{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KSFDUBSLY7LMVAHJXMQ3HSFJKT","short_pith_number":"pith:KSFDUBSL","schema_version":"1.0","canonical_sha256":"548a3a064bc7d6ca80e9bb21b3c8a954fdfd5eb51deb516a8bcd3a522f25ae72","source":{"kind":"arxiv","id":"2408.14837","version":2},"attestation_state":"computed","paper":{"title":"Diffusion Models Are Real-Time Game Engines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A diffusion model trained on gameplay can serve as a complete real-time game engine for complex environments like DOOM.","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Dani Valevski, Moab Arar, Shlomi Fruchter, Yaniv Leviathan","submitted_at":"2024-08-27T07:46:07Z","abstract_excerpt":"We present GameNGen, the first game engine powered entirely by a neural model that also enables real-time interaction with a complex environment over long trajectories at high quality. When trained on the classic game DOOM, GameNGen extracts gameplay and uses it to generate a playable environment that can interactively simulate new trajectories. GameNGen runs at 20 frames per second on a single TPU and remains stable over extended multi-minute play sessions. Next frame prediction achieves a PSNR of 29.4, comparable to lossy JPEG compression. Human raters are only slightly better than random ch"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2408.14837","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-27T07:46:07Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"dc4be22f667ff59b3227ecc3e5353ce7a523c23442c7a06f6566d8fedad52ef8","abstract_canon_sha256":"949dd90a855138b0a820eaeaa2a2d9335f808b677fc4a2d6f93d92d21b1ade77"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:47.942608Z","signature_b64":"vINJRcyyXfbOj4nzLAYDWYeKAZimswQMmqYkanJFAUvvKfK0tm9LCWDIce6iOHuWpIuS006/L3vvtrkUXE39Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"548a3a064bc7d6ca80e9bb21b3c8a954fdfd5eb51deb516a8bcd3a522f25ae72","last_reissued_at":"2026-05-17T23:38:47.941907Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:47.941907Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Models Are Real-Time Game Engines","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A diffusion model trained on gameplay can serve as a complete real-time game engine for complex environments like DOOM.","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.LG","authors_text":"Dani Valevski, Moab Arar, Shlomi Fruchter, Yaniv Leviathan","submitted_at":"2024-08-27T07:46:07Z","abstract_excerpt":"We present GameNGen, the first game engine powered entirely by a neural model that also enables real-time interaction with a complex environment over long trajectories at high quality. When trained on the classic game DOOM, GameNGen extracts gameplay and uses it to generate a playable environment that can interactively simulate new trajectories. GameNGen runs at 20 frames per second on a single TPU and remains stable over extended multi-minute play sessions. Next frame prediction achieves a PSNR of 29.4, comparable to lossy JPEG compression. Human raters are only slightly better than random ch"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"GameNGen is the first game engine powered entirely by a neural model that enables real-time interaction with a complex environment over long trajectories at high quality, running at 20 frames per second on a single TPU while remaining stable over extended multi-minute play sessions.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That conditioning augmentations and decoder fine-tuning will continue to prevent error accumulation and visual drift during extended auto-regressive rollouts beyond the tested multi-minute sessions, without additional mechanisms for long-term memory or consistency.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A diffusion model trained on gameplay can serve as a complete real-time game engine for complex environments like DOOM.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e1c4e5388cd14c16d131c71be4683ad24d218003939845bddcb1b7dcb68b3678"},"source":{"id":"2408.14837","kind":"arxiv","version":2},"verdict":{"id":"00e83f96-7c0a-47d6-a5cb-1667429aeae4","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T12:01:01.639050Z","strongest_claim":"GameNGen is the first game engine powered entirely by a neural model that enables real-time interaction with a complex environment over long trajectories at high quality, running at 20 frames per second on a single TPU while remaining stable over extended multi-minute play sessions.","one_line_summary":"A diffusion model trained on DOOM play sessions generates stable real-time interactive game frames at 20 FPS with quality near lossy JPEG.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That conditioning augmentations and decoder fine-tuning will continue to prevent error accumulation and visual drift during extended auto-regressive rollouts beyond the tested multi-minute sessions, without additional mechanisms for long-term memory or consistency.","pith_extraction_headline":"A diffusion model trained on gameplay can serve as a complete real-time game engine for complex environments like DOOM."