{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TVMUNXE3SK2PSLDCY3QK2PG2JM","short_pith_number":"pith:TVMUNXE3","schema_version":"1.0","canonical_sha256":"9d5946dc9b92b4f92c62c6e0ad3cda4b1abc9463b82547c54c87589104058220","source":{"kind":"arxiv","id":"2407.01531","version":2},"attestation_state":"computed","paper":{"title":"Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Chenfeng Xu, Masayoshi Tomizuka, Mingxiao Huo, Mingyu Ding, Pengliang Ji, Ran Tian, Wei Zhan, Xiang Zhang, Yichen Xie, Yifei Zhang, Yixiao Wang","submitted_at":"2024-07-01T17:59:56Z","abstract_excerpt":"The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning. Traditional models typically rely on a universal policy for all tasks, facing challenges such as high computational costs and catastrophic forgetting when learning new tasks. To address these issues, we introduce a sparse, reusable, and flexible policy, Sparse Diffusion Policy (SDP). By adopting Mixture of Experts (MoE) within a transformer-based diffusion policy, SDP selectively activates experts and skills, enabling efficient and task-specific learning without retraining the enti"},"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":"2407.01531","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-07-01T17:59:56Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3950357004cad7789d3f8e2af8451e1cee6d944332832936498f7d8bd76541a7","abstract_canon_sha256":"b961faf1e0a4c07450285433d13eca6435eefc94b88110b8520b32dd97554d48"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:25:44.976984Z","signature_b64":"tp3HMS/CnbmLbf4Fw2GB6Pyj5AHF3nCZcYcI5b5M+kKcqzGkwBUehJBl+lUtqRrCAQCMCmIW0L8Vo1EqOqs1Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d5946dc9b92b4f92c62c6e0ad3cda4b1abc9463b82547c54c87589104058220","last_reissued_at":"2026-07-05T09:25:44.976484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:25:44.976484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sparse Diffusion Policy: A Sparse, Reusable, and Flexible Policy for Robot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Chenfeng Xu, Masayoshi Tomizuka, Mingxiao Huo, Mingyu Ding, Pengliang Ji, Ran Tian, Wei Zhan, Xiang Zhang, Yichen Xie, Yifei Zhang, Yixiao Wang","submitted_at":"2024-07-01T17:59:56Z","abstract_excerpt":"The increasing complexity of tasks in robotics demands efficient strategies for multitask and continual learning. Traditional models typically rely on a universal policy for all tasks, facing challenges such as high computational costs and catastrophic forgetting when learning new tasks. To address these issues, we introduce a sparse, reusable, and flexible policy, Sparse Diffusion Policy (SDP). By adopting Mixture of Experts (MoE) within a transformer-based diffusion policy, SDP selectively activates experts and skills, enabling efficient and task-specific learning without retraining the enti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01531","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/2407.01531/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":"2407.01531","created_at":"2026-07-05T09:25:44.976548+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01531v2","created_at":"2026-07-05T09:25:44.976548+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01531","created_at":"2026-07-05T09:25:44.976548+00:00"},{"alias_kind":"pith_short_12","alias_value":"TVMUNXE3SK2P","created_at":"2026-07-05T09:25:44.976548+00:00"},{"alias_kind":"pith_short_16","alias_value":"TVMUNXE3SK2PSLDC","created_at":"2026-07-05T09:25:44.976548+00:00"},{"alias_kind":"pith_short_8","alias_value":"TVMUNXE3","created_at":"2026-07-05T09:25:44.976548+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.10503","citing_title":"Towards Long-Lived Robots: Continual Learning VLA Models via Reinforcement Fine-Tuning","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2511.18085","citing_title":"Continually Evolving Skill Knowledge in Vision Language Action Model","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2502.05855","citing_title":"DexVLA: Vision-Language Model with Plug-In Diffusion Expert for General Robot Control","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03066","citing_title":"Redefining End-of-Life: Intelligent Automation for Electronics Remanufacturing Systems","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03404","citing_title":"Diffusion Policy with Bayesian Expert Selection for Active Multi-Target Tracking","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07381","citing_title":"Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation","ref_index":50,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TVMUNXE3SK2PSLDCY3QK2PG2JM","json":"https://pith.science/pith/TVMUNXE3SK2PSLDCY3QK2PG2JM.json","graph_json":"https://pith.science/api/pith-number/TVMUNXE3SK2PSLDCY3QK2PG2JM/graph.json","events_json":"https://pith.science/api/pith-number/TVMUNXE3SK2PSLDCY3QK2PG2JM/events.json","paper":"https://pith.science/paper/TVMUNXE3"},"agent_actions":{"view_html":"https://pith.science/pith/TVMUNXE3SK2PSLDCY3QK2PG2JM","download_json":"https://pith.science/pith/TVMUNXE3SK2PSLDCY3QK2PG2JM.json","view_paper":"https://pith.science/paper/TVMUNXE3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01531&json=true","fetch_graph":"https://pith.science/api/pith-number/TVMUNXE3SK2PSLDCY3QK2PG2JM/graph.json","fetch_events":"https://pith.science/api/pith-number/TVMUNXE3SK2PSLDCY3QK2PG2JM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TVMUNXE3SK2PSLDCY3QK2PG2JM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TVMUNXE3SK2PSLDCY3QK2PG2JM/action/storage_attestation","attest_author":"https://pith.science/pith/TVMUNXE3SK2PSLDCY3QK2PG2JM/action/author_attestation","sign_citation":"https://pith.science/pith/TVMUNXE3SK2PSLDCY3QK2PG2JM/action/citation_signature","submit_replication":"https://pith.science/pith/TVMUNXE3SK2PSLDCY3QK2PG2JM/action/replication_record"}},"created_at":"2026-07-05T09:25:44.976548+00:00","updated_at":"2026-07-05T09:25:44.976548+00:00"}