{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MXV6OSVOQ7OXXOVIC3AZPHEOES","short_pith_number":"pith:MXV6OSVO","schema_version":"1.0","canonical_sha256":"65ebe74aae87dd7bbaa816c1979c8e24b1f2ff627d97453f6f28a8924469345e","source":{"kind":"arxiv","id":"2506.06199","version":1},"attestation_state":"computed","paper":{"title":"3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Hongyan Zhi, Lei Han, Mingkui Tan, Peihao Chen, Quanxi Wu, Siyuan Zhou, Yubo Dong","submitted_at":"2025-06-06T16:00:31Z","abstract_excerpt":"Manipulation has long been a challenging task for robots, while humans can effortlessly perform complex interactions with objects, such as hanging a cup on the mug rack. A key reason is the lack of a large and uniform dataset for teaching robots manipulation skills. Current robot datasets often record robot action in different action spaces within a simple scene. This hinders the robot to learn a unified and robust action representation for different robots within diverse scenes. Observing how humans understand a manipulation task, we find that understanding how the objects should move in the "},"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":"2506.06199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-06-06T16:00:31Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"b488f4e39afa9b29e389960024319dde267022e001a792a7545ec81e68815430","abstract_canon_sha256":"c4981fa51482469b487500ebf4ce29a36fc8ff0b33df16ef7a8fcda16ca1ff3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:27.432461Z","signature_b64":"n5lOqj6y4CkUbOSvTH5NlOMXNUgNBFZab/0qj1RBmzKSK7jQDYndmGx0wQXWBp0l5sJ/Zo1++xgrc3EjJgtLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"65ebe74aae87dd7bbaa816c1979c8e24b1f2ff627d97453f6f28a8924469345e","last_reissued_at":"2026-07-05T11:17:27.431748Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:27.431748Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Hongyan Zhi, Lei Han, Mingkui Tan, Peihao Chen, Quanxi Wu, Siyuan Zhou, Yubo Dong","submitted_at":"2025-06-06T16:00:31Z","abstract_excerpt":"Manipulation has long been a challenging task for robots, while humans can effortlessly perform complex interactions with objects, such as hanging a cup on the mug rack. A key reason is the lack of a large and uniform dataset for teaching robots manipulation skills. Current robot datasets often record robot action in different action spaces within a simple scene. This hinders the robot to learn a unified and robust action representation for different robots within diverse scenes. Observing how humans understand a manipulation task, we find that understanding how the objects should move in the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06199","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/2506.06199/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":"2506.06199","created_at":"2026-07-05T11:17:27.431859+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06199v1","created_at":"2026-07-05T11:17:27.431859+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06199","created_at":"2026-07-05T11:17:27.431859+00:00"},{"alias_kind":"pith_short_12","alias_value":"MXV6OSVOQ7OX","created_at":"2026-07-05T11:17:27.431859+00:00"},{"alias_kind":"pith_short_16","alias_value":"MXV6OSVOQ7OXXOVI","created_at":"2026-07-05T11:17:27.431859+00:00"},{"alias_kind":"pith_short_8","alias_value":"MXV6OSVO","created_at":"2026-07-05T11:17:27.431859+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.20781","citing_title":"World Action Models: A Survey","ref_index":207,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00836","citing_title":"From World Models to World Action Models: A Concise Tutorial for Robotics","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.16533","citing_title":"Kairos: A Regret-Aware Native World-Action Model Stack for Physical AI","ref_index":141,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00836","citing_title":"From World Models to World Action Models: A Concise Tutorial for Robotics","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12369","citing_title":"GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22882","citing_title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22882","citing_title":"GEM-4D: Geometry-Enhanced Video World Models for Robot Manipulation","ref_index":71,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22123","citing_title":"Beyond Pixels: Learning Invariant Rewards for Real-World Robotics From a Few Demonstrations","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17522","citing_title":"RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11459","citing_title":"Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12090","citing_title":"World Action Models: The Next Frontier in Embodied AI","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12369","citing_title":"GuidedVLA: Specifying Task-Relevant Factors via Plug-and-Play Action Attention Specialization","ref_index":102,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11459","citing_title":"Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MXV6OSVOQ7OXXOVIC3AZPHEOES","json":"https://pith.science/pith/MXV6OSVOQ7OXXOVIC3AZPHEOES.json","graph_json":"https://pith.science/api/pith-number/MXV6OSVOQ7OXXOVIC3AZPHEOES/graph.json","events_json":"https://pith.science/api/pith-number/MXV6OSVOQ7OXXOVIC3AZPHEOES/events.json","paper":"https://pith.science/paper/MXV6OSVO"},"agent_actions":{"view_html":"https://pith.science/pith/MXV6OSVOQ7OXXOVIC3AZPHEOES","download_json":"https://pith.science/pith/MXV6OSVOQ7OXXOVIC3AZPHEOES.json","view_paper":"https://pith.science/paper/MXV6OSVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06199&json=true","fetch_graph":"https://pith.science/api/pith-number/MXV6OSVOQ7OXXOVIC3AZPHEOES/graph.json","fetch_events":"https://pith.science/api/pith-number/MXV6OSVOQ7OXXOVIC3AZPHEOES/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MXV6OSVOQ7OXXOVIC3AZPHEOES/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MXV6OSVOQ7OXXOVIC3AZPHEOES/action/storage_attestation","attest_author":"https://pith.science/pith/MXV6OSVOQ7OXXOVIC3AZPHEOES/action/author_attestation","sign_citation":"https://pith.science/pith/MXV6OSVOQ7OXXOVIC3AZPHEOES/action/citation_signature","submit_replication":"https://pith.science/pith/MXV6OSVOQ7OXXOVIC3AZPHEOES/action/replication_record"}},"created_at":"2026-07-05T11:17:27.431859+00:00","updated_at":"2026-07-05T11:17:27.431859+00:00"}