{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GOMUL7EQPJFDKCNDFEUITDG7LJ","short_pith_number":"pith:GOMUL7EQ","schema_version":"1.0","canonical_sha256":"339945fc907a4a3509a32928898cdf5a5d0f46e78b75aaaf3d9a952265e6b3bd","source":{"kind":"arxiv","id":"2512.14614","version":1},"attestation_state":"computed","paper":{"title":"WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"WorldPlay generates long-horizon 720p video at 24 FPS while preserving geometric consistency through rebuilt context memory in a streaming diffusion model.","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chunchao Guo, Haiyu Zhang, Haoyuan Wang, Junta Wu, Jun Zhang, Tengfei Wang, Wenqiang Sun, Yunhong Wang, Zehan Wang, Zhenwei Wang","submitted_at":"2025-12-16T17:22:46Z","abstract_excerpt":"This paper presents WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods. WorldPlay draws power from three key innovations. 1) We use a Dual Action Representation to enable robust action control in response to the user's keyboard and mouse inputs. 2) To enforce long-term consistency, our Reconstituted Context Memory dynamically rebuilds context from past frames and uses temporal reframing to keep geometrically important but long-past fram"},"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":"2512.14614","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-16T17:22:46Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"7adf4431b585b8d603015636746a93281a3d2c5e75d6cbecbfa51c75c59941fb","abstract_canon_sha256":"5040a568926fb7e3eedae7b843a27b989f8e779e7d4748ee3509104442bf428f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:52.349707Z","signature_b64":"IjSbMcq8j8DxYX9lRWhur8T6Fbo75CazlfwWD81I6BR96JIcOX8j0EFilXL/SWEXU2ZrfKWXIneAt27BZkXXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"339945fc907a4a3509a32928898cdf5a5d0f46e78b75aaaf3d9a952265e6b3bd","last_reissued_at":"2026-05-17T23:38:52.349240Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:52.349240Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"WorldPlay generates long-horizon 720p video at 24 FPS while preserving geometric consistency through rebuilt context memory in a streaming diffusion model.","cross_cats":["cs.GR"],"primary_cat":"cs.CV","authors_text":"Chunchao Guo, Haiyu Zhang, Haoyuan Wang, Junta Wu, Jun Zhang, Tengfei Wang, Wenqiang Sun, Yunhong Wang, Zehan Wang, Zhenwei Wang","submitted_at":"2025-12-16T17:22:46Z","abstract_excerpt":"This paper presents WorldPlay, a streaming video diffusion model that enables real-time, interactive world modeling with long-term geometric consistency, resolving the trade-off between speed and memory that limits current methods. WorldPlay draws power from three key innovations. 1) We use a Dual Action Representation to enable robust action control in response to the user's keyboard and mouse inputs. 2) To enforce long-term consistency, our Reconstituted Context Memory dynamically rebuilds context from past frames and uses temporal reframing to keep geometrically important but long-past fram"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"WorldPlay generates long-horizon streaming 720p video at 24 FPS with superior consistency, comparing favorably with existing techniques and showing strong generalization across diverse scenes.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The Reconstituted Context Memory and Context Forcing methods actually preserve long-range geometric information and prevent error drift in practice without introducing new artifacts or requiring impractical memory.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"WorldPlay uses dual action representation, reconstituted context memory, and context forcing distillation to produce consistent 720p streaming video at 24 FPS for interactive world modeling.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"WorldPlay generates long-horizon 720p video at 24 FPS while preserving geometric consistency through rebuilt context memory in a streaming diffusion model.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fc4db54fe6af1dfc4cd1ab8e55b4ff3e745b14a4fe84bcb859d372b29d366ad1"},"source":{"id":"2512.14614","kind":"arxiv","version":1},"verdict":{"id":"4c14e863-3cab-4354-b7d5-ec17a064a9ee","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T14:25:17.859701Z","strongest_claim":"WorldPlay generates long-horizon streaming 720p video at 24 FPS with superior consistency, comparing favorably with existing techniques and showing strong generalization across diverse scenes.","one_line_summary":"WorldPlay uses dual action representation, reconstituted context memory, and context forcing distillation to produce consistent 720p streaming video at 24 FPS for interactive world modeling.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The Reconstituted Context Memory and Context Forcing methods actually preserve long-range geometric information and prevent error drift in practice without introducing new artifacts or requiring impractical memory.","pith_extraction_headline":"WorldPlay generates long-horizon 720p video at 24 FPS while preserving geometric consistency through rebuilt context memory in a streaming diffusion model."