{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:74FJ7C3E2CLCLXHA7C56WLZEIL","short_pith_number":"pith:74FJ7C3E","schema_version":"1.0","canonical_sha256":"ff0a9f8b64d09625dce0f8bbeb2f2442c7a77e0c03abe98da5ff545c49c07efb","source":{"kind":"arxiv","id":"2308.01872","version":1},"attestation_state":"computed","paper":{"title":"Thespian: Multi-Character Text Role-Playing Game Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Christopher Cui, Mark Riedl, Xiangyu Peng","submitted_at":"2023-08-03T16:53:53Z","abstract_excerpt":"Text-adventure games and text role-playing games are grand challenges for reinforcement learning game playing agents. Text role-playing games are open-ended environments where an agent must faithfully play a particular character. We consider the distinction between characters and actors, where an actor agent has the ability to play multiple characters. We present a framework we call a thespian agent that can learn to emulate multiple characters along with a soft prompt that can be used to direct it as to which character to play at any time. We further describe an attention mechanism that allow"},"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":"2308.01872","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-08-03T16:53:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"43ca217844d72488ba51733d147f22aa04a2401dc0d5ac11a380fceeae79e280","abstract_canon_sha256":"8ddb8fdde3c32a91b3028789b9ab49fc9ac7fc763dbdde6d08b27c80ef94ff6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:37:24.508966Z","signature_b64":"GHFyWCLXwBSQhS17Zv+6diwrVh119PeDGkHEQfvx/lhgGXd+CD4KFANUZVGSOs5Y6YaBJyVa3dYt/v89wMDQAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff0a9f8b64d09625dce0f8bbeb2f2442c7a77e0c03abe98da5ff545c49c07efb","last_reissued_at":"2026-07-05T06:37:24.508383Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:37:24.508383Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Thespian: Multi-Character Text Role-Playing Game Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Christopher Cui, Mark Riedl, Xiangyu Peng","submitted_at":"2023-08-03T16:53:53Z","abstract_excerpt":"Text-adventure games and text role-playing games are grand challenges for reinforcement learning game playing agents. Text role-playing games are open-ended environments where an agent must faithfully play a particular character. We consider the distinction between characters and actors, where an actor agent has the ability to play multiple characters. We present a framework we call a thespian agent that can learn to emulate multiple characters along with a soft prompt that can be used to direct it as to which character to play at any time. We further describe an attention mechanism that allow"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.01872","kind":"arxiv","version":1},"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/2308.01872/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":"2308.01872","created_at":"2026-07-05T06:37:24.508469+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.01872v1","created_at":"2026-07-05T06:37:24.508469+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.01872","created_at":"2026-07-05T06:37:24.508469+00:00"},{"alias_kind":"pith_short_12","alias_value":"74FJ7C3E2CLC","created_at":"2026-07-05T06:37:24.508469+00:00"},{"alias_kind":"pith_short_16","alias_value":"74FJ7C3E2CLCLXHA","created_at":"2026-07-05T06:37:24.508469+00:00"},{"alias_kind":"pith_short_8","alias_value":"74FJ7C3E","created_at":"2026-07-05T06:37:24.508469+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27025","citing_title":"Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/74FJ7C3E2CLCLXHA7C56WLZEIL","json":"https://pith.science/pith/74FJ7C3E2CLCLXHA7C56WLZEIL.json","graph_json":"https://pith.science/api/pith-number/74FJ7C3E2CLCLXHA7C56WLZEIL/graph.json","events_json":"https://pith.science/api/pith-number/74FJ7C3E2CLCLXHA7C56WLZEIL/events.json","paper":"https://pith.science/paper/74FJ7C3E"},"agent_actions":{"view_html":"https://pith.science/pith/74FJ7C3E2CLCLXHA7C56WLZEIL","download_json":"https://pith.science/pith/74FJ7C3E2CLCLXHA7C56WLZEIL.json","view_paper":"https://pith.science/paper/74FJ7C3E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.01872&json=true","fetch_graph":"https://pith.science/api/pith-number/74FJ7C3E2CLCLXHA7C56WLZEIL/graph.json","fetch_events":"https://pith.science/api/pith-number/74FJ7C3E2CLCLXHA7C56WLZEIL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/74FJ7C3E2CLCLXHA7C56WLZEIL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/74FJ7C3E2CLCLXHA7C56WLZEIL/action/storage_attestation","attest_author":"https://pith.science/pith/74FJ7C3E2CLCLXHA7C56WLZEIL/action/author_attestation","sign_citation":"https://pith.science/pith/74FJ7C3E2CLCLXHA7C56WLZEIL/action/citation_signature","submit_replication":"https://pith.science/pith/74FJ7C3E2CLCLXHA7C56WLZEIL/action/replication_record"}},"created_at":"2026-07-05T06:37:24.508469+00:00","updated_at":"2026-07-05T06:37:24.508469+00:00"}