{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:QDUHDKM52GSEOCXESSOL25GDNY","short_pith_number":"pith:QDUHDKM5","schema_version":"1.0","canonical_sha256":"80e871a99dd1a4470ae4949cbd74c36e12276155a17ceb4146cc62a985342584","source":{"kind":"arxiv","id":"2504.08388","version":1},"attestation_state":"computed","paper":{"title":"MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyu Wu, Jiang Bian, Junliang Guo, Tianyu He, Tim Pearce, Yang Ye, Yushu Jiang","submitted_at":"2025-04-11T09:41:04Z","abstract_excerpt":"World modeling is a crucial task for enabling intelligent agents to effectively interact with humans and operate in dynamic environments. In this work, we propose MineWorld, a real-time interactive world model on Minecraft, an open-ended sandbox game which has been utilized as a common testbed for world modeling. MineWorld is driven by a visual-action autoregressive Transformer, which takes paired game scenes and corresponding actions as input, and generates consequent new scenes following the actions. Specifically, by transforming visual game scenes and actions into discrete token ids with an"},"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":"2504.08388","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-11T09:41:04Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d526d7ff3444ada346876de2398dfc8e75311aac52e5f10522b69e724a211169","abstract_canon_sha256":"4dbb118ee5995228c4746d0e67b3d77a3df0b30b52f2fa8ae725d00cd79dade4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:47:48.223229Z","signature_b64":"6NRmL/h78FLusttuJytnZrn6sHUVHbfA0qCNNNx51B5edBA7+7LBYYJifdU39VyzUowGHJbYfFnhDKXZvvcgBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80e871a99dd1a4470ae4949cbd74c36e12276155a17ceb4146cc62a985342584","last_reissued_at":"2026-07-05T10:47:48.222681Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:47:48.222681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MineWorld: a Real-Time and Open-Source Interactive World Model on Minecraft","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Haoyu Wu, Jiang Bian, Junliang Guo, Tianyu He, Tim Pearce, Yang Ye, Yushu Jiang","submitted_at":"2025-04-11T09:41:04Z","abstract_excerpt":"World modeling is a crucial task for enabling intelligent agents to effectively interact with humans and operate in dynamic environments. In this work, we propose MineWorld, a real-time interactive world model on Minecraft, an open-ended sandbox game which has been utilized as a common testbed for world modeling. MineWorld is driven by a visual-action autoregressive Transformer, which takes paired game scenes and corresponding actions as input, and generates consequent new scenes following the actions. Specifically, by transforming visual game scenes and actions into discrete token ids with an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.08388","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/2504.08388/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":"2504.08388","created_at":"2026-07-05T10:47:48.222737+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.08388v1","created_at":"2026-07-05T10:47:48.222737+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.08388","created_at":"2026-07-05T10:47:48.222737+00:00"},{"alias_kind":"pith_short_12","alias_value":"QDUHDKM52GSE","created_at":"2026-07-05T10:47:48.222737+00:00"},{"alias_kind":"pith_short_16","alias_value":"QDUHDKM52GSEOCXE","created_at":"2026-07-05T10:47:48.222737+00:00"},{"alias_kind":"pith_short_8","alias_value":"QDUHDKM5","created_at":"2026-07-05T10:47:48.222737+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.06291","citing_title":"AlayaWorld: Long-Horizon and Playable Video World Generation","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05352","citing_title":"Multiplayer Interactive World Models with Representation Autoencoders","ref_index":202,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26694","citing_title":"PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31672","citing_title":"WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18180","citing_title":"EgoCS-400K: An Egocentric Gameplay Dataset for World Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12191","citing_title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03920","citing_title":"Benchmarking Visual State Tracking in Multimodal Video Understanding","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02436","citing_title":"Geometry-Aware Implicit Memory for Video World Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01164","citing_title":"Towards Interactive Video World Modeling: Frontiers, Challenges, Benchmarks, and Future Trends","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31672","citing_title":"WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26694","citing_title":"PhysEditWorld: A Large-Scale Dataset Toward Physics-Editable World Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31336","citing_title":"DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23345","citing_title":"SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models","ref_index":18,"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":16,"is_internal_anchor":false},{"citing_arxiv_id":"2505.21996","citing_title":"VRAG: Learning World Models for Interactive Video Generation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2507.07982","citing_title":"Geometry Forcing: Marrying Video Diffusion and 3D Representation for Consistent World Modeling","ref_index":27,"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":13,"is_internal_anchor":false},{"citing_arxiv_id":"2512.21714","citing_title":"AstraNav-World: World Model for Foresight Control and Consistency","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06949","citing_title":"DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24527","citing_title":"Training Agents Inside of Scalable World Models","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":228,"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":57,"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":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21686","citing_title":"WorldMark: A Unified Benchmark Suite for Interactive Video World Models","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09527","citing_title":"Envisioning the Future, One Step at a Time","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QDUHDKM52GSEOCXESSOL25GDNY","json":"https://pith.science/pith/QDUHDKM52GSEOCXESSOL25GDNY.json","graph_json":"https://pith.science/api/pith-number/QDUHDKM52GSEOCXESSOL25GDNY/graph.json","events_json":"https://pith.science/api/pith-number/QDUHDKM52GSEOCXESSOL25GDNY/events.json","paper":"https://pith.science/paper/QDUHDKM5"},"agent_actions":{"view_html":"https://pith.science/pith/QDUHDKM52GSEOCXESSOL25GDNY","download_json":"https://pith.science/pith/QDUHDKM52GSEOCXESSOL25GDNY.json","view_paper":"https://pith.science/paper/QDUHDKM5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.08388&json=true","fetch_graph":"https://pith.science/api/pith-number/QDUHDKM52GSEOCXESSOL25GDNY/graph.json","fetch_events":"https://pith.science/api/pith-number/QDUHDKM52GSEOCXESSOL25GDNY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QDUHDKM52GSEOCXESSOL25GDNY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QDUHDKM52GSEOCXESSOL25GDNY/action/storage_attestation","attest_author":"https://pith.science/pith/QDUHDKM52GSEOCXESSOL25GDNY/action/author_attestation","sign_citation":"https://pith.science/pith/QDUHDKM52GSEOCXESSOL25GDNY/action/citation_signature","submit_replication":"https://pith.science/pith/QDUHDKM52GSEOCXESSOL25GDNY/action/replication_record"}},"created_at":"2026-07-05T10:47:48.222737+00:00","updated_at":"2026-07-05T10:47:48.222737+00:00"}