{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:6S6C7K7PBELJLA2HARGGCESWZZ","short_pith_number":"pith:6S6C7K7P","schema_version":"1.0","canonical_sha256":"f4bc2fabef0916958347044c611256ce498018253eeb2ac57e4e76e98e77b8ea","source":{"kind":"arxiv","id":"1806.11532","version":2},"attestation_state":"computed","paper":{"title":"TextWorld: A Learning Environment for Text-based Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Trischler, \\'Akos K\\'ad\\'ar, Ben Kybartas, Emery Fine, James Moore, Layla El Asri, Mahmoud Adada, Marc-Alexandre C\\^ot\\'e, Matthew Hausknecht, Ruo Yu Tao, Tavian Barnes, Wendy Tay, Xingdi Yuan","submitted_at":"2018-06-29T16:56:07Z","abstract_excerpt":"We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like state tracking and reward assignment. It comes with a curated list of games whose features and challenges we have analyzed. More significantly, it enables users to handcraft or automatically generate new games. Its generative mechanisms give precise control over the difficulty, scope, and language of constructed games, and can be used to relax challenges inher"},"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":"1806.11532","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-06-29T16:56:07Z","cross_cats_sorted":["cs.CL","stat.ML"],"title_canon_sha256":"cba93307078baf0cf53b7c7adfaea7283919e3e1a092b2fa741a8049cfc34d94","abstract_canon_sha256":"05d77e985e0cbb633bfcd58663a7ef185e391e6482c53df89d9104099c3ccc11"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:17:47.157768Z","signature_b64":"P36MeDS+PPJ6LWj2BXnuNEnWScAvREKvHRghThOKCJv0sMhxiPviPuDih3+VWGnwg6Kdj0Ia9AzW8qv+nBl7AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4bc2fabef0916958347044c611256ce498018253eeb2ac57e4e76e98e77b8ea","last_reissued_at":"2026-07-05T00:17:47.157280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:17:47.157280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TextWorld: A Learning Environment for Text-based Games","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","stat.ML"],"primary_cat":"cs.LG","authors_text":"Adam Trischler, \\'Akos K\\'ad\\'ar, Ben Kybartas, Emery Fine, James Moore, Layla El Asri, Mahmoud Adada, Marc-Alexandre C\\^ot\\'e, Matthew Hausknecht, Ruo Yu Tao, Tavian Barnes, Wendy Tay, Xingdi Yuan","submitted_at":"2018-06-29T16:56:07Z","abstract_excerpt":"We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like state tracking and reward assignment. It comes with a curated list of games whose features and challenges we have analyzed. More significantly, it enables users to handcraft or automatically generate new games. Its generative mechanisms give precise control over the difficulty, scope, and language of constructed games, and can be used to relax challenges inher"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.11532","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/1806.11532/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":"1806.11532","created_at":"2026-07-05T00:17:47.157335+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.11532v2","created_at":"2026-07-05T00:17:47.157335+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.11532","created_at":"2026-07-05T00:17:47.157335+00:00"},{"alias_kind":"pith_short_12","alias_value":"6S6C7K7PBELJ","created_at":"2026-07-05T00:17:47.157335+00:00"},{"alias_kind":"pith_short_16","alias_value":"6S6C7K7PBELJLA2H","created_at":"2026-07-05T00:17:47.157335+00:00"},{"alias_kind":"pith_short_8","alias_value":"6S6C7K7P","created_at":"2026-07-05T00:17:47.157335+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19911","citing_title":"Multi-Agent Transactive Memory","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24020","citing_title":"Machine Intelligence that Understands Visual and Linguistic Information and Interacts with Humans and Environments","ref_index":157,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17637","citing_title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"1907.09273","citing_title":"Why Build an Assistant in Minecraft?","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17637","citing_title":"WebGameBench: Requirement-to-Application Evaluation for Coding Agents via Browser-Native Games","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"1909.01066","citing_title":"Language Models as Knowledge Bases?","ref_index":152,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27043","citing_title":"CL-bench Life: Can Language Models Learn from Real-Life Context?","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15529","citing_title":"LACE: Lattice Attention for Cross-thread Exploration","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11611","citing_title":"Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15529","citing_title":"LACE: Lattice Attention for Cross-thread Exploration","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15529","citing_title":"LACE: Lattice Attention for Cross-thread Exploration","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6S6C7K7PBELJLA2HARGGCESWZZ","json":"https://pith.science/pith/6S6C7K7PBELJLA2HARGGCESWZZ.json","graph_json":"https://pith.science/api/pith-number/6S6C7K7PBELJLA2HARGGCESWZZ/graph.json","events_json":"https://pith.science/api/pith-number/6S6C7K7PBELJLA2HARGGCESWZZ/events.json","paper":"https://pith.science/paper/6S6C7K7P"},"agent_actions":{"view_html":"https://pith.science/pith/6S6C7K7PBELJLA2HARGGCESWZZ","download_json":"https://pith.science/pith/6S6C7K7PBELJLA2HARGGCESWZZ.json","view_paper":"https://pith.science/paper/6S6C7K7P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.11532&json=true","fetch_graph":"https://pith.science/api/pith-number/6S6C7K7PBELJLA2HARGGCESWZZ/graph.json","fetch_events":"https://pith.science/api/pith-number/6S6C7K7PBELJLA2HARGGCESWZZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6S6C7K7PBELJLA2HARGGCESWZZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6S6C7K7PBELJLA2HARGGCESWZZ/action/storage_attestation","attest_author":"https://pith.science/pith/6S6C7K7PBELJLA2HARGGCESWZZ/action/author_attestation","sign_citation":"https://pith.science/pith/6S6C7K7PBELJLA2HARGGCESWZZ/action/citation_signature","submit_replication":"https://pith.science/pith/6S6C7K7PBELJLA2HARGGCESWZZ/action/replication_record"}},"created_at":"2026-07-05T00:17:47.157335+00:00","updated_at":"2026-07-05T00:17:47.157335+00:00"}