{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TH2SU6U2C4OGFAHMX7DPACH67S","short_pith_number":"pith:TH2SU6U2","schema_version":"1.0","canonical_sha256":"99f52a7a9a171c6280ecbfc6f008fefca34a6dd268325cbb351f5afcd9b76ea6","source":{"kind":"arxiv","id":"2403.03954","version":7},"attestation_state":"computed","paper":{"title":"3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A compact 3D point-cloud representation lets diffusion policies learn precise robot manipulation from only ten demonstrations.","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chenyuan Hu, Gu Zhang, Huazhe Xu, Kangning Zhang, Muhan Wang, Yanjie Ze","submitted_at":"2024-03-06T18:58:49Z","abstract_excerpt":"Imitation learning provides an efficient way to teach robots dexterous skills; however, learning complex skills robustly and generalizablely usually consumes large amounts of human demonstrations. To tackle this challenging problem, we present 3D Diffusion Policy (DP3), a novel visual imitation learning approach that incorporates the power of 3D visual representations into diffusion policies, a class of conditional action generative models. The core design of DP3 is the utilization of a compact 3D visual representation, extracted from sparse point clouds with an efficient point encoder. In our"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2403.03954","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-06T18:58:49Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"38c87db59baade0db5b3588d7a24aa23e5df235f6d265dcabba1e958f2f7f57a","abstract_canon_sha256":"674c6b880643042c8489509f171589c244982c96ccb748278b06b3613277ad0b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:53.898886Z","signature_b64":"Zqnk5/jw4qDr5q2fcw7hw8mUL0AIRMoL5cjO9B0kKpnqTTCvkWsU+z4fU+Ua349LtnylE75eMlR9QdDC/Qk/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99f52a7a9a171c6280ecbfc6f008fefca34a6dd268325cbb351f5afcd9b76ea6","last_reissued_at":"2026-05-17T23:38:53.898288Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:53.898288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"A compact 3D point-cloud representation lets diffusion policies learn precise robot manipulation from only ten demonstrations.","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chenyuan Hu, Gu Zhang, Huazhe Xu, Kangning Zhang, Muhan Wang, Yanjie Ze","submitted_at":"2024-03-06T18:58:49Z","abstract_excerpt":"Imitation learning provides an efficient way to teach robots dexterous skills; however, learning complex skills robustly and generalizablely usually consumes large amounts of human demonstrations. To tackle this challenging problem, we present 3D Diffusion Policy (DP3), a novel visual imitation learning approach that incorporates the power of 3D visual representations into diffusion policies, a class of conditional action generative models. The core design of DP3 is the utilization of a compact 3D visual representation, extracted from sparse point clouds with an efficient point encoder. In our"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"DP3 successfully handles most tasks with just 10 demonstrations and surpasses baselines with a 24.2% relative improvement. In 4 real robot tasks, DP3 demonstrates precise control with a high success rate of 85%, given only 40 demonstrations of each task, and shows excellent generalization abilities in diverse aspects, including space, viewpoint, appearance, and instance.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the compact 3D visual representation extracted from sparse point clouds is sufficient to capture all task-relevant geometry and generalizes across the reported variations without requiring additional modalities or task-specific tuning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DP3 uses compact 3D representations from sparse point clouds inside diffusion policies to learn generalizable visuomotor skills from few demonstrations, reporting 24% gains in simulation and 85% success on real robots.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A compact 3D point-cloud representation lets diffusion policies learn precise robot manipulation from only ten demonstrations.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"ca4b7c96669eec40f6437a925cdf6cfb940ff9f939db2a49af05c61dc98653a8"},"source":{"id":"2403.03954","kind":"arxiv","version":7},"verdict":{"id":"f026222b-ba74-4d38-a380-7be14c7b9072","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:45:13.165980Z","strongest_claim":"DP3 successfully handles most tasks with just 10 demonstrations and surpasses baselines with a 24.2% relative improvement. In 4 real robot tasks, DP3 demonstrates precise control with a high success rate of 85%, given only 40 demonstrations of each task, and shows excellent generalization abilities in diverse aspects, including space, viewpoint, appearance, and instance.","one_line_summary":"DP3 uses compact 3D representations from sparse point clouds inside diffusion policies to learn generalizable visuomotor skills from few demonstrations, reporting 24% gains in simulation and 85% success on real robots.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the compact 3D visual representation extracted from sparse point clouds is sufficient to capture all task-relevant geometry and generalizes across the reported variations without requiring additional modalities or task-specific tuning.","pith_extraction_headline":"A compact 3D point-cloud representation lets diffusion policies learn precise robot manipulation from only ten demonstrations."