f3c12cca035d5e965fc"},"schema_version":"1.0","source":{"id":"2605.29653","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.29653","created_at":"2026-05-29T01:05:53Z"},{"alias_kind":"arxiv_version","alias_value":"2605.29653v1","created_at":"2026-05-29T01:05:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29653","created_at":"2026-05-29T01:05:53Z"},{"alias_kind":"pith_short_12","alias_value":"H3SRUWBXVD43","created_at":"2026-05-29T01:05:53Z"},{"alias_kind":"pith_short_16","alias_value":"H3SRUWBXVD43JP6Q","created_at":"2026-05-29T01:05:53Z"},{"alias_kind":"pith_short_8","alias_value":"H3SRUWBX","created_at":"2026-05-29T01:05:53Z"}],"graph_snapshots":[{"event_id":"sha256:5d6c384d06b5c5c136c79f9b33192be2a7197b973bd6556a5094252db70cd8f7","target":"graph","created_at":"2026-05-29T01:05:53Z","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/2605.29653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chunping Wang, Dongdong Hua, Feng Gao, Renhong Huang, Yang Yang, Yifei Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T09:16:22Z","title":"PTCG-Bench: Can LLM Agents Master Pok\\'emon Trading Card Game?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29653","kind":"arxiv","version":1},"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":"sha256:4419a196393c6fd147cb06bcffdcf44ba47e77b498f9fc30315dc779ef3a4a19","target":"record","created_at":"2026-05-29T01:05:53Z","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":"3d3341817bf53a7e26f3b491044a5beda3b10afd09725d9c9ed71a4580ff62e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T09:16:22Z","title_canon_sha256":"187057f30d6dc0e47a5201e2a80c49a7060e9ccd70755f3c12cca035d5e965fc"},"schema_version":"1.0","source":{"id":"2605.29653","kind":"arxiv","version":1}},"canonical_sha256":"3ee51a5837a8f9b4bfd032d22d4bbd687a05bf5852c087a39183c9830eac30be","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ee51a5837a8f9b4bfd032d22d4bbd687a05bf5852c087a39183c9830eac30be","first_computed_at":"2026-05-29T01:05:53.166336Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T01:05:53.166336Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nrQpN4OJrXxe59SM7mImLNw/92TnvxWxYd3TXr1qkXwVSGxg4vlC8EX2tQwuSnPuCDqTJ977UARAWQtTA5kqCA==","signature_status":"signed_v1","signed_at":"2026-05-29T01:05:53.167131Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.29653","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4419a196393c6fd147cb06bcffdcf44ba47e77b498f9fc30315dc779ef3a4a19","sha256:5d6c384d06b5c5c136c79f9b33192be2a7197b973bd6556a5094252db70cd8f7"],"state_sha256":"1dd78de5d680961fd3939d48ae5a3def0fe74e4829a8ef5003655bfe760ea704"}