{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AX234YORT7FMA224TCLW25OBK2","short_pith_number":"pith:AX234YOR","schema_version":"1.0","canonical_sha256":"05f5be61d19fcac06b5c98976d75c156992273f366f86a254a21718ef987f862","source":{"kind":"arxiv","id":"2506.04098","version":2},"attestation_state":"computed","paper":{"title":"TextAtari: 100K Frames Game Playing with Language Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bo Jin, Chuyun Shen, Di Wu, Hongyuan Zha, Junjie Sheng, Wei Yin, Wenhao Li, Wenwu Li, Xiangfeng Wang, Yun Hua, Zixiao Huang","submitted_at":"2025-06-04T15:55:27Z","abstract_excerpt":"We present TextAtari, a benchmark for evaluating language agents on very long-horizon decision-making tasks spanning up to 100,000 steps. By translating the visual state representations of classic Atari games into rich textual descriptions, TextAtari creates a challenging test bed that bridges sequential decision-making with natural language processing. The benchmark includes nearly 100 distinct tasks with varying complexity, action spaces, and planning horizons, all rendered as text through an unsupervised representation learning framework (AtariARI). We evaluate three open-source large langu"},"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":"2506.04098","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T15:55:27Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9ef90ba072c320305394678f5b8dffd96d9bf14e3ca9ddc010ee668c84159cfd","abstract_canon_sha256":"30d8858a6e85b67222d6c640ffc1b965b3e0f0232942713cb48d9a430112d5f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:07.864901Z","signature_b64":"p4i4unhwR8AgmyeCJKPVGi522cQ9uNOzbxHnBE0uJgRD12XPtvRkeawenQ6x8iNGaSlMW4l91bqhEm7Ym+9+CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05f5be61d19fcac06b5c98976d75c156992273f366f86a254a21718ef987f862","last_reissued_at":"2026-07-05T11:19:07.864379Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:07.864379Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextAtari: 100K Frames Game Playing with Language Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bo Jin, Chuyun Shen, Di Wu, Hongyuan Zha, Junjie Sheng, Wei Yin, Wenhao Li, Wenwu Li, Xiangfeng Wang, Yun Hua, Zixiao Huang","submitted_at":"2025-06-04T15:55:27Z","abstract_excerpt":"We present TextAtari, a benchmark for evaluating language agents on very long-horizon decision-making tasks spanning up to 100,000 steps. By translating the visual state representations of classic Atari games into rich textual descriptions, TextAtari creates a challenging test bed that bridges sequential decision-making with natural language processing. The benchmark includes nearly 100 distinct tasks with varying complexity, action spaces, and planning horizons, all rendered as text through an unsupervised representation learning framework (AtariARI). We evaluate three open-source large langu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04098","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/2506.04098/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":"2506.04098","created_at":"2026-07-05T11:19:07.864448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04098v2","created_at":"2026-07-05T11:19:07.864448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04098","created_at":"2026-07-05T11:19:07.864448+00:00"},{"alias_kind":"pith_short_12","alias_value":"AX234YORT7FM","created_at":"2026-07-05T11:19:07.864448+00:00"},{"alias_kind":"pith_short_16","alias_value":"AX234YORT7FMA224","created_at":"2026-07-05T11:19:07.864448+00:00"},{"alias_kind":"pith_short_8","alias_value":"AX234YOR","created_at":"2026-07-05T11:19:07.864448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24539","citing_title":"DemoEvolve: Overcoming Sparse Feedback in Agentic Harness Evolution with Demonstrations","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18636","citing_title":"SPIKE: An Adaptive Dual Controller Framework for Cost-Efficient Long-Horizon Game Agents","ref_index":13,"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":97,"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":97,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AX234YORT7FMA224TCLW25OBK2","json":"https://pith.science/pith/AX234YORT7FMA224TCLW25OBK2.json","graph_json":"https://pith.science/api/pith-number/AX234YORT7FMA224TCLW25OBK2/graph.json","events_json":"https://pith.science/api/pith-number/AX234YORT7FMA224TCLW25OBK2/events.json","paper":"https://pith.science/paper/AX234YOR"},"agent_actions":{"view_html":"https://pith.science/pith/AX234YORT7FMA224TCLW25OBK2","download_json":"https://pith.science/pith/AX234YORT7FMA224TCLW25OBK2.json","view_paper":"https://pith.science/paper/AX234YOR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04098&json=true","fetch_graph":"https://pith.science/api/pith-number/AX234YORT7FMA224TCLW25OBK2/graph.json","fetch_events":"https://pith.science/api/pith-number/AX234YORT7FMA224TCLW25OBK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AX234YORT7FMA224TCLW25OBK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AX234YORT7FMA224TCLW25OBK2/action/storage_attestation","attest_author":"https://pith.science/pith/AX234YORT7FMA224TCLW25OBK2/action/author_attestation","sign_citation":"https://pith.science/pith/AX234YORT7FMA224TCLW25OBK2/action/citation_signature","submit_replication":"https://pith.science/pith/AX234YORT7FMA224TCLW25OBK2/action/replication_record"}},"created_at":"2026-07-05T11:19:07.864448+00:00","updated_at":"2026-07-05T11:19:07.864448+00:00"}