{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NBWGXMIIWLCYY2MHQTRZE5L3FJ","short_pith_number":"pith:NBWGXMII","schema_version":"1.0","canonical_sha256":"686c6bb108b2c58c698784e392757b2a7191ea529d8e6aff43f6af41d819bdeb","source":{"kind":"arxiv","id":"2506.18897","version":2},"attestation_state":"computed","paper":{"title":"MinD: Learning A Dual-System World Model for Real-Time Planning and Implicit Risk Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jiaming Liu, Kuangzhi Ge, Lei Han, Peidong Jia, Shanghang Zhang, Sirui Han, Siyuan Zhou, Tingguang Li, Xiaowei Chi, Yike Guo, Yuzhen Liu, Zichen He","submitted_at":"2025-06-23T17:59:06Z","abstract_excerpt":"Video Generation Models (VGMs) have become powerful backbones for Vision-Language-Action (VLA) models, leveraging large-scale pretraining for robust dynamics modeling. However, current methods underutilize their distribution modeling capabilities for predicting future states. Two challenges hinder progress: integrating generative processes into feature learning is both technically and conceptually underdeveloped, and naive frame-by-frame video diffusion is computationally inefficient for real-time robotics. To address these, we propose Manipulate in Dream (MinD), a dual-system world model for "},"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":"2506.18897","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-06-23T17:59:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"811e9d5f4ee093bf80c0f575cb58da52d6369ffe66aa29bf9dfb1337639a5dd8","abstract_canon_sha256":"c210e9632df658e9776efaf7b4bee8c94285e3bf7306c61b4b97d23da5397c6a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:20.878853Z","signature_b64":"DF0k5el2dvDxJ2tcwDWZQopa12sErwZQd9aWVvcBE3zZTj+KCbMV6QulignFXcn2wTwo3atr/HMpLBQWRNWjCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"686c6bb108b2c58c698784e392757b2a7191ea529d8e6aff43f6af41d819bdeb","last_reissued_at":"2026-07-05T11:56:20.878373Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:20.878373Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MinD: Learning A Dual-System World Model for Real-Time Planning and Implicit Risk Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Jiaming Liu, Kuangzhi Ge, Lei Han, Peidong Jia, Shanghang Zhang, Sirui Han, Siyuan Zhou, Tingguang Li, Xiaowei Chi, Yike Guo, Yuzhen Liu, Zichen He","submitted_at":"2025-06-23T17:59:06Z","abstract_excerpt":"Video Generation Models (VGMs) have become powerful backbones for Vision-Language-Action (VLA) models, leveraging large-scale pretraining for robust dynamics modeling. However, current methods underutilize their distribution modeling capabilities for predicting future states. Two challenges hinder progress: integrating generative processes into feature learning is both technically and conceptually underdeveloped, and naive frame-by-frame video diffusion is computationally inefficient for real-time robotics. To address these, we propose Manipulate in Dream (MinD), a dual-system world model for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.18897","kind":"arxiv","version":2},"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/2506.18897/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":"2506.18897","created_at":"2026-07-05T11:56:20.878433+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.18897v2","created_at":"2026-07-05T11:56:20.878433+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.18897","created_at":"2026-07-05T11:56:20.878433+00:00"},{"alias_kind":"pith_short_12","alias_value":"NBWGXMIIWLCY","created_at":"2026-07-05T11:56:20.878433+00:00"},{"alias_kind":"pith_short_16","alias_value":"NBWGXMIIWLCYY2MH","created_at":"2026-07-05T11:56:20.878433+00:00"},{"alias_kind":"pith_short_8","alias_value":"NBWGXMII","created_at":"2026-07-05T11:56:20.878433+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17924","citing_title":"PearlVLA: Progressive Embodied Action-Plan Refinement in Latent Space","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22882","citing_title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00113","citing_title":"World Models for Robotic Manipulation: A Survey","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22882","citing_title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12167","citing_title":"From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NBWGXMIIWLCYY2MHQTRZE5L3FJ","json":"https://pith.science/pith/NBWGXMIIWLCYY2MHQTRZE5L3FJ.json","graph_json":"https://pith.science/api/pith-number/NBWGXMIIWLCYY2MHQTRZE5L3FJ/graph.json","events_json":"https://pith.science/api/pith-number/NBWGXMIIWLCYY2MHQTRZE5L3FJ/events.json","paper":"https://pith.science/paper/NBWGXMII"},"agent_actions":{"view_html":"https://pith.science/pith/NBWGXMIIWLCYY2MHQTRZE5L3FJ","download_json":"https://pith.science/pith/NBWGXMIIWLCYY2MHQTRZE5L3FJ.json","view_paper":"https://pith.science/paper/NBWGXMII","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.18897&json=true","fetch_graph":"https://pith.science/api/pith-number/NBWGXMIIWLCYY2MHQTRZE5L3FJ/graph.json","fetch_events":"https://pith.science/api/pith-number/NBWGXMIIWLCYY2MHQTRZE5L3FJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NBWGXMIIWLCYY2MHQTRZE5L3FJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NBWGXMIIWLCYY2MHQTRZE5L3FJ/action/storage_attestation","attest_author":"https://pith.science/pith/NBWGXMIIWLCYY2MHQTRZE5L3FJ/action/author_attestation","sign_citation":"https://pith.science/pith/NBWGXMIIWLCYY2MHQTRZE5L3FJ/action/citation_signature","submit_replication":"https://pith.science/pith/NBWGXMIIWLCYY2MHQTRZE5L3FJ/action/replication_record"}},"created_at":"2026-07-05T11:56:20.878433+00:00","updated_at":"2026-07-05T11:56:20.878433+00:00"}