{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X5K7UQNXCIZS6V7CTZJOYOHUI6","short_pith_number":"pith:X5K7UQNX","schema_version":"1.0","canonical_sha256":"bf55fa41b712332f57e29e52ec38f447b4b74d990b5fe0a397e06a014492555a","source":{"kind":"arxiv","id":"2504.11442","version":2},"attestation_state":"computed","paper":{"title":"TextArena","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.CL","authors_text":"Bobby Cheng, Bo Liu, Cheston Tan, Leon Guertler, Leshem Choshen, Simon Yu","submitted_at":"2025-04-15T17:55:20Z","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"},"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":"2504.11442","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-15T17:55:20Z","cross_cats_sorted":["cs.AI","cs.LG","cs.MA"],"title_canon_sha256":"6b61cd0c69f6b5b1650602cc7decff69e3d12d1f6866590d6f2ef42f722f7f4a","abstract_canon_sha256":"450713c059e2093eb582f531269e1b01fdf421b44a108e6f12ae5ad6207115d6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:40.970421Z","signature_b64":"nW4yuJ5gpPJPTQwGgBMocLV5C04BpnUCljYIut5BaQFyaS88uDwWF433DLNRNEyfbUrVpRJh6S0IwyF3vvM5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf55fa41b712332f57e29e52ec38f447b4b74d990b5fe0a397e06a014492555a","last_reissued_at":"2026-07-05T11:08:40.969943Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:40.969943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextArena","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.MA"],"primary_cat":"cs.CL","authors_text":"Bobby Cheng, Bo Liu, Cheston Tan, Leon Guertler, Leshem Choshen, Simon Yu","submitted_at":"2025-04-15T17:55:20Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.11442","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/2504.11442/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":"2504.11442","created_at":"2026-07-05T11:08:40.970004+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.11442v2","created_at":"2026-07-05T11:08:40.970004+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.11442","created_at":"2026-07-05T11:08:40.970004+00:00"},{"alias_kind":"pith_short_12","alias_value":"X5K7UQNXCIZS","created_at":"2026-07-05T11:08:40.970004+00:00"},{"alias_kind":"pith_short_16","alias_value":"X5K7UQNXCIZS6V7C","created_at":"2026-07-05T11:08:40.970004+00:00"},{"alias_kind":"pith_short_8","alias_value":"X5K7UQNX","created_at":"2026-07-05T11:08:40.970004+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19338","citing_title":"Beyond the Current Observation: Evaluating Multimodal Large Language Models in Controllable Non-Markov Games","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11627","citing_title":"When Context Returns: Toward Robust Internalization in On-Policy Distillation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24539","citing_title":"DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29512","citing_title":"MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06556","citing_title":"Robots Need More than VLA and World Models","ref_index":166,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20744","citing_title":"Hack-Verifiable Environments: Towards Evaluating Reward Hacking at Scale","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.08827","citing_title":"A Survey of Reinforcement Learning for Large Reasoning Models","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2603.15432","citing_title":"Gym-V: A Unified Vision Environment System for Agentic Vision Research","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09965","citing_title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02751","citing_title":"Mitigating Misalignment Contagion by Steering with Implicit Traits","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08721","citing_title":"Breaking the Impasse: Dual-Scale Evolutionary Policy Training for Social Language Agents","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09965","citing_title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00226","citing_title":"Why Do LLMs Struggle in Strategic Play? Broken Links Between Observations, Beliefs, and Actions","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2601.11868","citing_title":"Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02751","citing_title":"Mitigating Misalignment Contagion by Steering with Implicit Traits","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X5K7UQNXCIZS6V7CTZJOYOHUI6","json":"https://pith.science/pith/X5K7UQNXCIZS6V7CTZJOYOHUI6.json","graph_json":"https://pith.science/api/pith-number/X5K7UQNXCIZS6V7CTZJOYOHUI6/graph.json","events_json":"https://pith.science/api/pith-number/X5K7UQNXCIZS6V7CTZJOYOHUI6/events.json","paper":"https://pith.science/paper/X5K7UQNX"},"agent_actions":{"view_html":"https://pith.science/pith/X5K7UQNXCIZS6V7CTZJOYOHUI6","download_json":"https://pith.science/pith/X5K7UQNXCIZS6V7CTZJOYOHUI6.json","view_paper":"https://pith.science/paper/X5K7UQNX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.11442&json=true","fetch_graph":"https://pith.science/api/pith-number/X5K7UQNXCIZS6V7CTZJOYOHUI6/graph.json","fetch_events":"https://pith.science/api/pith-number/X5K7UQNXCIZS6V7CTZJOYOHUI6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X5K7UQNXCIZS6V7CTZJOYOHUI6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X5K7UQNXCIZS6V7CTZJOYOHUI6/action/storage_attestation","attest_author":"https://pith.science/pith/X5K7UQNXCIZS6V7CTZJOYOHUI6/action/author_attestation","sign_citation":"https://pith.science/pith/X5K7UQNXCIZS6V7CTZJOYOHUI6/action/citation_signature","submit_replication":"https://pith.science/pith/X5K7UQNXCIZS6V7CTZJOYOHUI6/action/replication_record"}},"created_at":"2026-07-05T11:08:40.970004+00:00","updated_at":"2026-07-05T11:08:40.970004+00:00"}