{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HHX3QAVJXLW3KLP7WQ7NELWTOM","short_pith_number":"pith:HHX3QAVJ","schema_version":"1.0","canonical_sha256":"39efb802a9baedb52dffb43ed22ed37324d412f3d922547aa47b8731d97f2bfc","source":{"kind":"arxiv","id":"2507.23701","version":3},"attestation_state":"computed","paper":{"title":"TextQuests: How Good are LLMs at Text-Based Video Games?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Andy Zou, Dan Hendrycks, Long Phan, Mantas Mazeika","submitted_at":"2025-07-31T16:22:55Z","abstract_excerpt":"Evaluating AI agents within complex, interactive environments that mirror real-world challenges is critical for understanding their practical capabilities. While existing agent benchmarks effectively assess skills like tool use or performance on structured tasks, they often do not fully capture an agent's ability to operate autonomously in exploratory environments that demand sustained, self-directed reasoning over a long and growing context. To enable a more accurate assessment of AI agents in challenging exploratory environments, we introduce TextQuests, a benchmark based on the Infocom suit"},"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":"2507.23701","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-31T16:22:55Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"1ca107535ba7b38e237ace3352f7b369bccdf29a281edb81402ce5e657a7088c","abstract_canon_sha256":"9555ccf4433033a5d4aaa1b267420bb86c4c5a718066ead7254b103d010a5c5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:28.157181Z","signature_b64":"LShPm3LK9mUNiCNjnOyzMNli3olRM0GwmxQY1fP+dmiQ5t53a2sNIzP41i/eENkkVYvkLs1sdTwvnI4ijog9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39efb802a9baedb52dffb43ed22ed37324d412f3d922547aa47b8731d97f2bfc","last_reissued_at":"2026-07-05T11:53:28.156620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:28.156620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextQuests: How Good are LLMs at Text-Based Video Games?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Andy Zou, Dan Hendrycks, Long Phan, Mantas Mazeika","submitted_at":"2025-07-31T16:22:55Z","abstract_excerpt":"Evaluating AI agents within complex, interactive environments that mirror real-world challenges is critical for understanding their practical capabilities. While existing agent benchmarks effectively assess skills like tool use or performance on structured tasks, they often do not fully capture an agent's ability to operate autonomously in exploratory environments that demand sustained, self-directed reasoning over a long and growing context. To enable a more accurate assessment of AI agents in challenging exploratory environments, we introduce TextQuests, a benchmark based on the Infocom suit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.23701","kind":"arxiv","version":3},"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/2507.23701/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":"2507.23701","created_at":"2026-07-05T11:53:28.156695+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.23701v3","created_at":"2026-07-05T11:53:28.156695+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.23701","created_at":"2026-07-05T11:53:28.156695+00:00"},{"alias_kind":"pith_short_12","alias_value":"HHX3QAVJXLW3","created_at":"2026-07-05T11:53:28.156695+00:00"},{"alias_kind":"pith_short_16","alias_value":"HHX3QAVJXLW3KLP7","created_at":"2026-07-05T11:53:28.156695+00:00"},{"alias_kind":"pith_short_8","alias_value":"HHX3QAVJ","created_at":"2026-07-05T11:53:28.156695+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12429","citing_title":"Muse Spark Safety & Preparedness Report","ref_index":66,"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":133,"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":133,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11655","citing_title":"RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM","json":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM.json","graph_json":"https://pith.science/api/pith-number/HHX3QAVJXLW3KLP7WQ7NELWTOM/graph.json","events_json":"https://pith.science/api/pith-number/HHX3QAVJXLW3KLP7WQ7NELWTOM/events.json","paper":"https://pith.science/paper/HHX3QAVJ"},"agent_actions":{"view_html":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM","download_json":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM.json","view_paper":"https://pith.science/paper/HHX3QAVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.23701&json=true","fetch_graph":"https://pith.science/api/pith-number/HHX3QAVJXLW3KLP7WQ7NELWTOM/graph.json","fetch_events":"https://pith.science/api/pith-number/HHX3QAVJXLW3KLP7WQ7NELWTOM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM/action/storage_attestation","attest_author":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM/action/author_attestation","sign_citation":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM/action/citation_signature","submit_replication":"https://pith.science/pith/HHX3QAVJXLW3KLP7WQ7NELWTOM/action/replication_record"}},"created_at":"2026-07-05T11:53:28.156695+00:00","updated_at":"2026-07-05T11:53:28.156695+00:00"}