{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4AULGR7O3LBENVSEM7Y5KREZKV","short_pith_number":"pith:4AULGR7O","schema_version":"1.0","canonical_sha256":"e028b347eedac246d64467f1d5449955564fc54710dbfcba3590b16e2e6fa6de","source":{"kind":"arxiv","id":"2501.05439","version":1},"attestation_state":"computed","paper":{"title":"From Simple to Complex Skills: The Case of In-Hand Object Reorientation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Brent Yi, Haozhi Qi, Jitendra Malik, Mike Lambeta, Roberto Calandra, Yi Ma","submitted_at":"2025-01-09T18:49:39Z","abstract_excerpt":"Learning policies in simulation and transferring them to the real world has become a promising approach in dexterous manipulation. However, bridging the sim-to-real gap for each new task requires substantial human effort, such as careful reward engineering, hyperparameter tuning, and system identification. In this work, we present a system that leverages low-level skills to address these challenges for more complex tasks. Specifically, we introduce a hierarchical policy for in-hand object reorientation based on previously acquired rotation skills. This hierarchical policy learns to select whic"},"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":"2501.05439","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2025-01-09T18:49:39Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7cd6e2fb1371b69c36bb7af64e519a19746ae023118c34fe5e01ffb458675b8d","abstract_canon_sha256":"44343ea17c2887494fa6fc8b32f0f1780b6275a843ba32d130be5cf10a07d0f4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:09.938298Z","signature_b64":"VNvTzqkU+9m85jYRMdjEDYh2IK/bDpFQMFUjr9nZMarCHpsif9+mEBolmiDDuJ2T8ThN8KBOqxIj5+UrDmVlBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e028b347eedac246d64467f1d5449955564fc54710dbfcba3590b16e2e6fa6de","last_reissued_at":"2026-07-05T09:59:09.937807Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:09.937807Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Simple to Complex Skills: The Case of In-Hand Object Reorientation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Brent Yi, Haozhi Qi, Jitendra Malik, Mike Lambeta, Roberto Calandra, Yi Ma","submitted_at":"2025-01-09T18:49:39Z","abstract_excerpt":"Learning policies in simulation and transferring them to the real world has become a promising approach in dexterous manipulation. However, bridging the sim-to-real gap for each new task requires substantial human effort, such as careful reward engineering, hyperparameter tuning, and system identification. In this work, we present a system that leverages low-level skills to address these challenges for more complex tasks. Specifically, we introduce a hierarchical policy for in-hand object reorientation based on previously acquired rotation skills. This hierarchical policy learns to select whic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.05439","kind":"arxiv","version":1},"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/2501.05439/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":"2501.05439","created_at":"2026-07-05T09:59:09.937867+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.05439v1","created_at":"2026-07-05T09:59:09.937867+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.05439","created_at":"2026-07-05T09:59:09.937867+00:00"},{"alias_kind":"pith_short_12","alias_value":"4AULGR7O3LBE","created_at":"2026-07-05T09:59:09.937867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4AULGR7O3LBENVSE","created_at":"2026-07-05T09:59:09.937867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4AULGR7O","created_at":"2026-07-05T09:59:09.937867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.00338","citing_title":"Scalable Option Learning in High-Throughput Environments","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08508","citing_title":"Sumo: Dynamic and Generalizable Whole-Body Loco-Manipulation","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4AULGR7O3LBENVSEM7Y5KREZKV","json":"https://pith.science/pith/4AULGR7O3LBENVSEM7Y5KREZKV.json","graph_json":"https://pith.science/api/pith-number/4AULGR7O3LBENVSEM7Y5KREZKV/graph.json","events_json":"https://pith.science/api/pith-number/4AULGR7O3LBENVSEM7Y5KREZKV/events.json","paper":"https://pith.science/paper/4AULGR7O"},"agent_actions":{"view_html":"https://pith.science/pith/4AULGR7O3LBENVSEM7Y5KREZKV","download_json":"https://pith.science/pith/4AULGR7O3LBENVSEM7Y5KREZKV.json","view_paper":"https://pith.science/paper/4AULGR7O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.05439&json=true","fetch_graph":"https://pith.science/api/pith-number/4AULGR7O3LBENVSEM7Y5KREZKV/graph.json","fetch_events":"https://pith.science/api/pith-number/4AULGR7O3LBENVSEM7Y5KREZKV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4AULGR7O3LBENVSEM7Y5KREZKV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4AULGR7O3LBENVSEM7Y5KREZKV/action/storage_attestation","attest_author":"https://pith.science/pith/4AULGR7O3LBENVSEM7Y5KREZKV/action/author_attestation","sign_citation":"https://pith.science/pith/4AULGR7O3LBENVSEM7Y5KREZKV/action/citation_signature","submit_replication":"https://pith.science/pith/4AULGR7O3LBENVSEM7Y5KREZKV/action/replication_record"}},"created_at":"2026-07-05T09:59:09.937867+00:00","updated_at":"2026-07-05T09:59:09.937867+00:00"}