{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CNGKLEJOCI5BO2PZ4EPQPBFECD","short_pith_number":"pith:CNGKLEJO","schema_version":"1.0","canonical_sha256":"134ca5912e123a1769f9e11f0784a410fa17eee86ae0baae25e5bb45ab3e6e2a","source":{"kind":"arxiv","id":"2605.30957","version":1},"attestation_state":"computed","paper":{"title":"RDGen: Demonstration Generation for High-Quality Robot Learning via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Menglin Zou, Xinhai Sun, Yaojie Tu, Zhuang Li, Zijian Zhu","submitted_at":"2026-05-29T07:53:19Z","abstract_excerpt":"Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robot control. However, their performance remains fundamentally constrained by the availability of high-quality robot trajectory data. In current robot learning practice, such data are primarily collected through human teleoperation, which is labor-intensive, costly, and difficult to scale. In this paper, we propose RDGen, a sim-to-real reinforcement learning framework for generating high-quality robot demonstrations. Rather than employing reinforcement learning solely as the final control policy, RDGe"},"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":"2605.30957","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-05-29T07:53:19Z","cross_cats_sorted":[],"title_canon_sha256":"dd93cd9243df3a12224019d7e8323675a929df95385e3ab2dfe55a9ca4e01f9d","abstract_canon_sha256":"01413c31a952e27b743656f3fb43baecb96bf3bc2c22d3162dd48f0d99bfac02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:03:27.452547Z","signature_b64":"pYv0hbMasDsaYJA2RFHytJXslqOgOHccON8qVohgz7PMEHdIHvW3b8M7E0OUTBSddKc2UjgO/De1aLOIl0lPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"134ca5912e123a1769f9e11f0784a410fa17eee86ae0baae25e5bb45ab3e6e2a","last_reissued_at":"2026-06-01T01:03:27.452058Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:03:27.452058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RDGen: Demonstration Generation for High-Quality Robot Learning via Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Menglin Zou, Xinhai Sun, Yaojie Tu, Zhuang Li, Zijian Zhu","submitted_at":"2026-05-29T07:53:19Z","abstract_excerpt":"Vision-Language-Action (VLA) models have emerged as a promising paradigm for general-purpose robot control. However, their performance remains fundamentally constrained by the availability of high-quality robot trajectory data. In current robot learning practice, such data are primarily collected through human teleoperation, which is labor-intensive, costly, and difficult to scale. In this paper, we propose RDGen, a sim-to-real reinforcement learning framework for generating high-quality robot demonstrations. Rather than employing reinforcement learning solely as the final control policy, RDGe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30957","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/2605.30957/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":"2605.30957","created_at":"2026-06-01T01:03:27.452130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30957v1","created_at":"2026-06-01T01:03:27.452130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30957","created_at":"2026-06-01T01:03:27.452130+00:00"},{"alias_kind":"pith_short_12","alias_value":"CNGKLEJOCI5B","created_at":"2026-06-01T01:03:27.452130+00:00"},{"alias_kind":"pith_short_16","alias_value":"CNGKLEJOCI5BO2PZ","created_at":"2026-06-01T01:03:27.452130+00:00"},{"alias_kind":"pith_short_8","alias_value":"CNGKLEJO","created_at":"2026-06-01T01:03:27.452130+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/CNGKLEJOCI5BO2PZ4EPQPBFECD","json":"https://pith.science/pith/CNGKLEJOCI5BO2PZ4EPQPBFECD.json","graph_json":"https://pith.science/api/pith-number/CNGKLEJOCI5BO2PZ4EPQPBFECD/graph.json","events_json":"https://pith.science/api/pith-number/CNGKLEJOCI5BO2PZ4EPQPBFECD/events.json","paper":"https://pith.science/paper/CNGKLEJO"},"agent_actions":{"view_html":"https://pith.science/pith/CNGKLEJOCI5BO2PZ4EPQPBFECD","download_json":"https://pith.science/pith/CNGKLEJOCI5BO2PZ4EPQPBFECD.json","view_paper":"https://pith.science/paper/CNGKLEJO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30957&json=true","fetch_graph":"https://pith.science/api/pith-number/CNGKLEJOCI5BO2PZ4EPQPBFECD/graph.json","fetch_events":"https://pith.science/api/pith-number/CNGKLEJOCI5BO2PZ4EPQPBFECD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CNGKLEJOCI5BO2PZ4EPQPBFECD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CNGKLEJOCI5BO2PZ4EPQPBFECD/action/storage_attestation","attest_author":"https://pith.science/pith/CNGKLEJOCI5BO2PZ4EPQPBFECD/action/author_attestation","sign_citation":"https://pith.science/pith/CNGKLEJOCI5BO2PZ4EPQPBFECD/action/citation_signature","submit_replication":"https://pith.science/pith/CNGKLEJOCI5BO2PZ4EPQPBFECD/action/replication_record"}},"created_at":"2026-06-01T01:03:27.452130+00:00","updated_at":"2026-06-01T01:03:27.452130+00:00"}