{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DY4YTZY6XO4NIMJOFZTETFKLSP","short_pith_number":"pith:DY4YTZY6","schema_version":"1.0","canonical_sha256":"1e3989e71ebbb8d4312e2e6649954b93fb2cf56beab8d7c5ba64678bf4a3b5fd","source":{"kind":"arxiv","id":"2503.22634","version":2},"attestation_state":"computed","paper":{"title":"Empirical Analysis of Sim-and-Real Cotraining of Diffusion Policies for Planar Pushing from Pixels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Abhinav Agarwal, Adam Wei, Boyuan Chen, Nicholas Pfaff, Rohan Bosworth, Russ Tedrake","submitted_at":"2025-03-28T17:25:57Z","abstract_excerpt":"Cotraining with demonstration data generated both in simulation and on real hardware has emerged as a promising recipe for scaling imitation learning in robotics. This work seeks to elucidate basic principles of this sim-and-real cotraining to inform simulation design, sim-and-real dataset creation, and policy training. Our experiments confirm that cotraining with simulated data can dramatically improve performance, especially when real data is limited. We show that these performance gains scale with additional simulated data up to a plateau; adding more real-world data increases this performa"},"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":"2503.22634","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-03-28T17:25:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a18847c9c5d0a15669eba2f5e1cc742361cc7559a2fb6a40d9bd171c75b8b4ec","abstract_canon_sha256":"de6cb0651e1dc8cf2c64507f15c76c5b9d0eea810ab0a1e3f3227c7535878426"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:49:08.815517Z","signature_b64":"cmOv7z+L42J/zFx60nQ+hC/gDV4ZOIPpZhmIf27d9pab2YyZjlZVY7OMNS4gPz3MMMR6A/D6s2AxC6n6ehxvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e3989e71ebbb8d4312e2e6649954b93fb2cf56beab8d7c5ba64678bf4a3b5fd","last_reissued_at":"2026-07-05T11:49:08.814947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:49:08.814947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empirical Analysis of Sim-and-Real Cotraining of Diffusion Policies for Planar Pushing from Pixels","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Abhinav Agarwal, Adam Wei, Boyuan Chen, Nicholas Pfaff, Rohan Bosworth, Russ Tedrake","submitted_at":"2025-03-28T17:25:57Z","abstract_excerpt":"Cotraining with demonstration data generated both in simulation and on real hardware has emerged as a promising recipe for scaling imitation learning in robotics. This work seeks to elucidate basic principles of this sim-and-real cotraining to inform simulation design, sim-and-real dataset creation, and policy training. Our experiments confirm that cotraining with simulated data can dramatically improve performance, especially when real data is limited. We show that these performance gains scale with additional simulated data up to a plateau; adding more real-world data increases this performa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22634","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/2503.22634/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":"2503.22634","created_at":"2026-07-05T11:49:08.815005+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22634v2","created_at":"2026-07-05T11:49:08.815005+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22634","created_at":"2026-07-05T11:49:08.815005+00:00"},{"alias_kind":"pith_short_12","alias_value":"DY4YTZY6XO4N","created_at":"2026-07-05T11:49:08.815005+00:00"},{"alias_kind":"pith_short_16","alias_value":"DY4YTZY6XO4NIMJO","created_at":"2026-07-05T11:49:08.815005+00:00"},{"alias_kind":"pith_short_8","alias_value":"DY4YTZY6","created_at":"2026-07-05T11:49:08.815005+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01410","citing_title":"BIFROST: Bridging Invariant Feature Representation for Observation-space Sim2Real Transfer","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12365","citing_title":"Ambient Diffusion Policy: Imitation Learning from Suboptimal Data in Robotics","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28276","citing_title":"SimFoundry: Modular and Automated Scene Generation for Policy Learning and Evaluation","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26638","citing_title":"HyperSim: A Holistic Sim-To-Real Framework For Robust Robotic Manipulation","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27724","citing_title":"HumanoidMimicGen: Data Generation for Loco-Manipulation via Whole-Body Planning","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05331","citing_title":"A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13645","citing_title":"A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policies","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DY4YTZY6XO4NIMJOFZTETFKLSP","json":"https://pith.science/pith/DY4YTZY6XO4NIMJOFZTETFKLSP.json","graph_json":"https://pith.science/api/pith-number/DY4YTZY6XO4NIMJOFZTETFKLSP/graph.json","events_json":"https://pith.science/api/pith-number/DY4YTZY6XO4NIMJOFZTETFKLSP/events.json","paper":"https://pith.science/paper/DY4YTZY6"},"agent_actions":{"view_html":"https://pith.science/pith/DY4YTZY6XO4NIMJOFZTETFKLSP","download_json":"https://pith.science/pith/DY4YTZY6XO4NIMJOFZTETFKLSP.json","view_paper":"https://pith.science/paper/DY4YTZY6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22634&json=true","fetch_graph":"https://pith.science/api/pith-number/DY4YTZY6XO4NIMJOFZTETFKLSP/graph.json","fetch_events":"https://pith.science/api/pith-number/DY4YTZY6XO4NIMJOFZTETFKLSP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DY4YTZY6XO4NIMJOFZTETFKLSP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DY4YTZY6XO4NIMJOFZTETFKLSP/action/storage_attestation","attest_author":"https://pith.science/pith/DY4YTZY6XO4NIMJOFZTETFKLSP/action/author_attestation","sign_citation":"https://pith.science/pith/DY4YTZY6XO4NIMJOFZTETFKLSP/action/citation_signature","submit_replication":"https://pith.science/pith/DY4YTZY6XO4NIMJOFZTETFKLSP/action/replication_record"}},"created_at":"2026-07-05T11:49:08.815005+00:00","updated_at":"2026-07-05T11:49:08.815005+00:00"}