{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BCVGSCVJZX5P2RMLRDHJ57CNUK","short_pith_number":"pith:BCVGSCVJ","schema_version":"1.0","canonical_sha256":"08aa690aa9cdfafd458b88ce9efc4da2a9e3d2555a1e08e0345233b2389a82fb","source":{"kind":"arxiv","id":"2506.17201","version":1},"attestation_state":"computed","paper":{"title":"Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaqi Li, Junshu Tang, Longhuang Wu, Qinglin Lu, Shuai Shao, Tianbao Yu, Yuan Zhou, Zhiguo Cao, Zhiyong Xu","submitted_at":"2025-06-20T17:50:37Z","abstract_excerpt":"Recent advances in diffusion-based and controllable video generation have enabled high-quality and temporally coherent video synthesis, laying the groundwork for immersive interactive gaming experiences. However, current methods face limitations in dynamics, generality, long-term consistency, and efficiency, which limit the ability to create various gameplay videos. To address these gaps, we introduce Hunyuan-GameCraft, a novel framework for high-dynamic interactive video generation in game environments. To achieve fine-grained action control, we unify standard keyboard and mouse inputs into a"},"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":"2506.17201","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-20T17:50:37Z","cross_cats_sorted":[],"title_canon_sha256":"4e1b854dfb1a7ac537be78edeb6270a01abe4a96380e2c960b3f587e87546645","abstract_canon_sha256":"0c412d907439ef43934d570c35b7a811dc438ecae02142c11446358e80d14dc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:57.999454Z","signature_b64":"NoXCzwgEUPNpr4fikOMzahBR9/zcmbZTgvPYtNoL8dxC5Kcl2AQfjo0j4fgPz5c4jJqG3k1t/rFHBxRnfyyvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"08aa690aa9cdfafd458b88ce9efc4da2a9e3d2555a1e08e0345233b2389a82fb","last_reissued_at":"2026-07-05T11:24:57.998910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:57.998910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hunyuan-GameCraft: High-dynamic Interactive Game Video Generation with Hybrid History Condition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaqi Li, Junshu Tang, Longhuang Wu, Qinglin Lu, Shuai Shao, Tianbao Yu, Yuan Zhou, Zhiguo Cao, Zhiyong Xu","submitted_at":"2025-06-20T17:50:37Z","abstract_excerpt":"Recent advances in diffusion-based and controllable video generation have enabled high-quality and temporally coherent video synthesis, laying the groundwork for immersive interactive gaming experiences. However, current methods face limitations in dynamics, generality, long-term consistency, and efficiency, which limit the ability to create various gameplay videos. To address these gaps, we introduce Hunyuan-GameCraft, a novel framework for high-dynamic interactive video generation in game environments. To achieve fine-grained action control, we unify standard keyboard and mouse inputs into a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.17201","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/2506.17201/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":"2506.17201","created_at":"2026-07-05T11:24:57.998984+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.17201v1","created_at":"2026-07-05T11:24:57.998984+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.17201","created_at":"2026-07-05T11:24:57.998984+00:00"},{"alias_kind":"pith_short_12","alias_value":"BCVGSCVJZX5P","created_at":"2026-07-05T11:24:57.998984+00:00"},{"alias_kind":"pith_short_16","alias_value":"BCVGSCVJZX5P2RML","created_at":"2026-07-05T11:24:57.998984+00:00"},{"alias_kind":"pith_short_8","alias_value":"BCVGSCVJ","created_at":"2026-07-05T11:24:57.998984+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":32,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06291","citing_title":"AlayaWorld: Long-Horizon and Playable Video World Generation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05352","citing_title":"Multiplayer Interactive World Models with Representation Autoencoders","ref_index":239,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":220,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20545","citing_title":"Current World Models Lack a Persistent State Core","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18180","citing_title":"EgoCS-400K: An Egocentric Gameplay Dataset for World Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.16449","citing_title":"PermaVid: Consistent Video Generation Across Edits via Disentangled Context Memory","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09507","citing_title":"Prisma-World: Camera-Controllable Multi-Agent Video World Model","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07967","citing_title":"DisCo: World Models with Discrete Camera Motion Control","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07508","citing_title":"Streaming Video Generation with Streaming Force Control","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01222","citing_title":"Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02575","citing_title":"From Zero to Hero: Training-Free Custom Concept Spawning in World Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25874","citing_title":"WBench: A Comprehensive Multi-turn Benchmark for Interactive Video World Model Evaluation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28026","citing_title":"EMOSH: Expressive Motion and Shape Disentanglement for Human Animation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30855","citing_title":"Robust Dreamer: Deviation-Aware Latent Gaussian Memory for Action-Controlled AR Video Generation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31336","citing_title":"DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22718","citing_title":"WorldKV: Efficient World Memory with World Retrieval and Compression","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18803","citing_title":"PROWL: Prioritized Regret-Driven Optimization for World Model Learning","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2508.13009","citing_title":"Matrix-game 2.0: An open-source real-time and streaming interactive world model","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2510.02283","citing_title":"Self-Forcing++: Towards Minute-Scale High-Quality Video Generation","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14614","citing_title":"WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modeling","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":231,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BCVGSCVJZX5P2RMLRDHJ57CNUK","json":"https://pith.science/pith/BCVGSCVJZX5P2RMLRDHJ57CNUK.json","graph_json":"https://pith.science/api/pith-number/BCVGSCVJZX5P2RMLRDHJ57CNUK/graph.json","events_json":"https://pith.science/api/pith-number/BCVGSCVJZX5P2RMLRDHJ57CNUK/events.json","paper":"https://pith.science/paper/BCVGSCVJ"},"agent_actions":{"view_html":"https://pith.science/pith/BCVGSCVJZX5P2RMLRDHJ57CNUK","download_json":"https://pith.science/pith/BCVGSCVJZX5P2RMLRDHJ57CNUK.json","view_paper":"https://pith.science/paper/BCVGSCVJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.17201&json=true","fetch_graph":"https://pith.science/api/pith-number/BCVGSCVJZX5P2RMLRDHJ57CNUK/graph.json","fetch_events":"https://pith.science/api/pith-number/BCVGSCVJZX5P2RMLRDHJ57CNUK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BCVGSCVJZX5P2RMLRDHJ57CNUK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BCVGSCVJZX5P2RMLRDHJ57CNUK/action/storage_attestation","attest_author":"https://pith.science/pith/BCVGSCVJZX5P2RMLRDHJ57CNUK/action/author_attestation","sign_citation":"https://pith.science/pith/BCVGSCVJZX5P2RMLRDHJ57CNUK/action/citation_signature","submit_replication":"https://pith.science/pith/BCVGSCVJZX5P2RMLRDHJ57CNUK/action/replication_record"}},"created_at":"2026-07-05T11:24:57.998984+00:00","updated_at":"2026-07-05T11:24:57.998984+00:00"}