{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V2T64JEV67DDPAS3HGRT2QV6AH","short_pith_number":"pith:V2T64JEV","schema_version":"1.0","canonical_sha256":"aea7ee2495f7c637825b39a33d42be01f31ae247c78dd07d36e46baf3800c034","source":{"kind":"arxiv","id":"2506.18701","version":1},"attestation_state":"computed","paper":{"title":"Matrix-Game: Interactive World Foundation Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Biao Jiang, Boyang Wang, Chunli Peng, Eric Li, Fei Kang, Puyi Wang, Qingcheng Zhu, Yahui Zhou, Yang Liu, Yifan Zhang, Zedong Gao","submitted_at":"2025-06-23T14:40:49Z","abstract_excerpt":"We introduce Matrix-Game, an interactive world foundation model for controllable game world generation. Matrix-Game is trained using a two-stage pipeline that first performs large-scale unlabeled pretraining for environment understanding, followed by action-labeled training for interactive video generation. To support this, we curate Matrix-Game-MC, a comprehensive Minecraft dataset comprising over 2,700 hours of unlabeled gameplay video clips and over 1,000 hours of high-quality labeled clips with fine-grained keyboard and mouse action annotations. Our model adopts a controllable image-to-wor"},"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":"2506.18701","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-23T14:40:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e98a21231cd04496fb4d9f94f32648a13fb6847a71940c1dfa4dc73ed03a8503","abstract_canon_sha256":"7864fd8c593c62b01ef22dba7689ed2582afc51fe18af6b99b9d8aac33449b42"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:54.358234Z","signature_b64":"WKSjobA5kMajTcBtjxhanypeUZcwNOUUPyjJIAAjAtIm63MJ9zEmITnSec9qxSDAAHxk0rkOoYd4/qnalClnCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aea7ee2495f7c637825b39a33d42be01f31ae247c78dd07d36e46baf3800c034","last_reissued_at":"2026-07-05T11:25:54.357690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:54.357690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Matrix-Game: Interactive World Foundation Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Biao Jiang, Boyang Wang, Chunli Peng, Eric Li, Fei Kang, Puyi Wang, Qingcheng Zhu, Yahui Zhou, Yang Liu, Yifan Zhang, Zedong Gao","submitted_at":"2025-06-23T14:40:49Z","abstract_excerpt":"We introduce Matrix-Game, an interactive world foundation model for controllable game world generation. Matrix-Game is trained using a two-stage pipeline that first performs large-scale unlabeled pretraining for environment understanding, followed by action-labeled training for interactive video generation. To support this, we curate Matrix-Game-MC, a comprehensive Minecraft dataset comprising over 2,700 hours of unlabeled gameplay video clips and over 1,000 hours of high-quality labeled clips with fine-grained keyboard and mouse action annotations. Our model adopts a controllable image-to-wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18701","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/2506.18701/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":"2506.18701","created_at":"2026-07-05T11:25:54.357747+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18701v1","created_at":"2026-07-05T11:25:54.357747+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18701","created_at":"2026-07-05T11:25:54.357747+00:00"},{"alias_kind":"pith_short_12","alias_value":"V2T64JEV67DD","created_at":"2026-07-05T11:25:54.357747+00:00"},{"alias_kind":"pith_short_16","alias_value":"V2T64JEV67DDPAS3","created_at":"2026-07-05T11:25:54.357747+00:00"},{"alias_kind":"pith_short_8","alias_value":"V2T64JEV","created_at":"2026-07-05T11:25:54.357747+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":30,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17730","citing_title":"ActWorld: From Explorable to Interactive World Model via Action-Aware Memory","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18180","citing_title":"EgoCS-400K: An Egocentric Gameplay Dataset for World Models","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11129","citing_title":"WorldOlympiad: Can Your World Model Survive a Triathlon?","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07967","citing_title":"DisCo: World Models with Discrete Camera Motion Control","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07508","citing_title":"Streaming Video Generation with Streaming Force Control","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01060","citing_title":"RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation","ref_index":61,"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":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01164","citing_title":"Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends","ref_index":11,"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":77,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15824","citing_title":"FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30292","citing_title":"DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31336","citing_title":"DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23458","citing_title":"One-Forcing: Towards Stable One-Step Autoregressive Video Generation","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22940","citing_title":"One-to-All Animation: Alignment-Free Character Animation and Image Pose Transfer","ref_index":63,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15824","citing_title":"FashionChameleon: Towards Real-Time and Interactive Human-Garment Video Customization","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18601","citing_title":"Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models","ref_index":49,"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":57,"is_internal_anchor":false},{"citing_arxiv_id":"2601.20540","citing_title":"Advancing Open-source World Models","ref_index":89,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15178","citing_title":"SANA-WM: Efficient Minute-Scale World Modeling with Hybrid Linear Diffusion Transformer","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2603.11911","citing_title":"InSpatio-WorldFM: An Open-Source Real-Time Generative Frame Model","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22622","citing_title":"LongLive: Real-time Interactive Long Video Generation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28980","citing_title":"Stepper: Stepwise Immersive Scene Generation with Multiview Panoramas","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":229,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02799","citing_title":"UNICA: A Unified Neural Framework for Controllable 3D Avatars","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09965","citing_title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","ref_index":218,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V2T64JEV67DDPAS3HGRT2QV6AH","json":"https://pith.science/pith/V2T64JEV67DDPAS3HGRT2QV6AH.json","graph_json":"https://pith.science/api/pith-number/V2T64JEV67DDPAS3HGRT2QV6AH/graph.json","events_json":"https://pith.science/api/pith-number/V2T64JEV67DDPAS3HGRT2QV6AH/events.json","paper":"https://pith.science/paper/V2T64JEV"},"agent_actions":{"view_html":"https://pith.science/pith/V2T64JEV67DDPAS3HGRT2QV6AH","download_json":"https://pith.science/pith/V2T64JEV67DDPAS3HGRT2QV6AH.json","view_paper":"https://pith.science/paper/V2T64JEV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18701&json=true","fetch_graph":"https://pith.science/api/pith-number/V2T64JEV67DDPAS3HGRT2QV6AH/graph.json","fetch_events":"https://pith.science/api/pith-number/V2T64JEV67DDPAS3HGRT2QV6AH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V2T64JEV67DDPAS3HGRT2QV6AH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V2T64JEV67DDPAS3HGRT2QV6AH/action/storage_attestation","attest_author":"https://pith.science/pith/V2T64JEV67DDPAS3HGRT2QV6AH/action/author_attestation","sign_citation":"https://pith.science/pith/V2T64JEV67DDPAS3HGRT2QV6AH/action/citation_signature","submit_replication":"https://pith.science/pith/V2T64JEV67DDPAS3HGRT2QV6AH/action/replication_record"}},"created_at":"2026-07-05T11:25:54.357747+00:00","updated_at":"2026-07-05T11:25:54.357747+00:00"}