{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UB2Y5OL3ENRWYSKIJFAOO7DSQC","short_pith_number":"pith:UB2Y5OL3","schema_version":"1.0","canonical_sha256":"a0758eb97b23636c49484940e77c728096b310df0c17b773aa38cda4122e7f1a","source":{"kind":"arxiv","id":"2603.12243","version":4},"attestation_state":"computed","paper":{"title":"HandelBot: Real-World Piano Playing via Fast Adaptation of Dexterous Robot Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"HandelBot adapts a simulation policy in two stages to let a dexterous robot play piano accurately after 30 minutes of real data.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Amber Xie, Dorsa Sadigh, Haozhi Qi","submitted_at":"2026-03-12T17:56:29Z","abstract_excerpt":"Mastering dexterous manipulation with multi-fingered hands has been a grand challenge in robotics for decades. Despite its potential, the difficulty of collecting high-quality data remains a primary bottleneck for high-precision tasks. While reinforcement learning and simulation-to-real-world transfer offer a promising alternative, the transferred policies often fail for tasks demanding millimeter-scale precision, such as bimanual piano playing. In this work, we introduce HandelBot, a framework that combines a simulation policy and rapid adaptation through a two-stage pipeline. Starting from a"},"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":true},"canonical_record":{"source":{"id":"2603.12243","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-03-12T17:56:29Z","cross_cats_sorted":[],"title_canon_sha256":"d43d5cf8b40f1cb80969e69ffacd50a77b984f229d5a5e9f012443e282536e28","abstract_canon_sha256":"87dbc93e30dbef1b78a49e3035a4825cb3edd6fceeb58804cfa0b3aa8f6dc0ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:10.503303Z","signature_b64":"rAuOauLH8nLf/H6FPiCGES/Z8byiutJWwIHmmzzvbKyy39QAh2E76OsG/OBPoH2EX/PsiXW2H9fFVFSXHYdMAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0758eb97b23636c49484940e77c728096b310df0c17b773aa38cda4122e7f1a","last_reissued_at":"2026-05-20T00:02:10.502441Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:10.502441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HandelBot: Real-World Piano Playing via Fast Adaptation of Dexterous Robot Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"HandelBot adapts a simulation policy in two stages to let a dexterous robot play piano accurately after 30 minutes of real data.","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Amber Xie, Dorsa Sadigh, Haozhi Qi","submitted_at":"2026-03-12T17:56:29Z","abstract_excerpt":"Mastering dexterous manipulation with multi-fingered hands has been a grand challenge in robotics for decades. Despite its potential, the difficulty of collecting high-quality data remains a primary bottleneck for high-precision tasks. While reinforcement learning and simulation-to-real-world transfer offer a promising alternative, the transferred policies often fail for tasks demanding millimeter-scale precision, such as bimanual piano playing. In this work, we introduce HandelBot, a framework that combines a simulation policy and rapid adaptation through a two-stage pipeline. Starting from a"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Through extensive hardware experiments across five recognized songs, we demonstrate that HandelBot can successfully perform precise bimanual piano playing. Our system outperforms direct simulation deployment by a factor of 1.8x and requires only 30 minutes of physical interaction data.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a simulation-trained policy provides a sufficiently close starting point for the structured refinement stage to correct spatial misalignments to millimeter precision using only limited physical rollouts without introducing new instabilities in bimanual coordination.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HandelBot achieves precise bimanual piano playing by refining a simulation policy through lateral finger adjustments and residual RL, outperforming direct sim deployment by 1.8x with only 30 minutes of physical data across five songs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"HandelBot adapts a simulation policy in two stages to let a dexterous robot play piano accurately after 30 minutes of real data.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"21fd8c0c1f441cf68984ff2ad4d63af70cf43059fe47a8aee850d2f41c323515"},"source":{"id":"2603.12243","kind":"arxiv","version":4},"verdict":{"id":"3c5b6be6-2a2a-4f52-8aa1-a643c321fb02","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T11:45:02.148110Z","strongest_claim":"Through extensive hardware experiments across five recognized songs, we demonstrate that HandelBot can successfully perform precise bimanual piano playing. Our system outperforms direct simulation deployment by a factor of 1.8x and requires only 30 minutes of physical interaction data.","one_line_summary":"HandelBot achieves precise bimanual piano playing by refining a simulation policy through lateral finger adjustments and residual RL, outperforming direct sim deployment by 1.8x with only 30 minutes of physical data across five songs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a simulation-trained policy provides a sufficiently close starting point for the structured refinement stage to correct spatial misalignments to millimeter precision using only limited physical rollouts without introducing new instabilities in bimanual coordination.","pith_extraction_headline":"HandelBot adapts a simulation policy in two stages to let a dexterous robot play piano accurately after 30 minutes of real data."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.12243/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":2,"snapshot_sha256":"b4481a22bb3f504b786eae7b262dea5a80245b774a2be7314c6913984bd46814"},"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":"2603.12243","created_at":"2026-05-20T00:02:10.502588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.12243v4","created_at":"2026-05-20T00:02:10.502588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.12243","created_at":"2026-05-20T00:02:10.502588+00:00"},{"alias_kind":"pith_short_12","alias_value":"UB2Y5OL3ENRW","created_at":"2026-05-20T00:02:10.502588+00:00"},{"alias_kind":"pith_short_16","alias_value":"UB2Y5OL3ENRWYSKI","created_at":"2026-05-20T00:02:10.502588+00:00"},{"alias_kind":"pith_short_8","alias_value":"UB2Y5OL3","created_at":"2026-05-20T00:02:10.502588+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UB2Y5OL3ENRWYSKIJFAOO7DSQC","json":"https://pith.science/pith/UB2Y5OL3ENRWYSKIJFAOO7DSQC.json","graph_json":"https://pith.science/api/pith-number/UB2Y5OL3ENRWYSKIJFAOO7DSQC/graph.json","events_json":"https://pith.science/api/pith-number/UB2Y5OL3ENRWYSKIJFAOO7DSQC/events.json","paper":"https://pith.science/paper/UB2Y5OL3"},"agent_actions":{"view_html":"https://pith.science/pith/UB2Y5OL3ENRWYSKIJFAOO7DSQC","download_json":"https://pith.science/pith/UB2Y5OL3ENRWYSKIJFAOO7DSQC.json","view_paper":"https://pith.science/paper/UB2Y5OL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.12243&json=true","fetch_graph":"https://pith.science/api/pith-number/UB2Y5OL3ENRWYSKIJFAOO7DSQC/graph.json","fetch_events":"https://pith.science/api/pith-number/UB2Y5OL3ENRWYSKIJFAOO7DSQC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UB2Y5OL3ENRWYSKIJFAOO7DSQC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UB2Y5OL3ENRWYSKIJFAOO7DSQC/action/storage_attestation","attest_author":"https://pith.science/pith/UB2Y5OL3ENRWYSKIJFAOO7DSQC/action/author_attestation","sign_citation":"https://pith.science/pith/UB2Y5OL3ENRWYSKIJFAOO7DSQC/action/citation_signature","submit_replication":"https://pith.science/pith/UB2Y5OL3ENRWYSKIJFAOO7DSQC/action/replication_record"}},"created_at":"2026-05-20T00:02:10.502588+00:00","updated_at":"2026-05-20T00:02:10.502588+00:00"}