{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2LJSLGYN4M2QF2DIBMLB5LFKE7","short_pith_number":"pith:2LJSLGYN","schema_version":"1.0","canonical_sha256":"d2d3259b0de33502e8680b161eacaa27e28810dfc2555e8b81db6060cbb0fed7","source":{"kind":"arxiv","id":"2602.12628","version":4},"attestation_state":"computed","paper":{"title":"Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chao Yu, Feng Gao, Hongzhi Zang, Jiakai Zhou, Kang Chen, Liangzhi Shi, Shuaihang Chen, Tonghe Zhang, Weinan Zhang, Yinuo Chen, Yu Wang","submitted_at":"2026-02-13T05:15:50Z","abstract_excerpt":"Simulation offers a scalable and low-cost way to enrich vision-language-action (VLA) training, reducing reliance on expensive real-robot demonstrations. However, most sim-real co-training methods rely on supervised fine-tuning (SFT), which treats simulation as a static source of demonstrations and does not exploit large-scale closed-loop interaction. Consequently, real-world gains and generalization are often limited. In this paper, we propose an RL-based sim-real Co-training (RL-Co) framework that leverages interactive simulation while preserving real-world capabilities. Our method follows a "},"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":"2602.12628","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-13T05:15:50Z","cross_cats_sorted":[],"title_canon_sha256":"6ed32f2e7d030247bc226870f80d602a4f4bd24dd1b7bd93e48facfe8c2a2b94","abstract_canon_sha256":"ce0bcdf0b2772b722300ed10a65e8588eaf4f6b0d110cc6237e62bbbd6dcb866"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:20.219100Z","signature_b64":"HwVQ83woMnYyvV8kyJgoah6fnc1rcsUAc/nSnBkpON7DUIqIMYEtrn814SGSlVFrwSMA4mWCYpfAlLxbWZjsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2d3259b0de33502e8680b161eacaa27e28810dfc2555e8b81db6060cbb0fed7","last_reissued_at":"2026-06-05T01:15:20.218542Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:20.218542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chao Yu, Feng Gao, Hongzhi Zang, Jiakai Zhou, Kang Chen, Liangzhi Shi, Shuaihang Chen, Tonghe Zhang, Weinan Zhang, Yinuo Chen, Yu Wang","submitted_at":"2026-02-13T05:15:50Z","abstract_excerpt":"Simulation offers a scalable and low-cost way to enrich vision-language-action (VLA) training, reducing reliance on expensive real-robot demonstrations. However, most sim-real co-training methods rely on supervised fine-tuning (SFT), which treats simulation as a static source of demonstrations and does not exploit large-scale closed-loop interaction. Consequently, real-world gains and generalization are often limited. In this paper, we propose an RL-based sim-real Co-training (RL-Co) framework that leverages interactive simulation while preserving real-world capabilities. Our method follows a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12628","kind":"arxiv","version":4},"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/2602.12628/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":"2602.12628","created_at":"2026-06-05T01:15:20.218600+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.12628v4","created_at":"2026-06-05T01:15:20.218600+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12628","created_at":"2026-06-05T01:15:20.218600+00:00"},{"alias_kind":"pith_short_12","alias_value":"2LJSLGYN4M2Q","created_at":"2026-06-05T01:15:20.218600+00:00"},{"alias_kind":"pith_short_16","alias_value":"2LJSLGYN4M2QF2DI","created_at":"2026-06-05T01:15:20.218600+00:00"},{"alias_kind":"pith_short_8","alias_value":"2LJSLGYN","created_at":"2026-06-05T01:15:20.218600+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/2LJSLGYN4M2QF2DIBMLB5LFKE7","json":"https://pith.science/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7.json","graph_json":"https://pith.science/api/pith-number/2LJSLGYN4M2QF2DIBMLB5LFKE7/graph.json","events_json":"https://pith.science/api/pith-number/2LJSLGYN4M2QF2DIBMLB5LFKE7/events.json","paper":"https://pith.science/paper/2LJSLGYN"},"agent_actions":{"view_html":"https://pith.science/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7","download_json":"https://pith.science/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7.json","view_paper":"https://pith.science/paper/2LJSLGYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.12628&json=true","fetch_graph":"https://pith.science/api/pith-number/2LJSLGYN4M2QF2DIBMLB5LFKE7/graph.json","fetch_events":"https://pith.science/api/pith-number/2LJSLGYN4M2QF2DIBMLB5LFKE7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7/action/storage_attestation","attest_author":"https://pith.science/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7/action/author_attestation","sign_citation":"https://pith.science/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7/action/citation_signature","submit_replication":"https://pith.science/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7/action/replication_record"}},"created_at":"2026-06-05T01:15:20.218600+00:00","updated_at":"2026-06-05T01:15:20.218600+00:00"}