{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7PPKAPBBO3EJC52TVOUGJEHPLQ","short_pith_number":"pith:7PPKAPBB","schema_version":"1.0","canonical_sha256":"fbdea03c2176c8917753aba86490ef5c06ed26f36d29ff3df5039a14777da5dd","source":{"kind":"arxiv","id":"2601.12894","version":2},"attestation_state":"computed","paper":{"title":"Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Hanyun Cui, Jianbo Zhou, Kangye Ji, Ye Li, Yuan Meng, Zhi Wang","submitted_at":"2026-01-19T09:50:36Z","abstract_excerpt":"Diffusion Policy has dominated action generation due to its strong capabilities for modeling multi-modal action distributions, but its multi-step denoising processes make it impractical for real-time visuomotor control. Existing caching-based acceleration methods typically rely on $\\textit{static}$ schedules that fail to adapt to the $\\textit{dynamics}$ of robot-environment interactions, thereby leading to suboptimal performance. In this paper, we propose $\\underline{\\textbf{S}}$parse $\\underline{\\textbf{A}}$ction$\\underline{\\textbf{G}}$en ($\\textbf{SAG}$) for extremely sparse action generatio"},"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":"2601.12894","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.RO","submitted_at":"2026-01-19T09:50:36Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e9a367adb385e439848f5af5ce2667ca0da4b9deb67d497a057b87c0258a2a32","abstract_canon_sha256":"c46dc3c63b3d467651cb5ab6b7537775df232f603bf33ef50c00edd98e29d650"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:38.621762Z","signature_b64":"QpWhtW8q5mwvZTs6oVGIUnIm62lO2QO+pHkY1hkj1AZsko5sZUB23XiOPB8rCsP7+N89pQQfo3ktwymP5VYHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbdea03c2176c8917753aba86490ef5c06ed26f36d29ff3df5039a14777da5dd","last_reissued_at":"2026-05-20T00:01:38.621021Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:38.621021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse ActionGen: Accelerating Diffusion Policy with Real-time Pruning","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Hanyun Cui, Jianbo Zhou, Kangye Ji, Ye Li, Yuan Meng, Zhi Wang","submitted_at":"2026-01-19T09:50:36Z","abstract_excerpt":"Diffusion Policy has dominated action generation due to its strong capabilities for modeling multi-modal action distributions, but its multi-step denoising processes make it impractical for real-time visuomotor control. Existing caching-based acceleration methods typically rely on $\\textit{static}$ schedules that fail to adapt to the $\\textit{dynamics}$ of robot-environment interactions, thereby leading to suboptimal performance. In this paper, we propose $\\underline{\\textbf{S}}$parse $\\underline{\\textbf{A}}$ction$\\underline{\\textbf{G}}$en ($\\textbf{SAG}$) for extremely sparse action generatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.12894","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/2601.12894/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":"2601.12894","created_at":"2026-05-20T00:01:38.621132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.12894v2","created_at":"2026-05-20T00:01:38.621132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.12894","created_at":"2026-05-20T00:01:38.621132+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PPKAPBBO3EJ","created_at":"2026-05-20T00:01:38.621132+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PPKAPBBO3EJC52T","created_at":"2026-05-20T00:01:38.621132+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PPKAPBB","created_at":"2026-05-20T00:01:38.621132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13316","citing_title":"Test-time Sparsity for Extreme Fast Action Diffusion","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PPKAPBBO3EJC52TVOUGJEHPLQ","json":"https://pith.science/pith/7PPKAPBBO3EJC52TVOUGJEHPLQ.json","graph_json":"https://pith.science/api/pith-number/7PPKAPBBO3EJC52TVOUGJEHPLQ/graph.json","events_json":"https://pith.science/api/pith-number/7PPKAPBBO3EJC52TVOUGJEHPLQ/events.json","paper":"https://pith.science/paper/7PPKAPBB"},"agent_actions":{"view_html":"https://pith.science/pith/7PPKAPBBO3EJC52TVOUGJEHPLQ","download_json":"https://pith.science/pith/7PPKAPBBO3EJC52TVOUGJEHPLQ.json","view_paper":"https://pith.science/paper/7PPKAPBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.12894&json=true","fetch_graph":"https://pith.science/api/pith-number/7PPKAPBBO3EJC52TVOUGJEHPLQ/graph.json","fetch_events":"https://pith.science/api/pith-number/7PPKAPBBO3EJC52TVOUGJEHPLQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PPKAPBBO3EJC52TVOUGJEHPLQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PPKAPBBO3EJC52TVOUGJEHPLQ/action/storage_attestation","attest_author":"https://pith.science/pith/7PPKAPBBO3EJC52TVOUGJEHPLQ/action/author_attestation","sign_citation":"https://pith.science/pith/7PPKAPBBO3EJC52TVOUGJEHPLQ/action/citation_signature","submit_replication":"https://pith.science/pith/7PPKAPBBO3EJC52TVOUGJEHPLQ/action/replication_record"}},"created_at":"2026-05-20T00:01:38.621132+00:00","updated_at":"2026-05-20T00:01:38.621132+00:00"}