{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UUAARPARA7RI4HPLLAERAT64GC","short_pith_number":"pith:UUAARPAR","schema_version":"1.0","canonical_sha256":"a50008bc1107e28e1deb5809104fdc3096393bfbc0e22a7dcc4ae1ddc1ab17a7","source":{"kind":"arxiv","id":"2508.11002","version":2},"attestation_state":"computed","paper":{"title":"3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Arsalan Mousavian, Jiahe Xu, Katerina Fragkiadaki, Matthew Bronars, Nikolaos Gkanatsios, Tsung-Wei Ke","submitted_at":"2025-08-14T18:07:40Z","abstract_excerpt":"We present 3D FlowMatch Actor (3DFA), a 3D policy architecture for robot manipulation that combines flow matching for trajectory prediction with 3D pretrained visual scene representations for learning from demonstration. 3DFA leverages 3D relative attention between action and visual tokens during action denoising, building on prior work in 3D diffusion-based single-arm policy learning. Through a combination of flow matching and targeted system-level and architectural optimizations, 3DFA achieves over 30x faster training and inference than previous 3D diffusion-based policies, without sacrifici"},"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":"2508.11002","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-08-14T18:07:40Z","cross_cats_sorted":[],"title_canon_sha256":"2e544c63aea18766ab7433cc612aff5b79abc02bed04e66f881817ba708f434d","abstract_canon_sha256":"9d30dd7f760e32d3e3fb884ca7d7eecc3b90484fc7db22d05358cb2c46647e8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:22.817632Z","signature_b64":"tWQS5v4CZ9lQHMpVjjFDz3DKWdiotNXEnbm16+O9gp6cJbfgwt0WsIDs4mmEDZmNd9wnjIp/6Z/uarIlT1/qDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a50008bc1107e28e1deb5809104fdc3096393bfbc0e22a7dcc4ae1ddc1ab17a7","last_reissued_at":"2026-07-05T11:56:22.817159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:22.817159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D FlowMatch Actor: Unified 3D Policy for Single- and Dual-Arm Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Arsalan Mousavian, Jiahe Xu, Katerina Fragkiadaki, Matthew Bronars, Nikolaos Gkanatsios, Tsung-Wei Ke","submitted_at":"2025-08-14T18:07:40Z","abstract_excerpt":"We present 3D FlowMatch Actor (3DFA), a 3D policy architecture for robot manipulation that combines flow matching for trajectory prediction with 3D pretrained visual scene representations for learning from demonstration. 3DFA leverages 3D relative attention between action and visual tokens during action denoising, building on prior work in 3D diffusion-based single-arm policy learning. Through a combination of flow matching and targeted system-level and architectural optimizations, 3DFA achieves over 30x faster training and inference than previous 3D diffusion-based policies, without sacrifici"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11002","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/2508.11002/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":"2508.11002","created_at":"2026-07-05T11:56:22.817217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11002v2","created_at":"2026-07-05T11:56:22.817217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11002","created_at":"2026-07-05T11:56:22.817217+00:00"},{"alias_kind":"pith_short_12","alias_value":"UUAARPARA7RI","created_at":"2026-07-05T11:56:22.817217+00:00"},{"alias_kind":"pith_short_16","alias_value":"UUAARPARA7RI4HPL","created_at":"2026-07-05T11:56:22.817217+00:00"},{"alias_kind":"pith_short_8","alias_value":"UUAARPAR","created_at":"2026-07-05T11:56:22.817217+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01938","citing_title":"PhysMani: Physics-principled 3D World Model for Dynamic Object Manipulation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10899","citing_title":"MV-Actor: Aligning Multi-View Semantics and Spatial Awareness for Bimanual Manipulation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31329","citing_title":"3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04269","citing_title":"Instant-Fold: In-Context Imitation Learning for Deformable Object Manipulation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31329","citing_title":"3D HAMSTER: Bridging Planning and Control in Hierarchical Vision Language Action Models through 3D Trajectory Guidance","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31493","citing_title":"ChronoFlow-Policy: Unifying Past-Current-Future Interaction Flow in Visuomotor Policy Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15281","citing_title":"R3D: Revisiting 3D Policy Learning","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UUAARPARA7RI4HPLLAERAT64GC","json":"https://pith.science/pith/UUAARPARA7RI4HPLLAERAT64GC.json","graph_json":"https://pith.science/api/pith-number/UUAARPARA7RI4HPLLAERAT64GC/graph.json","events_json":"https://pith.science/api/pith-number/UUAARPARA7RI4HPLLAERAT64GC/events.json","paper":"https://pith.science/paper/UUAARPAR"},"agent_actions":{"view_html":"https://pith.science/pith/UUAARPARA7RI4HPLLAERAT64GC","download_json":"https://pith.science/pith/UUAARPARA7RI4HPLLAERAT64GC.json","view_paper":"https://pith.science/paper/UUAARPAR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11002&json=true","fetch_graph":"https://pith.science/api/pith-number/UUAARPARA7RI4HPLLAERAT64GC/graph.json","fetch_events":"https://pith.science/api/pith-number/UUAARPARA7RI4HPLLAERAT64GC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UUAARPARA7RI4HPLLAERAT64GC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UUAARPARA7RI4HPLLAERAT64GC/action/storage_attestation","attest_author":"https://pith.science/pith/UUAARPARA7RI4HPLLAERAT64GC/action/author_attestation","sign_citation":"https://pith.science/pith/UUAARPARA7RI4HPLLAERAT64GC/action/citation_signature","submit_replication":"https://pith.science/pith/UUAARPARA7RI4HPLLAERAT64GC/action/replication_record"}},"created_at":"2026-07-05T11:56:22.817217+00:00","updated_at":"2026-07-05T11:56:22.817217+00:00"}