},"references":{"count":81,"sample":[{"doi":"","year":2024,"title":"Diffusion for world modeling: Visual details matter in atari","work_id":"d9676607-838e-4c01-a91d-fdd83d1c181f","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Ac3d: Analyzing and improving 3d camera control in video diffusion trans- formers","work_id":"04724e59-193c-4821-ae21-21ebd6c9e842","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Navigation world models","work_id":"13a8b5e7-df85-4cad-9645-8e684faae06e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Uni3c: Unifying precisely 3d-enhanced camera and hu- man motion controls for video generation.arXiv preprint arXiv:2504.14899, 2025","work_id":"c4cc0875-d298-400d-a5cd-f9de3bb813d1","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Gamegen-x: Interactive open-world game video generation","work_id":"5f3b923c-3fdc-468a-8951-94c4ff7b1e29","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":81,"snapshot_sha256":"da74a3586c3b9bd6d657fe9bfe6721d8e959bb6a50d90f19a7eac5676244b3b0","internal_anchors":17},"formal_canon":{"evidence_count":3,"snapshot_sha256":"d6ec8d5fc53940cdf3d0b7f087d734775aaed757aa639cb278e82ad6066e6ebf"},"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":"2512.14614","created_at":"2026-05-17T23:38:52.349322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.14614v1","created_at":"2026-05-17T23:38:52.349322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.14614","created_at":"2026-05-17T23:38:52.349322+00:00"},{"alias_kind":"pith_short_12","alias_value":"GOMUL7EQPJFD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"GOMUL7EQPJFDKCND","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"GOMUL7EQ","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":32,"internal_anchor_count":32,"sample":[{"citing_arxiv_id":"2605.11596","citing_title":"HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23345","citing_title":"SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23458","citing_title":"One-Forcing: Towards Stable One-Step Autoregressive Video Generation","ref_index":61,"is_internal_anchor":true},{"citing_arxiv_id":"2602.02214","citing_title":"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22718","citing_title":"WorldKV: Efficient World Memory with World Retrieval and Compression","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2602.02214","citing_title":"Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21072","citing_title":"Q-ARVD: Quantizing Autoregressive Video Diffusion Models","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08567","citing_title":"ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15824","citing_title":"FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18601","citing_title":"Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2602.06949","citing_title":"DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos","ref_index":86,"is_internal_anchor":true},{"citing_arxiv_id":"2601.20540","citing_title":"Advancing Open-source World Models","ref_index":68,"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":6,"is_internal_anchor":true},{"citing_arxiv_id":"2603.11911","citing_title":"InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15182","citing_title":"Warp-as-History: Generalizable Camera-Controlled Video Generation from One Training Video","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14487","citing_title":"Head Forcing: Long Autoregressive Video Generation via Head Heterogeneity","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":234,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02799","citing_title":"UNICA: A Unified Neural Framework for Controllable 3D Avatars","ref_index":60,"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":155,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11596","citing_title":"HorizonDrive: Self-Corrective Autoregressive World Model for Long-horizon Driving Simulation","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08567","citing_title":"ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Models","ref_index":27,"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":155,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00078","citing_title":"Being-H0.7: A Latent World-Action Model from Egocentric Videos","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21686","citing_title":"WorldMark: A Unified Benchmark Suite for Interactive Video World Models","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08995","citing_title":"Matrix-Game 3.0: Real-Time and Streaming Interactive World Model with Long-Horizon Memory","ref_index":32,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GOMUL7EQPJFDKCNDFEUITDG7LJ","json":"https://pith.science/pith/GOMUL7EQPJFDKCNDFEUITDG7LJ.json","graph_json":"https://pith.science/api/pith-number/GOMUL7EQPJFDKCNDFEUITDG7LJ/graph.json","events_json":"https://pith.science/api/pith-number/GOMUL7EQPJFDKCNDFEUITDG7LJ/events.json","paper":"https://pith.science/paper/GOMUL7EQ"},"agent_actions":{"view_html":"https://pith.science/pith/GOMUL7EQPJFDKCNDFEUITDG7LJ","download_json":"https://pith.science/pith/GOMUL7EQPJFDKCNDFEUITDG7LJ.json","view_paper":"https://pith.science/paper/GOMUL7EQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.14614&json=true","fetch_graph":"https://pith.science/api/pith-number/GOMUL7EQPJFDKCNDFEUITDG7LJ/graph.json","fetch_events":"https://pith.science/api/pith-number/GOMUL7EQPJFDKCNDFEUITDG7LJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GOMUL7EQPJFDKCNDFEUITDG7LJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GOMUL7EQPJFDKCNDFEUITDG7LJ/action/storage_attestation","attest_author":"https://pith.science/pith/GOMUL7EQPJFDKCNDFEUITDG7LJ/action/author_attestation","sign_citation":"https://pith.science/pith/GOMUL7EQPJFDKCNDFEUITDG7LJ/action/citation_signature","submit_replication":"https://pith.science/pith/GOMUL7EQPJFDKCNDFEUITDG7LJ/action/replication_record"}},"created_at":"2026-05-17T23:38:52.349322+00:00","updated_at":"2026-05-17T23:38:52.349322+00:00"}