{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:WLWDD4UDCMJD76EBSHSK5A5SM7","short_pith_number":"pith:WLWDD4UD","schema_version":"1.0","canonical_sha256":"b2ec31f28313123ff88191e4ae83b267faf879d66d21fa50a8e4e8f621d407d7","source":{"kind":"arxiv","id":"2112.04893","version":1},"attestation_state":"computed","paper":{"title":"Real-World Dexterous Object Manipulation based Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Jilong Wang, Qingfeng Yao, Shuyu Yang","submitted_at":"2021-11-22T02:48:05Z","abstract_excerpt":"Deep reinforcement learning has shown its advantages in real-time decision-making based on the state of the agent. In this stage, we solved the task of using a real robot to manipulate the cube to a given trajectory. The task is broken down into different procedures and we propose a hierarchical structure, the high-level deep reinforcement learning model selects appropriate contact positions and the low-level control module performs the position control under the corresponding trajectory. Our framework reduces the disadvantage of low sample efficiency of deep reinforcement learning and lacking"},"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":"2112.04893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2021-11-22T02:48:05Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"404ff905cc839e4ef7ba4cbae269349cb6ccde404caa1861bbae2efb7780b18b","abstract_canon_sha256":"30fbe339204f8e21b6f230ef7caa331f461098b062236467134f8761f7ac74ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:39:26.747271Z","signature_b64":"X9FyqW7lXo08ceuDsjacLcT0cDIcSs4Zbj6O+9CtepMYw76CE+8tHVkiw+8kKy2qjCgQP9gZuFP2Z5KIg0WQDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2ec31f28313123ff88191e4ae83b267faf879d66d21fa50a8e4e8f621d407d7","last_reissued_at":"2026-07-05T03:39:26.746832Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:39:26.746832Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Real-World Dexterous Object Manipulation based Deep Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.RO","authors_text":"Jilong Wang, Qingfeng Yao, Shuyu Yang","submitted_at":"2021-11-22T02:48:05Z","abstract_excerpt":"Deep reinforcement learning has shown its advantages in real-time decision-making based on the state of the agent. In this stage, we solved the task of using a real robot to manipulate the cube to a given trajectory. The task is broken down into different procedures and we propose a hierarchical structure, the high-level deep reinforcement learning model selects appropriate contact positions and the low-level control module performs the position control under the corresponding trajectory. Our framework reduces the disadvantage of low sample efficiency of deep reinforcement learning and lacking"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.04893","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/2112.04893/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":"2112.04893","created_at":"2026-07-05T03:39:26.746902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.04893v1","created_at":"2026-07-05T03:39:26.746902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.04893","created_at":"2026-07-05T03:39:26.746902+00:00"},{"alias_kind":"pith_short_12","alias_value":"WLWDD4UDCMJD","created_at":"2026-07-05T03:39:26.746902+00:00"},{"alias_kind":"pith_short_16","alias_value":"WLWDD4UDCMJD76EB","created_at":"2026-07-05T03:39:26.746902+00:00"},{"alias_kind":"pith_short_8","alias_value":"WLWDD4UD","created_at":"2026-07-05T03:39:26.746902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WLWDD4UDCMJD76EBSHSK5A5SM7","json":"https://pith.science/pith/WLWDD4UDCMJD76EBSHSK5A5SM7.json","graph_json":"https://pith.science/api/pith-number/WLWDD4UDCMJD76EBSHSK5A5SM7/graph.json","events_json":"https://pith.science/api/pith-number/WLWDD4UDCMJD76EBSHSK5A5SM7/events.json","paper":"https://pith.science/paper/WLWDD4UD"},"agent_actions":{"view_html":"https://pith.science/pith/WLWDD4UDCMJD76EBSHSK5A5SM7","download_json":"https://pith.science/pith/WLWDD4UDCMJD76EBSHSK5A5SM7.json","view_paper":"https://pith.science/paper/WLWDD4UD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.04893&json=true","fetch_graph":"https://pith.science/api/pith-number/WLWDD4UDCMJD76EBSHSK5A5SM7/graph.json","fetch_events":"https://pith.science/api/pith-number/WLWDD4UDCMJD76EBSHSK5A5SM7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WLWDD4UDCMJD76EBSHSK5A5SM7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WLWDD4UDCMJD76EBSHSK5A5SM7/action/storage_attestation","attest_author":"https://pith.science/pith/WLWDD4UDCMJD76EBSHSK5A5SM7/action/author_attestation","sign_citation":"https://pith.science/pith/WLWDD4UDCMJD76EBSHSK5A5SM7/action/citation_signature","submit_replication":"https://pith.science/pith/WLWDD4UDCMJD76EBSHSK5A5SM7/action/replication_record"}},"created_at":"2026-07-05T03:39:26.746902+00:00","updated_at":"2026-07-05T03:39:26.746902+00:00"}