{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:HEZXAD7ENL55X2RBQDMWM7M4AP","short_pith_number":"pith:HEZXAD7E","schema_version":"1.0","canonical_sha256":"3933700fe46afbdbea2180d9667d9c03fa6ec3897b1701a13b28cf7c8d7c3b4d","source":{"kind":"arxiv","id":"2406.14540","version":2},"attestation_state":"computed","paper":{"title":"IRASim: A Fine-Grained World Model for Robot Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chilam Cheang, Fangqi Zhu, Hongtao Wu, Song Guo, Tao Kong, Yuxiao Liu","submitted_at":"2024-06-20T17:50:16Z","abstract_excerpt":"World models allow autonomous agents to plan and explore by predicting the visual outcomes of different actions. However, for robot manipulation, it is challenging to accurately model the fine-grained robot-object interaction within the visual space using existing methods which overlooks precise alignment between each action and the corresponding frame. In this paper, we present IRASim, a novel world model capable of generating videos with fine-grained robot-object interaction details, conditioned on historical observations and robot action trajectories. We train a diffusion transformer and in"},"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":"2406.14540","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-20T17:50:16Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"35948f18c0aa08b24b778af27b26344d9032021222c729ec331198e149f9963f","abstract_canon_sha256":"1e43c62543f7b6474ae9031214738cfda7fed975f2a1216c521a2216f90b133c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:40.032539Z","signature_b64":"Xb7FRjqGXg3oFbWsingEz1nbYMcANWumU5RNdC0sFzCxEqZ3gm3S3+nPc0ylg/KdjARVVAu6ZpzMG+l+tHD0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3933700fe46afbdbea2180d9667d9c03fa6ec3897b1701a13b28cf7c8d7c3b4d","last_reissued_at":"2026-07-05T11:44:40.032094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:40.032094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IRASim: A Fine-Grained World Model for Robot Manipulation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chilam Cheang, Fangqi Zhu, Hongtao Wu, Song Guo, Tao Kong, Yuxiao Liu","submitted_at":"2024-06-20T17:50:16Z","abstract_excerpt":"World models allow autonomous agents to plan and explore by predicting the visual outcomes of different actions. However, for robot manipulation, it is challenging to accurately model the fine-grained robot-object interaction within the visual space using existing methods which overlooks precise alignment between each action and the corresponding frame. In this paper, we present IRASim, a novel world model capable of generating videos with fine-grained robot-object interaction details, conditioned on historical observations and robot action trajectories. We train a diffusion transformer and in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14540","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/2406.14540/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":"2406.14540","created_at":"2026-07-05T11:44:40.032147+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.14540v2","created_at":"2026-07-05T11:44:40.032147+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14540","created_at":"2026-07-05T11:44:40.032147+00:00"},{"alias_kind":"pith_short_12","alias_value":"HEZXAD7ENL55","created_at":"2026-07-05T11:44:40.032147+00:00"},{"alias_kind":"pith_short_16","alias_value":"HEZXAD7ENL55X2RB","created_at":"2026-07-05T11:44:40.032147+00:00"},{"alias_kind":"pith_short_8","alias_value":"HEZXAD7E","created_at":"2026-07-05T11:44:40.032147+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.08639","citing_title":"Native Video-Action Pretraining for Generalizable Robot Control","ref_index":133,"is_internal_anchor":true},{"citing_arxiv_id":"2607.06559","citing_title":"RynnWorld-4D: 4D Embodied World Models for Robotic Manipulation","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2606.21088","citing_title":"MV-WAM: Manifold-Aware World Action Model with Value Augmentation","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":214,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18610","citing_title":"SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05773","citing_title":"PiL-World: A Chunk-Wise World Model for VLA Policy-in-the-Loop Evaluation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01060","citing_title":"RoboWorld: Fast and Reliable Neural Simulators for Generalist Robot Policy Evaluation","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14398","citing_title":"Coding Agent Is Good As World Simulator","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31734","citing_title":"MemLearner: Learning to Query Context memory for Video World Models","ref_index":75,"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":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18610","citing_title":"SC3-Eval: Evaluating Robot Foundation Models via Self-Consistent Video Generation","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27491","citing_title":"GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00133","citing_title":"World Models: A Comprehensive Survey of Architectures, Methodologies, Reasoning Paradigms, and Applications","ref_index":187,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29360","citing_title":"MiraBench: Evaluating Action-Conditioned Reliability in Robotic World Models","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14598","citing_title":"DSSP: Diffusion State Space Policy with Full-History Encoding","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17912","citing_title":"WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26433","citing_title":"Co-Evolving Latent Action World Models","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2512.15840","citing_title":"Large Video Planner Enables Generalizable Robot Control","ref_index":90,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11075","citing_title":"RISE: Self-Improving Robot Policy with Compositional World Model","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10125","citing_title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14398","citing_title":"Coding Agent Is Good As World Simulator","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13775","citing_title":"RoboEvolve: Co-Evolving Planner-Simulator for Robotic Manipulation with Limited Data","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00062","citing_title":"World Simulation with Video Foundation Models for Physical AI","ref_index":101,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08712","citing_title":"From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23001","citing_title":"Vision-Language-Action in Robotics: A Survey of Datasets, Benchmarks, and Data Engines","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HEZXAD7ENL55X2RBQDMWM7M4AP","json":"https://pith.science/pith/HEZXAD7ENL55X2RBQDMWM7M4AP.json","graph_json":"https://pith.science/api/pith-number/HEZXAD7ENL55X2RBQDMWM7M4AP/graph.json","events_json":"https://pith.science/api/pith-number/HEZXAD7ENL55X2RBQDMWM7M4AP/events.json","paper":"https://pith.science/paper/HEZXAD7E"},"agent_actions":{"view_html":"https://pith.science/pith/HEZXAD7ENL55X2RBQDMWM7M4AP","download_json":"https://pith.science/pith/HEZXAD7ENL55X2RBQDMWM7M4AP.json","view_paper":"https://pith.science/paper/HEZXAD7E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.14540&json=true","fetch_graph":"https://pith.science/api/pith-number/HEZXAD7ENL55X2RBQDMWM7M4AP/graph.json","fetch_events":"https://pith.science/api/pith-number/HEZXAD7ENL55X2RBQDMWM7M4AP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HEZXAD7ENL55X2RBQDMWM7M4AP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HEZXAD7ENL55X2RBQDMWM7M4AP/action/storage_attestation","attest_author":"https://pith.science/pith/HEZXAD7ENL55X2RBQDMWM7M4AP/action/author_attestation","sign_citation":"https://pith.science/pith/HEZXAD7ENL55X2RBQDMWM7M4AP/action/citation_signature","submit_replication":"https://pith.science/pith/HEZXAD7ENL55X2RBQDMWM7M4AP/action/replication_record"}},"created_at":"2026-07-05T11:44:40.032147+00:00","updated_at":"2026-07-05T11:44:40.032147+00:00"}