},"references":{"count":86,"sample":[{"doi":"","year":2023,"title":"Dexterous functional grasping","work_id":"9d69378e-39e5-400e-b8d6-32281def3639","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2022,"title":"Is Conditional Generative Modeling all you need for Decision-Making?","work_id":"dac365c0-e557-4886-9a1b-179151a66160","ref_index":2,"cited_arxiv_id":"2211.15657","is_internal_anchor":true},{"doi":"","year":2023,"title":"Dexterous imitation made easy: A learning-based framework for efficient dexterous manip- ulation","work_id":"dea89fcb-ec88-420f-98c5-98f62b27946c","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"Layer normalization","work_id":"ed385731-279c-494d-a83e-231e5685c903","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Dexart: Benchmarking generalizable dexterous manipu- lation with articulated objects","work_id":"29407570-41c3-421c-984f-e44dbbe81587","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":86,"snapshot_sha256":"344f58f2269bcfefd09f744cdb20674d831cb97527c15d73c90166e0af897c52","internal_anchors":3},"formal_canon":{"evidence_count":3,"snapshot_sha256":"a1db8447b7fb0c2773103f3a1554ac5f959ef739f1af420d76ce6e6df4d4ec5c"},"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":"2403.03954","created_at":"2026-05-17T23:38:53.898395+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.03954v7","created_at":"2026-05-17T23:38:53.898395+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03954","created_at":"2026-05-17T23:38:53.898395+00:00"},{"alias_kind":"pith_short_12","alias_value":"TH2SU6U2C4OG","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"TH2SU6U2C4OGFAHM","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"TH2SU6U2","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":57,"internal_anchor_count":57,"sample":[{"citing_arxiv_id":"2511.02239","citing_title":"LACY: A Vision-Language Model-based Language-Action Cycle for Self-Improving Robotic Manipulation","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14598","citing_title":"DSSP: Diffusion State Space Policy with Full-History Encoding","ref_index":62,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21862","citing_title":"EvoScene-VLA: Evolving Scene Beliefs Inside the Action Decoder for Chunked Robot Control","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22671","citing_title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2509.19102","citing_title":"FUNCanon: Learning Pose-Aware Action Primitives via Functional Object Canonicalization for Generalizable Robotic Manipulation","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2509.14787","citing_title":"COMPASS: Confined-space Manipulation Planning with Active Sensing Strategy","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2601.12894","citing_title":"Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20200","citing_title":"Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulation","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2602.09023","citing_title":"TwinRL: Digital Twin-Driven Reinforcement Learning for Real-World Robotic Manipulation","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2602.16712","citing_title":"One Hand to Rule Them All: Canonical Representations for Unified Dexterous Manipulation","ref_index":41,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20856","citing_title":"DISC: Decoupling Instruction from State-Conditioned Control via Policy Generation","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20894","citing_title":"Mobile UMI: Cross-View Diffusion Policy with Decoupled Kinematics for Mobile Manipulation","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20737","citing_title":"Resolving Long-Tail Ambiguity in Unsupervised 3D Point Cloud Segmentation with Language Priors","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21414","citing_title":"PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interaction","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21460","citing_title":"HITL-D: Human In The Loop Diffusion Assisted Shared Control","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16043","citing_title":"Learning Sim-Grounded Policies for Bimanual Rope Manipulation from Human Teleoperation Data","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17300","citing_title":"HCLM: A Hierarchical Framework for Cooperative Loco-Manipulation with Dual Quadrupeds","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17522","citing_title":"RoboFlow4D: A Lightweight Flow World Model Toward Real-Time Flow-Guided Robotic Manipulation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15536","citing_title":"SkiP: When to Skip and When to Refine for Efficient Robot Manipulation","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2506.15953","citing_title":"ViTacFormer: Learning Cross-Modal Representation for Visuo-Tactile Dexterous Manipulation","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2510.01433","citing_title":"AFFORD2ACT: Affordance-Guided Automatic Keypoint Selection for Generalizable and Lightweight Robotic Manipulation","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2511.01770","citing_title":"Lightweight Learning from Actuation-Space Demonstrations via Flow Matching for Whole-Body Soft Robotic Grasping","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2511.12878","citing_title":"Uni-Hand: Universal Hand Motion Forecasting in Egocentric Views","ref_index":42,"is_internal_anchor":true},{"citing_arxiv_id":"2506.15799","citing_title":"Steering Your Diffusion Policy with Latent Space Reinforcement Learning","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2512.01773","citing_title":"IGen: Scalable Data Generation for Robot Learning from Open-World Images","ref_index":68,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":3,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S","json":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S.json","graph_json":"https://pith.science/api/pith-number/TH2SU6U2C4OGFAHMX7DPACH67S/graph.json","events_json":"https://pith.science/api/pith-number/TH2SU6U2C4OGFAHMX7DPACH67S/events.json","paper":"https://pith.science/paper/TH2SU6U2"},"agent_actions":{"view_html":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S","download_json":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S.json","view_paper":"https://pith.science/paper/TH2SU6U2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.03954&json=true","fetch_graph":"https://pith.science/api/pith-number/TH2SU6U2C4OGFAHMX7DPACH67S/graph.json","fetch_events":"https://pith.science/api/pith-number/TH2SU6U2C4OGFAHMX7DPACH67S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S/action/storage_attestation","attest_author":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S/action/author_attestation","sign_citation":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S/action/citation_signature","submit_replication":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S/action/replication_record"}},"created_at":"2026-05-17T23:38:53.898395+00:00","updated_at":"2026-05-17T23:38:53.898395+00:00"}