{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GS2KG5A5YBVXDCXYDLXJ6NCBHS","short_pith_number":"pith:GS2KG5A5","schema_version":"1.0","canonical_sha256":"34b4a3741dc06b718af81aee9f34413c9f65a4987295db599bd6c20860ceeb63","source":{"kind":"arxiv","id":"2009.13303","version":2},"attestation_state":"computed","paper":{"title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Jorge Pe\\~na Queralta, Tomi Westerlund, Wenshuai Zhao","submitted_at":"2020-09-24T21:05:46Z","abstract_excerpt":"Deep reinforcement learning has recently seen huge success across multiple areas in the robotics domain. Owing to the limitations of gathering real-world data, i.e., sample inefficiency and the cost of collecting it, simulation environments are utilized for training the different agents. This not only aids in providing a potentially infinite data source, but also alleviates safety concerns with real robots. Nonetheless, the gap between the simulated and real worlds degrades the performance of the policies once the models are transferred into real robots. Multiple research efforts are therefore"},"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":"2009.13303","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-09-24T21:05:46Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"4b880c6b2b17cb77d67efda19dd45970ccf5c16088977baf42512aeff16b4e1a","abstract_canon_sha256":"e2087031df4f91029de24cf1aee4f0e63f80a5b89a8f4bc0e5bdbc05ba07d3c2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:13.437385Z","signature_b64":"6+1xAezuPAHd6EHJ/ch6RYwmWsVZt1qbf8848eEP+mAZ8jyc2fwExBylC6Uod7/FX/rgTW4zzhUMJbnFzDVlAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34b4a3741dc06b718af81aee9f34413c9f65a4987295db599bd6c20860ceeb63","last_reissued_at":"2026-07-05T02:56:13.436898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:13.436898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sim-to-Real Transfer in Deep Reinforcement Learning for Robotics: a Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.LG","authors_text":"Jorge Pe\\~na Queralta, Tomi Westerlund, Wenshuai Zhao","submitted_at":"2020-09-24T21:05:46Z","abstract_excerpt":"Deep reinforcement learning has recently seen huge success across multiple areas in the robotics domain. Owing to the limitations of gathering real-world data, i.e., sample inefficiency and the cost of collecting it, simulation environments are utilized for training the different agents. This not only aids in providing a potentially infinite data source, but also alleviates safety concerns with real robots. Nonetheless, the gap between the simulated and real worlds degrades the performance of the policies once the models are transferred into real robots. Multiple research efforts are therefore"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2009.13303","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/2009.13303/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":"2009.13303","created_at":"2026-07-05T02:56:13.436947+00:00"},{"alias_kind":"arxiv_version","alias_value":"2009.13303v2","created_at":"2026-07-05T02:56:13.436947+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2009.13303","created_at":"2026-07-05T02:56:13.436947+00:00"},{"alias_kind":"pith_short_12","alias_value":"GS2KG5A5YBVX","created_at":"2026-07-05T02:56:13.436947+00:00"},{"alias_kind":"pith_short_16","alias_value":"GS2KG5A5YBVXDCXY","created_at":"2026-07-05T02:56:13.436947+00:00"},{"alias_kind":"pith_short_8","alias_value":"GS2KG5A5","created_at":"2026-07-05T02:56:13.436947+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.18953","citing_title":"Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30765","citing_title":"Deep Reinforcement Learning for Individual Atomic Control and Cooling","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31101","citing_title":"Efficient Sim-to-Real Transfer of World-Action Models from Synthetic Priors","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30456","citing_title":"Vision-Language-Action Models: Experimental Insights from a Real-World UR5 Platform","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11174","citing_title":"EmbodiedGovBench: A Benchmark for Governance, Recovery, and Upgrade Safety in Embodied Agent Systems","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GS2KG5A5YBVXDCXYDLXJ6NCBHS","json":"https://pith.science/pith/GS2KG5A5YBVXDCXYDLXJ6NCBHS.json","graph_json":"https://pith.science/api/pith-number/GS2KG5A5YBVXDCXYDLXJ6NCBHS/graph.json","events_json":"https://pith.science/api/pith-number/GS2KG5A5YBVXDCXYDLXJ6NCBHS/events.json","paper":"https://pith.science/paper/GS2KG5A5"},"agent_actions":{"view_html":"https://pith.science/pith/GS2KG5A5YBVXDCXYDLXJ6NCBHS","download_json":"https://pith.science/pith/GS2KG5A5YBVXDCXYDLXJ6NCBHS.json","view_paper":"https://pith.science/paper/GS2KG5A5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2009.13303&json=true","fetch_graph":"https://pith.science/api/pith-number/GS2KG5A5YBVXDCXYDLXJ6NCBHS/graph.json","fetch_events":"https://pith.science/api/pith-number/GS2KG5A5YBVXDCXYDLXJ6NCBHS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GS2KG5A5YBVXDCXYDLXJ6NCBHS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GS2KG5A5YBVXDCXYDLXJ6NCBHS/action/storage_attestation","attest_author":"https://pith.science/pith/GS2KG5A5YBVXDCXYDLXJ6NCBHS/action/author_attestation","sign_citation":"https://pith.science/pith/GS2KG5A5YBVXDCXYDLXJ6NCBHS/action/citation_signature","submit_replication":"https://pith.science/pith/GS2KG5A5YBVXDCXYDLXJ6NCBHS/action/replication_record"}},"created_at":"2026-07-05T02:56:13.436947+00:00","updated_at":"2026-07-05T02:56:13.436947+00:00"}