},"references":{"count":88,"sample":[{"doi":"","year":null,"title":"Advances in Neural Information Processing Systems , volume=","work_id":"bd768442-f658-45cd-8a6d-dec95c5eaa2b","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Proceedings of the IEEE/CVF conference on computer vision and pattern recognition , pages=","work_id":"575b0292-9b85-4da9-a1f5-5a4768b0f754","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Scaling Autoregressive Models for Content-Rich Text-to-Image Generation","work_id":"0a105815-ff2e-43ce-8566-966cdcae1af4","ref_index":3,"cited_arxiv_id":"2206.10789","is_internal_anchor":true},{"doi":"","year":2022,"title":"The Tenth International Conference on Learning Representations,","work_id":"7ec62083-2e3c-4a9c-84bb-f15142ac7b26","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Fast high-resolution image synthesis with latent adversarial diffusion distillation","work_id":"94329895-d192-430f-a517-12f01ae2de5e","ref_index":8,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":88,"snapshot_sha256":"1528e491aceefefa9033b41e73fe427d7f05de460717ca050244942f9e38caee","internal_anchors":15},"formal_canon":{"evidence_count":3,"snapshot_sha256":"20add8aa95c3bac462ed980a09db219a776b3c636e9b714ac352a763baf0ceca"},"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":"2408.14837","created_at":"2026-05-17T23:38:47.942024+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14837v2","created_at":"2026-05-17T23:38:47.942024+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14837","created_at":"2026-05-17T23:38:47.942024+00:00"},{"alias_kind":"pith_short_12","alias_value":"KSFDUBSLY7LM","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"KSFDUBSLY7LMVAHJ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"KSFDUBSL","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":28,"internal_anchor_count":28,"sample":[{"citing_arxiv_id":"2605.23345","citing_title":"SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2502.11537","citing_title":"Simulus: Combining Improvements in Sample-Efficient World Model Agents","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18803","citing_title":"PROWL: Prioritized Regret-Driven Optimization for World Model Learning","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15256","citing_title":"ReactiveGWM: Steering NPC in Reactive Game World Models","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2505.21996","citing_title":"VRAG: Learning World Models for Interactive Video Generation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2507.07982","citing_title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2508.13009","citing_title":"Matrix-game 2.0: An open-source real-time and streaming interactive world model","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2503.19325","citing_title":"Long-Context Autoregressive Video Modeling with Next-Frame Prediction","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2505.23884","citing_title":"Test-Time Training Done Right","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2509.25161","citing_title":"Rolling Forcing: Autoregressive Long Video Diffusion in Real Time","ref_index":94,"is_internal_anchor":true},{"citing_arxiv_id":"2601.22149","citing_title":"DynaWeb: Model-Based Reinforcement Learning of Web Agents","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2601.22149","citing_title":"DynaWeb: Model-Based Reinforcement Learning of Web Agents","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2601.20540","citing_title":"Advancing Open-source World Models","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15178","citing_title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2603.21210","citing_title":"Pretrained Video Models as Differentiable Physics Simulators for Urban Wind Flows","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2509.24527","citing_title":"Training Agents Inside of Scalable World Models","ref_index":71,"is_internal_anchor":true},{"citing_arxiv_id":"2503.00200","citing_title":"Unified Video Action Model","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09965","citing_title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","ref_index":167,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":299,"is_internal_anchor":true},{"citing_arxiv_id":"2604.28185","citing_title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","ref_index":81,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09965","citing_title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","ref_index":167,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21686","citing_title":"WorldMark: A Unified Benchmark Suite for Interactive Video World Models","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01896","citing_title":"Divide and Conquer: Decoupled Representation Alignment for Multimodal World Models","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06882","citing_title":"Telecom World Models: Unifying Digital Twins, Foundation Models, and Predictive Planning for 6G","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2501.03575","citing_title":"Cosmos World Foundation Model Platform for Physical AI","ref_index":198,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KSFDUBSLY7LMVAHJXMQ3HSFJKT","json":"https://pith.science/pith/KSFDUBSLY7LMVAHJXMQ3HSFJKT.json","graph_json":"https://pith.science/api/pith-number/KSFDUBSLY7LMVAHJXMQ3HSFJKT/graph.json","events_json":"https://pith.science/api/pith-number/KSFDUBSLY7LMVAHJXMQ3HSFJKT/events.json","paper":"https://pith.science/paper/KSFDUBSL"},"agent_actions":{"view_html":"https://pith.science/pith/KSFDUBSLY7LMVAHJXMQ3HSFJKT","download_json":"https://pith.science/pith/KSFDUBSLY7LMVAHJXMQ3HSFJKT.json","view_paper":"https://pith.science/paper/KSFDUBSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14837&json=true","fetch_graph":"https://pith.science/api/pith-number/KSFDUBSLY7LMVAHJXMQ3HSFJKT/graph.json","fetch_events":"https://pith.science/api/pith-number/KSFDUBSLY7LMVAHJXMQ3HSFJKT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KSFDUBSLY7LMVAHJXMQ3HSFJKT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KSFDUBSLY7LMVAHJXMQ3HSFJKT/action/storage_attestation","attest_author":"https://pith.science/pith/KSFDUBSLY7LMVAHJXMQ3HSFJKT/action/author_attestation","sign_citation":"https://pith.science/pith/KSFDUBSLY7LMVAHJXMQ3HSFJKT/action/citation_signature","submit_replication":"https://pith.science/pith/KSFDUBSLY7LMVAHJXMQ3HSFJKT/action/replication_record"}},"created_at":"2026-05-17T23:38:47.942024+00:00","updated_at":"2026-05-17T23:38:47.942024+00:00"}