{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TTQOX6XML4D4NDY6CE5RDOKFHV","short_pith_number":"pith:TTQOX6XM","schema_version":"1.0","canonical_sha256":"9ce0ebfaec5f07c68f1e113b11b9453d73b17cbb3307716c0b9e59744f9d7204","source":{"kind":"arxiv","id":"2505.09723","version":1},"attestation_state":"computed","paper":{"title":"EnerVerse-AC: Envisioning Embodied Environments with Action Condition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chiming Liu, Guanghui Ren, Hongsheng Li, Liliang Chen, Maoqing Yao, Pengfei Zhou, Shengcong Chen, Siyuan Huang, Xindong He, Yue Liao, Yuxin Jiang","submitted_at":"2025-05-14T18:30:53Z","abstract_excerpt":"Robotic imitation learning has advanced from solving static tasks to addressing dynamic interaction scenarios, but testing and evaluation remain costly and challenging due to the need for real-time interaction with dynamic environments. We propose EnerVerse-AC (EVAC), an action-conditional world model that generates future visual observations based on an agent's predicted actions, enabling realistic and controllable robotic inference. Building on prior architectures, EVAC introduces a multi-level action-conditioning mechanism and ray map encoding for dynamic multi-view image generation while e"},"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":"2505.09723","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T18:30:53Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"978ee7f960248e57e296cf76b1641fb118c661b222adc4a3ab55f7f97ae76825","abstract_canon_sha256":"2cd4c8c81f94aa4a3b08ad9dfa362728f3deebc4a473269a05a986c63768009d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:44.843845Z","signature_b64":"xGsnWbkxuJFO43chDJZrVtJS6NKeU2s67XC6R0Ed6Q8WZXVpisLqz0VZrVVDd1LJEGEZAZ2uDDZhyca7aJkzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ce0ebfaec5f07c68f1e113b11b9453d73b17cbb3307716c0b9e59744f9d7204","last_reissued_at":"2026-07-05T11:03:44.843357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:44.843357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EnerVerse-AC: Envisioning Embodied Environments with Action Condition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Chiming Liu, Guanghui Ren, Hongsheng Li, Liliang Chen, Maoqing Yao, Pengfei Zhou, Shengcong Chen, Siyuan Huang, Xindong He, Yue Liao, Yuxin Jiang","submitted_at":"2025-05-14T18:30:53Z","abstract_excerpt":"Robotic imitation learning has advanced from solving static tasks to addressing dynamic interaction scenarios, but testing and evaluation remain costly and challenging due to the need for real-time interaction with dynamic environments. We propose EnerVerse-AC (EVAC), an action-conditional world model that generates future visual observations based on an agent's predicted actions, enabling realistic and controllable robotic inference. Building on prior architectures, EVAC introduces a multi-level action-conditioning mechanism and ray map encoding for dynamic multi-view image generation while e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09723","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/2505.09723/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":"2505.09723","created_at":"2026-07-05T11:03:44.843426+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09723v1","created_at":"2026-07-05T11:03:44.843426+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09723","created_at":"2026-07-05T11:03:44.843426+00:00"},{"alias_kind":"pith_short_12","alias_value":"TTQOX6XML4D4","created_at":"2026-07-05T11:03:44.843426+00:00"},{"alias_kind":"pith_short_16","alias_value":"TTQOX6XML4D4NDY6","created_at":"2026-07-05T11:03:44.843426+00:00"},{"alias_kind":"pith_short_8","alias_value":"TTQOX6XM","created_at":"2026-07-05T11:03:44.843426+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06401","citing_title":"A Definition and Roadmap for World Models","ref_index":215,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18960","citing_title":"Mem-World: Memory-Augmented Action-Conditioned World Models for Persistent Robot Manipulation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18375","citing_title":"PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13672","citing_title":"WEAVER, Better, Faster, Longer: An Effective World Model for Robotic Manipulation","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09813","citing_title":"iMaC: Translating Actions into Motion and Contact Images for Embodied World Models","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":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01799","citing_title":"Embody4D: A Generalist Data Engine for Embodied 4D World Modeling","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29501","citing_title":"Learning Transferable Dynamics Priors from Action to World Modeling","ref_index":24,"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":13,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01027","citing_title":"$\\tau_0$-WM: A Unified Video-Action World Model for Robotic Manipulation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2510.26433","citing_title":"Co-Evolving Latent Action World Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2602.06949","citing_title":"DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10125","citing_title":"Ctrl-World: A Controllable Generative World Model for Robot Manipulation","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2508.05635","citing_title":"Genie Envisioner: A Unified World Foundation Platform for Robotic Manipulation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2603.28489","citing_title":"Video Generation Models as World Models: Efficient Paradigms, Architectures and Algorithms","ref_index":207,"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":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22152","citing_title":"dWorldEval: Scalable Robotic Policy Evaluation via Discrete Diffusion World Model","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21741","citing_title":"Hi-WM: Human-in-the-World-Model for Scalable Robot Post-Training","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01799","citing_title":"Embody4D: A Generalist Data Engine for Embodied 4D World Modeling","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TTQOX6XML4D4NDY6CE5RDOKFHV","json":"https://pith.science/pith/TTQOX6XML4D4NDY6CE5RDOKFHV.json","graph_json":"https://pith.science/api/pith-number/TTQOX6XML4D4NDY6CE5RDOKFHV/graph.json","events_json":"https://pith.science/api/pith-number/TTQOX6XML4D4NDY6CE5RDOKFHV/events.json","paper":"https://pith.science/paper/TTQOX6XM"},"agent_actions":{"view_html":"https://pith.science/pith/TTQOX6XML4D4NDY6CE5RDOKFHV","download_json":"https://pith.science/pith/TTQOX6XML4D4NDY6CE5RDOKFHV.json","view_paper":"https://pith.science/paper/TTQOX6XM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09723&json=true","fetch_graph":"https://pith.science/api/pith-number/TTQOX6XML4D4NDY6CE5RDOKFHV/graph.json","fetch_events":"https://pith.science/api/pith-number/TTQOX6XML4D4NDY6CE5RDOKFHV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TTQOX6XML4D4NDY6CE5RDOKFHV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TTQOX6XML4D4NDY6CE5RDOKFHV/action/storage_attestation","attest_author":"https://pith.science/pith/TTQOX6XML4D4NDY6CE5RDOKFHV/action/author_attestation","sign_citation":"https://pith.science/pith/TTQOX6XML4D4NDY6CE5RDOKFHV/action/citation_signature","submit_replication":"https://pith.science/pith/TTQOX6XML4D4NDY6CE5RDOKFHV/action/replication_record"}},"created_at":"2026-07-05T11:03:44.843426+00:00","updated_at":"2026-07-05T11:03:44.843426+00:00"}