{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:TH2SU6U2C4OGFAHMX7DPACH67S","short_pith_number":"pith:TH2SU6U2","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"},"canonical_sha256":"99f52a7a9a171c6280ecbfc6f008fefca34a6dd268325cbb351f5afcd9b76ea6","source":{"kind":"arxiv","id":"2403.03954","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03954","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03954v7","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03954","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"TH2SU6U2C4OG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TH2SU6U2C4OGFAHM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TH2SU6U2","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:TH2SU6U2C4OGFAHMX7DPACH67S","target":"record","payload":{"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"},"canonical_sha256":"99f52a7a9a171c6280ecbfc6f008fefca34a6dd268325cbb351f5afcd9b76ea6","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"},"source_kind":"arxiv","source_id":"2403.03954","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6DGwMXE8qMgehTsvPdXb7MXMBb3OIrsGYYupholNkm0xrHUlkv5AamQ4QklAJ0ILip7Ru6oEhV6YBBZNJ0+3DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:20:18.216074Z"},"content_sha256":"6caec2406301e547e98ee45ac058827c9282b615ff1dbd35ad49f8daf4726803","schema_version":"1.0","event_id":"sha256:6caec2406301e547e98ee45ac058827c9282b615ff1dbd35ad49f8daf4726803"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:TH2SU6U2C4OGFAHMX7DPACH67S","target":"graph","payload":{"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"},"verdict_id":"f026222b-ba74-4d38-a380-7be14c7b9072"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"69YLRPSWODO/qd5J/8t38fy5C0l7wNh21PT5/ZGU9opODaNmbKBSAT3DO6kj84TMMXuss5/phCrvJlxe28VnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:20:18.216678Z"},"content_sha256":"f077a8efdd6be95b179fdbf98ec6297f75d0790577e8e0adfceab03f350803a0","schema_version":"1.0","event_id":"sha256:f077a8efdd6be95b179fdbf98ec6297f75d0790577e8e0adfceab03f350803a0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S/bundle.json","state_url":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TH2SU6U2C4OGFAHMX7DPACH67S/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-26T17:20:18Z","links":{"resolver":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S","bundle":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S/bundle.json","state":"https://pith.science/pith/TH2SU6U2C4OGFAHMX7DPACH67S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TH2SU6U2C4OGFAHMX7DPACH67S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:TH2SU6U2C4OGFAHMX7DPACH67S","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"674c6b880643042c8489509f171589c244982c96ccb748278b06b3613277ad0b","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-06T18:58:49Z","title_canon_sha256":"38c87db59baade0db5b3588d7a24aa23e5df235f6d265dcabba1e958f2f7f57a"},"schema_version":"1.0","source":{"id":"2403.03954","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.03954","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"arxiv_version","alias_value":"2403.03954v7","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.03954","created_at":"2026-05-17T23:38:53Z"},{"alias_kind":"pith_short_12","alias_value":"TH2SU6U2C4OG","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"TH2SU6U2C4OGFAHM","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"TH2SU6U2","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:f077a8efdd6be95b179fdbf98ec6297f75d0790577e8e0adfceab03f350803a0","target":"graph","created_at":"2026-05-17T23:38:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A compact 3D point-cloud representation lets diffusion policies learn precise robot manipulation from only ten demonstrations."}],"snapshot_sha256":"ca4b7c96669eec40f6437a925cdf6cfb940ff9f939db2a49af05c61dc98653a8"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"a1db8447b7fb0c2773103f3a1554ac5f959ef739f1af420d76ce6e6df4d4ec5c"},"paper":{"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","authors_text":"Chenyuan Hu, Gu Zhang, Huazhe Xu, Kangning Zhang, Muhan Wang, Yanjie Ze","cross_cats":["cs.CV","cs.LG"],"headline":"A compact 3D point-cloud representation lets diffusion policies learn precise robot manipulation from only ten demonstrations.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-06T18:58:49Z","title":"3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations"},"references":{"count":86,"internal_anchors":3,"resolved_work":86,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Dexterous functional grasping","work_id":"9d69378e-39e5-400e-b8d6-32281def3639","year":2023},{"cited_arxiv_id":"2211.15657","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Is Conditional Generative Modeling all you need for Decision-Making?","work_id":"dac365c0-e557-4886-9a1b-179151a66160","year":2022},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Dexterous imitation made easy: A learning-based framework for efficient dexterous manip- ulation","work_id":"dea89fcb-ec88-420f-98c5-98f62b27946c","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Layer normalization","work_id":"ed385731-279c-494d-a83e-231e5685c903","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Dexart: Benchmarking generalizable dexterous manipu- lation with articulated objects","work_id":"29407570-41c3-421c-984f-e44dbbe81587","year":2023}],"snapshot_sha256":"344f58f2269bcfefd09f744cdb20674d831cb97527c15d73c90166e0af897c52"},"source":{"id":"2403.03954","kind":"arxiv","version":7},"verdict":{"created_at":"2026-05-15T01:45:13.165980Z","id":"f026222b-ba74-4d38-a380-7be14c7b9072","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"A compact 3D point-cloud representation lets diffusion policies learn precise robot manipulation from only ten demonstrations.","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.","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."}},"verdict_id":"f026222b-ba74-4d38-a380-7be14c7b9072"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6caec2406301e547e98ee45ac058827c9282b615ff1dbd35ad49f8daf4726803","target":"record","created_at":"2026-05-17T23:38:53Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"674c6b880643042c8489509f171589c244982c96ccb748278b06b3613277ad0b","cross_cats_sorted":["cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-03-06T18:58:49Z","title_canon_sha256":"38c87db59baade0db5b3588d7a24aa23e5df235f6d265dcabba1e958f2f7f57a"},"schema_version":"1.0","source":{"id":"2403.03954","kind":"arxiv","version":7}},"canonical_sha256":"99f52a7a9a171c6280ecbfc6f008fefca34a6dd268325cbb351f5afcd9b76ea6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99f52a7a9a171c6280ecbfc6f008fefca34a6dd268325cbb351f5afcd9b76ea6","first_computed_at":"2026-05-17T23:38:53.898288Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:53.898288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zqnk5/jw4qDr5q2fcw7hw8mUL0AIRMoL5cjO9B0kKpnqTTCvkWsU+z4fU+Ua349LtnylE75eMlR9QdDC/Qk/Ag==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:53.898886Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.03954","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6caec2406301e547e98ee45ac058827c9282b615ff1dbd35ad49f8daf4726803","sha256:f077a8efdd6be95b179fdbf98ec6297f75d0790577e8e0adfceab03f350803a0"],"state_sha256":"f0229d0c84f932369589505a6a6859cd710d86671010cff45a6312efbe2bc531"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"umriz4UFPWTa/7ctUfnC9jA1tE0eJa/XBAvgdgdiE/RwovItCTaD7iOlev/VRY1bsBGrcBTb53TwFnWLOB+mCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T17:20:18.219456Z","bundle_sha256":"341dad3285b572a4d24de85b1fabb4b22208eba35a385715d1b4fa2160d6221e"}}