{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JAHM3KGFQ2YLRETM4IMVZRMA7Z","short_pith_number":"pith:JAHM3KGF","schema_version":"1.0","canonical_sha256":"480ecda8c586b0b8926ce2195cc580fe58bd3a3dd0469a3e617fe51f6949b8f6","source":{"kind":"arxiv","id":"2505.07819","version":2},"attestation_state":"computed","paper":{"title":"H$^3$DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Huazhe Xu, Pu Hua, Xianbang Wang, Yiyang Lu, Yufeng Tian, Zhecheng Yuan, Zhengrong Xue","submitted_at":"2025-05-12T17:59:43Z","abstract_excerpt":"Visuomotor policy learning has witnessed substantial progress in robotic manipulation, with recent approaches predominantly relying on generative models to model the action distribution. However, these methods often overlook the critical coupling between visual perception and action prediction. In this work, we introduce $\\textbf{Triply-Hierarchical Diffusion Policy}~(\\textbf{H$^{\\mathbf{3}}$DP})$, a novel visuomotor learning framework that explicitly incorporates hierarchical structures to strengthen the integration between visual features and action generation. H$^{3}$DP contains $\\mathbf{3}"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.07819","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-05-12T17:59:43Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"a5a956ec0ce34f28e3f2bc0b036826cbca1171303c4c2e415d072c3dcec895ef","abstract_canon_sha256":"28d015d26ae2eb1d6931ef88efb2e09a1f98260c6bc2e565165f65718f26f624"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:40.058498Z","signature_b64":"9yIyNKBvIO43tqc4oS0VEcGOr3IuHAp6rOuAK5XSndfQRyN7adrKofVMLshshblnqFzp5J/VOsZqM0CO56nmCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"480ecda8c586b0b8926ce2195cc580fe58bd3a3dd0469a3e617fe51f6949b8f6","last_reissued_at":"2026-07-05T11:22:40.057976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:40.057976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"H$^3$DP: Triply-Hierarchical Diffusion Policy for Visuomotor Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Huazhe Xu, Pu Hua, Xianbang Wang, Yiyang Lu, Yufeng Tian, Zhecheng Yuan, Zhengrong Xue","submitted_at":"2025-05-12T17:59:43Z","abstract_excerpt":"Visuomotor policy learning has witnessed substantial progress in robotic manipulation, with recent approaches predominantly relying on generative models to model the action distribution. However, these methods often overlook the critical coupling between visual perception and action prediction. In this work, we introduce $\\textbf{Triply-Hierarchical Diffusion Policy}~(\\textbf{H$^{\\mathbf{3}}$DP})$, a novel visuomotor learning framework that explicitly incorporates hierarchical structures to strengthen the integration between visual features and action generation. H$^{3}$DP contains $\\mathbf{3}"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07819","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/2505.07819/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":"2505.07819","created_at":"2026-07-05T11:22:40.058031+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07819v2","created_at":"2026-07-05T11:22:40.058031+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07819","created_at":"2026-07-05T11:22:40.058031+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAHM3KGFQ2YL","created_at":"2026-07-05T11:22:40.058031+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAHM3KGFQ2YLRETM","created_at":"2026-07-05T11:22:40.058031+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAHM3KGF","created_at":"2026-07-05T11:22:40.058031+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14598","citing_title":"DSSP: Diffusion State Space Policy with Full-History Encoding","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10101","citing_title":"Robo3R: Enhancing Robotic Manipulation with Accurate Feed-Forward 3D Reconstruction","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06067","citing_title":"HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JAHM3KGFQ2YLRETM4IMVZRMA7Z","json":"https://pith.science/pith/JAHM3KGFQ2YLRETM4IMVZRMA7Z.json","graph_json":"https://pith.science/api/pith-number/JAHM3KGFQ2YLRETM4IMVZRMA7Z/graph.json","events_json":"https://pith.science/api/pith-number/JAHM3KGFQ2YLRETM4IMVZRMA7Z/events.json","paper":"https://pith.science/paper/JAHM3KGF"},"agent_actions":{"view_html":"https://pith.science/pith/JAHM3KGFQ2YLRETM4IMVZRMA7Z","download_json":"https://pith.science/pith/JAHM3KGFQ2YLRETM4IMVZRMA7Z.json","view_paper":"https://pith.science/paper/JAHM3KGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07819&json=true","fetch_graph":"https://pith.science/api/pith-number/JAHM3KGFQ2YLRETM4IMVZRMA7Z/graph.json","fetch_events":"https://pith.science/api/pith-number/JAHM3KGFQ2YLRETM4IMVZRMA7Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAHM3KGFQ2YLRETM4IMVZRMA7Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAHM3KGFQ2YLRETM4IMVZRMA7Z/action/storage_attestation","attest_author":"https://pith.science/pith/JAHM3KGFQ2YLRETM4IMVZRMA7Z/action/author_attestation","sign_citation":"https://pith.science/pith/JAHM3KGFQ2YLRETM4IMVZRMA7Z/action/citation_signature","submit_replication":"https://pith.science/pith/JAHM3KGFQ2YLRETM4IMVZRMA7Z/action/replication_record"}},"created_at":"2026-07-05T11:22:40.058031+00:00","updated_at":"2026-07-05T11:22:40.058031+00:00"}