{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7AFZEBUPT32XZAROJS4PWMS5CN","short_pith_number":"pith:7AFZEBUP","schema_version":"1.0","canonical_sha256":"f80b92068f9ef57c822e4cb8fb325d137e39cb20c4dc0249d984ede88ce08652","source":{"kind":"arxiv","id":"2405.10315","version":3},"attestation_state":"computed","paper":{"title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chen Wang, Jiajun Wu, Li Fei-Fei, Ruohan Zhang, Yunfan Jiang","submitted_at":"2024-05-16T17:59:07Z","abstract_excerpt":"Learning in simulation and transferring the learned policy to the real world has the potential to enable generalist robots. The key challenge of this approach is to address simulation-to-reality (sim-to-real) gaps. Previous methods often require domain-specific knowledge a priori. We argue that a straightforward way to obtain such knowledge is by asking humans to observe and assist robot policy execution in the real world. The robots can then learn from humans to close various sim-to-real gaps. We propose TRANSIC, a data-driven approach to enable successful sim-to-real transfer based on a huma"},"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":"2405.10315","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2024-05-16T17:59:07Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"b8dd355807ebb0c3403b809f9dbc629df8805f0c3538c086c1fb894200564445","abstract_canon_sha256":"ffbe72299b07fcd332ea64b341f929c01f54cc258ef39bc48adaa11f4125eeaf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:57.464387Z","signature_b64":"kNC2OWBxIRLz7YlHHRIaxInb1jUeNoSfpo7t4ZYS/3yX51dHiSSt+fHoynkEbXI/rldMPKUAt5ZuXclXmfwXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f80b92068f9ef57c822e4cb8fb325d137e39cb20c4dc0249d984ede88ce08652","last_reissued_at":"2026-07-05T09:19:57.463909Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:57.463909Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TRANSIC: Sim-to-Real Policy Transfer by Learning from Online Correction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Chen Wang, Jiajun Wu, Li Fei-Fei, Ruohan Zhang, Yunfan Jiang","submitted_at":"2024-05-16T17:59:07Z","abstract_excerpt":"Learning in simulation and transferring the learned policy to the real world has the potential to enable generalist robots. The key challenge of this approach is to address simulation-to-reality (sim-to-real) gaps. Previous methods often require domain-specific knowledge a priori. We argue that a straightforward way to obtain such knowledge is by asking humans to observe and assist robot policy execution in the real world. The robots can then learn from humans to close various sim-to-real gaps. We propose TRANSIC, a data-driven approach to enable successful sim-to-real transfer based on a huma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10315","kind":"arxiv","version":3},"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/2405.10315/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":"2405.10315","created_at":"2026-07-05T09:19:57.463965+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10315v3","created_at":"2026-07-05T09:19:57.463965+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10315","created_at":"2026-07-05T09:19:57.463965+00:00"},{"alias_kind":"pith_short_12","alias_value":"7AFZEBUPT32X","created_at":"2026-07-05T09:19:57.463965+00:00"},{"alias_kind":"pith_short_16","alias_value":"7AFZEBUPT32XZARO","created_at":"2026-07-05T09:19:57.463965+00:00"},{"alias_kind":"pith_short_8","alias_value":"7AFZEBUP","created_at":"2026-07-05T09:19:57.463965+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22860","citing_title":"HiL-ResRL: A Model-Agnostic Finetuning Adapter via Human-in-the-loop Residual Reinforcement Learning","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06218","citing_title":"TAM: Torque Adaptation Module for Robust Motion Transfer in Manipulation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28476","citing_title":"FADA: Few-Shot Domain Adaptation via Dynamics Alignment for Humanoid Control","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09989","citing_title":"StereoPolicy: Improving Robotic Manipulation Policies via Stereo Perception","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7AFZEBUPT32XZAROJS4PWMS5CN","json":"https://pith.science/pith/7AFZEBUPT32XZAROJS4PWMS5CN.json","graph_json":"https://pith.science/api/pith-number/7AFZEBUPT32XZAROJS4PWMS5CN/graph.json","events_json":"https://pith.science/api/pith-number/7AFZEBUPT32XZAROJS4PWMS5CN/events.json","paper":"https://pith.science/paper/7AFZEBUP"},"agent_actions":{"view_html":"https://pith.science/pith/7AFZEBUPT32XZAROJS4PWMS5CN","download_json":"https://pith.science/pith/7AFZEBUPT32XZAROJS4PWMS5CN.json","view_paper":"https://pith.science/paper/7AFZEBUP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10315&json=true","fetch_graph":"https://pith.science/api/pith-number/7AFZEBUPT32XZAROJS4PWMS5CN/graph.json","fetch_events":"https://pith.science/api/pith-number/7AFZEBUPT32XZAROJS4PWMS5CN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7AFZEBUPT32XZAROJS4PWMS5CN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7AFZEBUPT32XZAROJS4PWMS5CN/action/storage_attestation","attest_author":"https://pith.science/pith/7AFZEBUPT32XZAROJS4PWMS5CN/action/author_attestation","sign_citation":"https://pith.science/pith/7AFZEBUPT32XZAROJS4PWMS5CN/action/citation_signature","submit_replication":"https://pith.science/pith/7AFZEBUPT32XZAROJS4PWMS5CN/action/replication_record"}},"created_at":"2026-07-05T09:19:57.463965+00:00","updated_at":"2026-07-05T09:19:57.463965+00:00"}