{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:X5K7UQNXCIZS6V7CTZJOYOHUI6","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":"450713c059e2093eb582f531269e1b01fdf421b44a108e6f12ae5ad6207115d6","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T17:55:20Z","title_canon_sha256":"6b61cd0c69f6b5b1650602cc7decff69e3d12d1f6866590d6f2ef42f722f7f4a"},"schema_version":"1.0","source":{"id":"2504.11442","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.11442","created_at":"2026-07-05T11:08:40Z"},{"alias_kind":"arxiv_version","alias_value":"2504.11442v2","created_at":"2026-07-05T11:08:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11442","created_at":"2026-07-05T11:08:40Z"},{"alias_kind":"pith_short_12","alias_value":"X5K7UQNXCIZS","created_at":"2026-07-05T11:08:40Z"},{"alias_kind":"pith_short_16","alias_value":"X5K7UQNXCIZS6V7C","created_at":"2026-07-05T11:08:40Z"},{"alias_kind":"pith_short_8","alias_value":"X5K7UQNX","created_at":"2026-07-05T11:08:40Z"}],"graph_snapshots":[{"event_id":"sha256:e9d204fdbaab4d32e1f778034a3c8d2c8d9d2ec3ae10957293a5bcac29191113","target":"graph","created_at":"2026-07-05T11:08:40Z","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/2504.11442/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"TextArena is an open-source collection of competitive text-based games for training and evaluation of agentic behavior in Large Language Models (LLMs). It spans 57+ unique environments (including single-player, two-player, and multi-player setups) and allows for easy evaluation of model capabilities via an online-play system (against humans and other submitted models) with real-time TrueSkill scores. Traditional benchmarks rarely assess dynamic social skills such as negotiation, theory of mind, and deception, creating a gap that TextArena addresses. Designed with research, community and extens","authors_text":"Bobby Cheng, Bo Liu, Cheston Tan, Leon Guertler, Leshem Choshen, Simon Yu","cross_cats":["cs.AI","cs.LG","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T17:55:20Z","title":"TextArena"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11442","kind":"arxiv","version":2},"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:ff0d0206228830491c87ce70f4b09e1bca8ae8e8b1670a13f4a7c41da2ecbf70","target":"record","created_at":"2026-07-05T11:08:40Z","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":"450713c059e2093eb582f531269e1b01fdf421b44a108e6f12ae5ad6207115d6","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T17:55:20Z","title_canon_sha256":"6b61cd0c69f6b5b1650602cc7decff69e3d12d1f6866590d6f2ef42f722f7f4a"},"schema_version":"1.0","source":{"id":"2504.11442","kind":"arxiv","version":2}},"canonical_sha256":"bf55fa41b712332f57e29e52ec38f447b4b74d990b5fe0a397e06a014492555a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf55fa41b712332f57e29e52ec38f447b4b74d990b5fe0a397e06a014492555a","first_computed_at":"2026-07-05T11:08:40.969943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:40.969943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nW4yuJ5gpPJPTQwGgBMocLV5C04BpnUCljYIut5BaQFyaS88uDwWF433DLNRNEyfbUrVpRJh6S0IwyF3vvM5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:40.970421Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.11442","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff0d0206228830491c87ce70f4b09e1bca8ae8e8b1670a13f4a7c41da2ecbf70","sha256:e9d204fdbaab4d32e1f778034a3c8d2c8d9d2ec3ae10957293a5bcac29191113"],"state_sha256":"3a8c2e3ec366868acc7fcb993f7eebfa09b7247be33da91c019c327d8d9836b1"}