{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZHQMUOIPMAPG5ZKFCHFHKJUDXK","short_pith_number":"pith:ZHQMUOIP","schema_version":"1.0","canonical_sha256":"c9e0ca390f601e6ee54511ca752683ba9dc36b99292b976de633bc8419ad1176","source":{"kind":"arxiv","id":"2305.12127","version":1},"attestation_state":"computed","paper":{"title":"DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Aleksei Petrenko, Ankur Handa, Arthur Allshire, Gavriel State, Viktor Makoviychuk","submitted_at":"2023-05-20T07:25:27Z","abstract_excerpt":"In this work, we propose algorithms and methods that enable learning dexterous object manipulation using simulated one- or two-armed robots equipped with multi-fingered hand end-effectors. Using a parallel GPU-accelerated physics simulator (Isaac Gym), we implement challenging tasks for these robots, including regrasping, grasp-and-throw, and object reorientation. To solve these problems we introduce a decentralized Population-Based Training (PBT) algorithm that allows us to massively amplify the exploration capabilities of deep reinforcement learning. We find that this method significantly ou"},"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":"2305.12127","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-05-20T07:25:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"94e718b478d8a0b0c298833560daa386debd15369bc1f5101995489042236fb0","abstract_canon_sha256":"21ef43ce0e11cc23e4d00fc172817e502eedec9d7f6dc698dda952a1f684194c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:06.751044Z","signature_b64":"24R0ARDJiTyKkGgcoIkmVHQ4fQyA5QHmqbxXZQJMLDmslQcfbTyo4b4S4w9SsitTyT3U5aBwKVbR0GMM1PPoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9e0ca390f601e6ee54511ca752683ba9dc36b99292b976de633bc8419ad1176","last_reissued_at":"2026-07-05T06:12:06.750651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:06.750651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DexPBT: Scaling up Dexterous Manipulation for Hand-Arm Systems with Population Based Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Aleksei Petrenko, Ankur Handa, Arthur Allshire, Gavriel State, Viktor Makoviychuk","submitted_at":"2023-05-20T07:25:27Z","abstract_excerpt":"In this work, we propose algorithms and methods that enable learning dexterous object manipulation using simulated one- or two-armed robots equipped with multi-fingered hand end-effectors. Using a parallel GPU-accelerated physics simulator (Isaac Gym), we implement challenging tasks for these robots, including regrasping, grasp-and-throw, and object reorientation. To solve these problems we introduce a decentralized Population-Based Training (PBT) algorithm that allows us to massively amplify the exploration capabilities of deep reinforcement learning. We find that this method significantly ou"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12127","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/2305.12127/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":"2305.12127","created_at":"2026-07-05T06:12:06.750707+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.12127v1","created_at":"2026-07-05T06:12:06.750707+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12127","created_at":"2026-07-05T06:12:06.750707+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZHQMUOIPMAPG","created_at":"2026-07-05T06:12:06.750707+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZHQMUOIPMAPG5ZKF","created_at":"2026-07-05T06:12:06.750707+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZHQMUOIP","created_at":"2026-07-05T06:12:06.750707+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.04831","citing_title":"Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning","ref_index":75,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZHQMUOIPMAPG5ZKFCHFHKJUDXK","json":"https://pith.science/pith/ZHQMUOIPMAPG5ZKFCHFHKJUDXK.json","graph_json":"https://pith.science/api/pith-number/ZHQMUOIPMAPG5ZKFCHFHKJUDXK/graph.json","events_json":"https://pith.science/api/pith-number/ZHQMUOIPMAPG5ZKFCHFHKJUDXK/events.json","paper":"https://pith.science/paper/ZHQMUOIP"},"agent_actions":{"view_html":"https://pith.science/pith/ZHQMUOIPMAPG5ZKFCHFHKJUDXK","download_json":"https://pith.science/pith/ZHQMUOIPMAPG5ZKFCHFHKJUDXK.json","view_paper":"https://pith.science/paper/ZHQMUOIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.12127&json=true","fetch_graph":"https://pith.science/api/pith-number/ZHQMUOIPMAPG5ZKFCHFHKJUDXK/graph.json","fetch_events":"https://pith.science/api/pith-number/ZHQMUOIPMAPG5ZKFCHFHKJUDXK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZHQMUOIPMAPG5ZKFCHFHKJUDXK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZHQMUOIPMAPG5ZKFCHFHKJUDXK/action/storage_attestation","attest_author":"https://pith.science/pith/ZHQMUOIPMAPG5ZKFCHFHKJUDXK/action/author_attestation","sign_citation":"https://pith.science/pith/ZHQMUOIPMAPG5ZKFCHFHKJUDXK/action/citation_signature","submit_replication":"https://pith.science/pith/ZHQMUOIPMAPG5ZKFCHFHKJUDXK/action/replication_record"}},"created_at":"2026-07-05T06:12:06.750707+00:00","updated_at":"2026-07-05T06:12:06.750707+00:00"}