{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:C32IHJXZR2TY6CDUE6UGJNDSSA","short_pith_number":"pith:C32IHJXZ","schema_version":"1.0","canonical_sha256":"16f483a6f98ea78f087427a864b4729019db3435c1f2a643e497fe33f9cf2c53","source":{"kind":"arxiv","id":"2502.20396","version":2},"attestation_state":"computed","paper":{"title":"Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Jitendra Malik, Kartik Sachdev, Linxi Fan, Toru Lin, Yuke Zhu","submitted_at":"2025-02-27T18:59:52Z","abstract_excerpt":"Learning generalizable robot manipulation policies, especially for complex multi-fingered humanoids, remains a significant challenge. Existing approaches primarily rely on extensive data collection and imitation learning, which are expensive, labor-intensive, and difficult to scale. Sim-to-real reinforcement learning (RL) offers a promising alternative, but has mostly succeeded in simpler state-based or single-hand setups. How to effectively extend this to vision-based, contact-rich bimanual manipulation tasks remains an open question. In this paper, we introduce a practical sim-to-real RL rec"},"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":"2502.20396","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-02-27T18:59:52Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.SY","eess.SY"],"title_canon_sha256":"51cf7d30222e454774a856fa0ab90fcc6a100de754990e495e0bf69ffa4c70fd","abstract_canon_sha256":"10c724a09d80f726655b1d584ef38bb8c8a244bd3b628971311d781385c756c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:41.429853Z","signature_b64":"rYmWMHT+1JdViQI0FeQoYxz1r2kRJ63COZkLC57b8KayWjcm4uwS017U37exKg5k6aHPEa72NQ3k/219Q6CJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"16f483a6f98ea78f087427a864b4729019db3435c1f2a643e497fe33f9cf2c53","last_reissued_at":"2026-07-05T12:02:41.429359Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:41.429359Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sim-to-Real Reinforcement Learning for Vision-Based Dexterous Manipulation on Humanoids","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.SY","eess.SY"],"primary_cat":"cs.RO","authors_text":"Jitendra Malik, Kartik Sachdev, Linxi Fan, Toru Lin, Yuke Zhu","submitted_at":"2025-02-27T18:59:52Z","abstract_excerpt":"Learning generalizable robot manipulation policies, especially for complex multi-fingered humanoids, remains a significant challenge. Existing approaches primarily rely on extensive data collection and imitation learning, which are expensive, labor-intensive, and difficult to scale. Sim-to-real reinforcement learning (RL) offers a promising alternative, but has mostly succeeded in simpler state-based or single-hand setups. How to effectively extend this to vision-based, contact-rich bimanual manipulation tasks remains an open question. In this paper, we introduce a practical sim-to-real RL rec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.20396","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/2502.20396/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":"2502.20396","created_at":"2026-07-05T12:02:41.429415+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.20396v2","created_at":"2026-07-05T12:02:41.429415+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.20396","created_at":"2026-07-05T12:02:41.429415+00:00"},{"alias_kind":"pith_short_12","alias_value":"C32IHJXZR2TY","created_at":"2026-07-05T12:02:41.429415+00:00"},{"alias_kind":"pith_short_16","alias_value":"C32IHJXZR2TY6CDU","created_at":"2026-07-05T12:02:41.429415+00:00"},{"alias_kind":"pith_short_8","alias_value":"C32IHJXZ","created_at":"2026-07-05T12:02:41.429415+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22471","citing_title":"Scalable Multi-Task Data Generation via Reinforcement Learning for Language-Conditioned Bimanual Dexterous Manipulation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12604","citing_title":"EgoEngine: From Egocentric Human Videos to High-Fidelity Dexterous Robot Demonstrations","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22471","citing_title":"Scalable Multi-Task Data Generation via Reinforcement Learning for Language-Conditioned Bimanual Dexterous Manipulation","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27676","citing_title":"CWI: Composite Humanoid Whole-Body Imitation System for Loco-manipulation","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29298","citing_title":"MonoDuo: Using One Robot Arm to Learn Bimanual Policies","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2510.03599","citing_title":"Learning to Act Through Contact: A Unified View of Multi-Task Robot Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13925","citing_title":"Towards Robotic Dexterous Hand Intelligence: A Survey","ref_index":169,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C32IHJXZR2TY6CDUE6UGJNDSSA","json":"https://pith.science/pith/C32IHJXZR2TY6CDUE6UGJNDSSA.json","graph_json":"https://pith.science/api/pith-number/C32IHJXZR2TY6CDUE6UGJNDSSA/graph.json","events_json":"https://pith.science/api/pith-number/C32IHJXZR2TY6CDUE6UGJNDSSA/events.json","paper":"https://pith.science/paper/C32IHJXZ"},"agent_actions":{"view_html":"https://pith.science/pith/C32IHJXZR2TY6CDUE6UGJNDSSA","download_json":"https://pith.science/pith/C32IHJXZR2TY6CDUE6UGJNDSSA.json","view_paper":"https://pith.science/paper/C32IHJXZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.20396&json=true","fetch_graph":"https://pith.science/api/pith-number/C32IHJXZR2TY6CDUE6UGJNDSSA/graph.json","fetch_events":"https://pith.science/api/pith-number/C32IHJXZR2TY6CDUE6UGJNDSSA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C32IHJXZR2TY6CDUE6UGJNDSSA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C32IHJXZR2TY6CDUE6UGJNDSSA/action/storage_attestation","attest_author":"https://pith.science/pith/C32IHJXZR2TY6CDUE6UGJNDSSA/action/author_attestation","sign_citation":"https://pith.science/pith/C32IHJXZR2TY6CDUE6UGJNDSSA/action/citation_signature","submit_replication":"https://pith.science/pith/C32IHJXZR2TY6CDUE6UGJNDSSA/action/replication_record"}},"created_at":"2026-07-05T12:02:41.429415+00:00","updated_at":"2026-07-05T12:02:41.429415+00:00"}