{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:55TGQDABMFKCCRWEJZGQFZUOGX","short_pith_number":"pith:55TGQDAB","schema_version":"1.0","canonical_sha256":"ef66680c0161542146c44e4d02e68e35c28dc768273183ba8433735b82aef54b","source":{"kind":"arxiv","id":"2406.04806","version":4},"attestation_state":"computed","paper":{"title":"Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Olav Egeland, Sigmund H. H{\\o}eg, Yilun Du","submitted_at":"2024-06-07T10:13:44Z","abstract_excerpt":"Diffusion models have seen rapid adoption in robotic imitation learning, enabling autonomous execution of complex dexterous tasks. However, action synthesis is often slow, requiring many steps of iterative denoising, limiting the extent to which models can be used in tasks that require fast reactive policies. To sidestep this, recent works have explored how the distillation of the diffusion process can be used to accelerate policy synthesis. However, distillation is computationally expensive and can hurt both the accuracy and diversity of synthesized actions. We propose SDP (Streaming Diffusio"},"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":"2406.04806","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-06-07T10:13:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c230c06ac2410e4aa14eff8794d0a8c51abf36e304de955adf1ae619aa740671","abstract_canon_sha256":"afdc217cf01aa16fa0c8911a30a94304271a148987f55afd664ef3ef1d28c084"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:10.267187Z","signature_b64":"Oio8G0vXJlUDFSl2uyj5mUBZiXgVgqKvYcgHg5xHjA85v7UE7qGF7G0d0Zl43zSc+Vg003AkB1NULX9QUn5TBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef66680c0161542146c44e4d02e68e35c28dc768273183ba8433735b82aef54b","last_reissued_at":"2026-07-05T09:19:10.266715Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:10.266715Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Streaming Diffusion Policy: Fast Policy Synthesis with Variable Noise Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Olav Egeland, Sigmund H. H{\\o}eg, Yilun Du","submitted_at":"2024-06-07T10:13:44Z","abstract_excerpt":"Diffusion models have seen rapid adoption in robotic imitation learning, enabling autonomous execution of complex dexterous tasks. However, action synthesis is often slow, requiring many steps of iterative denoising, limiting the extent to which models can be used in tasks that require fast reactive policies. To sidestep this, recent works have explored how the distillation of the diffusion process can be used to accelerate policy synthesis. However, distillation is computationally expensive and can hurt both the accuracy and diversity of synthesized actions. We propose SDP (Streaming Diffusio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.04806","kind":"arxiv","version":4},"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/2406.04806/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":"2406.04806","created_at":"2026-07-05T09:19:10.266764+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.04806v4","created_at":"2026-07-05T09:19:10.266764+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.04806","created_at":"2026-07-05T09:19:10.266764+00:00"},{"alias_kind":"pith_short_12","alias_value":"55TGQDABMFKC","created_at":"2026-07-05T09:19:10.266764+00:00"},{"alias_kind":"pith_short_16","alias_value":"55TGQDABMFKCCRWE","created_at":"2026-07-05T09:19:10.266764+00:00"},{"alias_kind":"pith_short_8","alias_value":"55TGQDAB","created_at":"2026-07-05T09:19:10.266764+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25295","citing_title":"DynaMOMA: Instantaneous Prediction of Grasp Poses for Mobile Manipulation of Dynamic Objects","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19774","citing_title":"Start Right, Arrive Right: Asynchronous Execution via Initial Noise Selection","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13355","citing_title":"Real-Time Execution with Autoregressive Policies","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24433","citing_title":"Smoother Action Chunking Flow Policy via Prior-Corrected Orthogonal Trust-Region Guidance","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12894","citing_title":"Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12978","citing_title":"Learning Native Continuation for Action Chunking Flow Policies","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19199","citing_title":"FASTER: Rethinking Real-Time Flow VLAs","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2506.07339","citing_title":"Real-Time Execution of Action Chunking Flow Policies","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19199","citing_title":"FASTER: Rethinking Real-Time Flow VLAs","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13316","citing_title":"Test-time Sparsity for Extreme Fast Action Diffusion","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55TGQDABMFKCCRWEJZGQFZUOGX","json":"https://pith.science/pith/55TGQDABMFKCCRWEJZGQFZUOGX.json","graph_json":"https://pith.science/api/pith-number/55TGQDABMFKCCRWEJZGQFZUOGX/graph.json","events_json":"https://pith.science/api/pith-number/55TGQDABMFKCCRWEJZGQFZUOGX/events.json","paper":"https://pith.science/paper/55TGQDAB"},"agent_actions":{"view_html":"https://pith.science/pith/55TGQDABMFKCCRWEJZGQFZUOGX","download_json":"https://pith.science/pith/55TGQDABMFKCCRWEJZGQFZUOGX.json","view_paper":"https://pith.science/paper/55TGQDAB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.04806&json=true","fetch_graph":"https://pith.science/api/pith-number/55TGQDABMFKCCRWEJZGQFZUOGX/graph.json","fetch_events":"https://pith.science/api/pith-number/55TGQDABMFKCCRWEJZGQFZUOGX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55TGQDABMFKCCRWEJZGQFZUOGX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55TGQDABMFKCCRWEJZGQFZUOGX/action/storage_attestation","attest_author":"https://pith.science/pith/55TGQDABMFKCCRWEJZGQFZUOGX/action/author_attestation","sign_citation":"https://pith.science/pith/55TGQDABMFKCCRWEJZGQFZUOGX/action/citation_signature","submit_replication":"https://pith.science/pith/55TGQDABMFKCCRWEJZGQFZUOGX/action/replication_record"}},"created_at":"2026-07-05T09:19:10.266764+00:00","updated_at":"2026-07-05T09:19:10.266764+00:00"}