{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6S3VVO5PISCD6XU4VXMGZT3EOY","short_pith_number":"pith:6S3VVO5P","schema_version":"1.0","canonical_sha256":"f4b75abbaf44843f5e9cadd86ccf64760be7e64a487a096617dbf75f1c215ea0","source":{"kind":"arxiv","id":"2507.08892","version":1},"attestation_state":"computed","paper":{"title":"Multi-Actor Generative Artificial Intelligence as a Game Engine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Alexander Sasha Vezhnevets, Davide Paglieri, Jayd Matyas, Joel Z. Leibo, Logan Cross, Minsuk Chang, Simon Osindero, William A. Cunningham, William S. Isaac","submitted_at":"2025-07-10T22:31:09Z","abstract_excerpt":"Generative AI can be used in multi-actor environments with purposes ranging from social science modeling to interactive narrative and AI evaluation. Supporting this diversity of use cases -- which we classify as Simulationist, Dramatist, and Evaluationist -- demands a flexible scenario definition framework. We argue here that a good approach is to take inspiration from tabletop role-playing games (TTRPGs), where a Game Master (GM) is responsible for the environment and generates all parts of the story not directly determined by the voluntary actions of player characters. We argue that the Enti"},"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":"2507.08892","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-10T22:31:09Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"951f23ea923838926576a28cb31778aa0e5495813b07a1d0ee81163938e1a28e","abstract_canon_sha256":"badb54dc27cd5ebd1a1838ae68863dc46f01c2adc2e630a5c98962ada951695f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:00.172556Z","signature_b64":"1BtPiXJhNq2/IVAipf/qLKjbwDsDHYL2qiO973XCmVZGHjx8sCSOt2M3M8MjT1RfDNcDIiWyMcBKkLwLW4RzAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4b75abbaf44843f5e9cadd86ccf64760be7e64a487a096617dbf75f1c215ea0","last_reissued_at":"2026-07-05T11:36:00.172006Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:00.172006Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Actor Generative Artificial Intelligence as a Game Engine","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Alexander Sasha Vezhnevets, Davide Paglieri, Jayd Matyas, Joel Z. Leibo, Logan Cross, Minsuk Chang, Simon Osindero, William A. Cunningham, William S. Isaac","submitted_at":"2025-07-10T22:31:09Z","abstract_excerpt":"Generative AI can be used in multi-actor environments with purposes ranging from social science modeling to interactive narrative and AI evaluation. Supporting this diversity of use cases -- which we classify as Simulationist, Dramatist, and Evaluationist -- demands a flexible scenario definition framework. We argue here that a good approach is to take inspiration from tabletop role-playing games (TTRPGs), where a Game Master (GM) is responsible for the environment and generates all parts of the story not directly determined by the voluntary actions of player characters. We argue that the Enti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.08892","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/2507.08892/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":"2507.08892","created_at":"2026-07-05T11:36:00.172066+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.08892v1","created_at":"2026-07-05T11:36:00.172066+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.08892","created_at":"2026-07-05T11:36:00.172066+00:00"},{"alias_kind":"pith_short_12","alias_value":"6S3VVO5PISCD","created_at":"2026-07-05T11:36:00.172066+00:00"},{"alias_kind":"pith_short_16","alias_value":"6S3VVO5PISCD6XU4","created_at":"2026-07-05T11:36:00.172066+00:00"},{"alias_kind":"pith_short_8","alias_value":"6S3VVO5P","created_at":"2026-07-05T11:36:00.172066+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30258","citing_title":"EASE Configuration Facilitates A Reproducible Science of LLM Social Simulations","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19791","citing_title":"Stabilising Generative Models of Attitude Change","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18394","citing_title":"OpenGame: Open Agentic Coding for Games","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6S3VVO5PISCD6XU4VXMGZT3EOY","json":"https://pith.science/pith/6S3VVO5PISCD6XU4VXMGZT3EOY.json","graph_json":"https://pith.science/api/pith-number/6S3VVO5PISCD6XU4VXMGZT3EOY/graph.json","events_json":"https://pith.science/api/pith-number/6S3VVO5PISCD6XU4VXMGZT3EOY/events.json","paper":"https://pith.science/paper/6S3VVO5P"},"agent_actions":{"view_html":"https://pith.science/pith/6S3VVO5PISCD6XU4VXMGZT3EOY","download_json":"https://pith.science/pith/6S3VVO5PISCD6XU4VXMGZT3EOY.json","view_paper":"https://pith.science/paper/6S3VVO5P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.08892&json=true","fetch_graph":"https://pith.science/api/pith-number/6S3VVO5PISCD6XU4VXMGZT3EOY/graph.json","fetch_events":"https://pith.science/api/pith-number/6S3VVO5PISCD6XU4VXMGZT3EOY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6S3VVO5PISCD6XU4VXMGZT3EOY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6S3VVO5PISCD6XU4VXMGZT3EOY/action/storage_attestation","attest_author":"https://pith.science/pith/6S3VVO5PISCD6XU4VXMGZT3EOY/action/author_attestation","sign_citation":"https://pith.science/pith/6S3VVO5PISCD6XU4VXMGZT3EOY/action/citation_signature","submit_replication":"https://pith.science/pith/6S3VVO5PISCD6XU4VXMGZT3EOY/action/replication_record"}},"created_at":"2026-07-05T11:36:00.172066+00:00","updated_at":"2026-07-05T11:36:00.172066+00:00"}