{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UXZ5CQN4PKFSNLOBWFJXGGNXPS","short_pith_number":"pith:UXZ5CQN4","schema_version":"1.0","canonical_sha256":"a5f3d141bc7a8b26adc1b1537319b77cb3646f3141e99c193b9c65ff6e58ee91","source":{"kind":"arxiv","id":"2303.03486","version":3},"attestation_state":"computed","paper":{"title":"Sampling-based Exploration for Reinforcement Learning of Dexterous Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Eric T. Chang, Gagan Khandate, Johnson Adams, Matei Ciocarlie, Seth Matthew Dennis, Siqi Shang, Tristan Luca Saidi, Yang Liu","submitted_at":"2023-03-06T20:34:23Z","abstract_excerpt":"In this paper, we present a novel method for achieving dexterous manipulation of complex objects, while simultaneously securing the object without the use of passive support surfaces. We posit that a key difficulty for training such policies in a Reinforcement Learning framework is the difficulty of exploring the problem state space, as the accessible regions of this space form a complex structure along manifolds of a high-dimensional space. To address this challenge, we use two versions of the non-holonomic Rapidly-Exploring Random Trees algorithm; one version is more general, but requires ex"},"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":"2303.03486","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2023-03-06T20:34:23Z","cross_cats_sorted":[],"title_canon_sha256":"6271b977ceb242acd37ce5fcab3037f2646dc9f08454c13324d52e6ec36099b7","abstract_canon_sha256":"b85d39bd353bcbfa0c1f1badee986e7564ed51f28a0e778b8245562278285760"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:45.674777Z","signature_b64":"VTsLIWEoVpnR2XucB4TzJN0oKG5qHfUGtaRi8MGgjv3HcLbuZU1wxPgDfkxbnFRfujGidk/PLxDOZHElW9JxBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a5f3d141bc7a8b26adc1b1537319b77cb3646f3141e99c193b9c65ff6e58ee91","last_reissued_at":"2026-07-05T06:12:45.674328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:45.674328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sampling-based Exploration for Reinforcement Learning of Dexterous Manipulation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Eric T. Chang, Gagan Khandate, Johnson Adams, Matei Ciocarlie, Seth Matthew Dennis, Siqi Shang, Tristan Luca Saidi, Yang Liu","submitted_at":"2023-03-06T20:34:23Z","abstract_excerpt":"In this paper, we present a novel method for achieving dexterous manipulation of complex objects, while simultaneously securing the object without the use of passive support surfaces. We posit that a key difficulty for training such policies in a Reinforcement Learning framework is the difficulty of exploring the problem state space, as the accessible regions of this space form a complex structure along manifolds of a high-dimensional space. To address this challenge, we use two versions of the non-holonomic Rapidly-Exploring Random Trees algorithm; one version is more general, but requires ex"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.03486","kind":"arxiv","version":3},"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/2303.03486/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":"2303.03486","created_at":"2026-07-05T06:12:45.674387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.03486v3","created_at":"2026-07-05T06:12:45.674387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.03486","created_at":"2026-07-05T06:12:45.674387+00:00"},{"alias_kind":"pith_short_12","alias_value":"UXZ5CQN4PKFS","created_at":"2026-07-05T06:12:45.674387+00:00"},{"alias_kind":"pith_short_16","alias_value":"UXZ5CQN4PKFSNLOB","created_at":"2026-07-05T06:12:45.674387+00:00"},{"alias_kind":"pith_short_8","alias_value":"UXZ5CQN4","created_at":"2026-07-05T06:12:45.674387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13925","citing_title":"Towards Robotic Dexterous Hand Intelligence: A Survey","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UXZ5CQN4PKFSNLOBWFJXGGNXPS","json":"https://pith.science/pith/UXZ5CQN4PKFSNLOBWFJXGGNXPS.json","graph_json":"https://pith.science/api/pith-number/UXZ5CQN4PKFSNLOBWFJXGGNXPS/graph.json","events_json":"https://pith.science/api/pith-number/UXZ5CQN4PKFSNLOBWFJXGGNXPS/events.json","paper":"https://pith.science/paper/UXZ5CQN4"},"agent_actions":{"view_html":"https://pith.science/pith/UXZ5CQN4PKFSNLOBWFJXGGNXPS","download_json":"https://pith.science/pith/UXZ5CQN4PKFSNLOBWFJXGGNXPS.json","view_paper":"https://pith.science/paper/UXZ5CQN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.03486&json=true","fetch_graph":"https://pith.science/api/pith-number/UXZ5CQN4PKFSNLOBWFJXGGNXPS/graph.json","fetch_events":"https://pith.science/api/pith-number/UXZ5CQN4PKFSNLOBWFJXGGNXPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UXZ5CQN4PKFSNLOBWFJXGGNXPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UXZ5CQN4PKFSNLOBWFJXGGNXPS/action/storage_attestation","attest_author":"https://pith.science/pith/UXZ5CQN4PKFSNLOBWFJXGGNXPS/action/author_attestation","sign_citation":"https://pith.science/pith/UXZ5CQN4PKFSNLOBWFJXGGNXPS/action/citation_signature","submit_replication":"https://pith.science/pith/UXZ5CQN4PKFSNLOBWFJXGGNXPS/action/replication_record"}},"created_at":"2026-07-05T06:12:45.674387+00:00","updated_at":"2026-07-05T06:12:45.674387+00:00"}