{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2LJSLGYN4M2QF2DIBMLB5LFKE7","short_pith_number":"pith:2LJSLGYN","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"},"canonical_sha256":"d2d3259b0de33502e8680b161eacaa27e28810dfc2555e8b81db6060cbb0fed7","source":{"kind":"arxiv","id":"2602.12628","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.12628","created_at":"2026-06-05T01:15:20Z"},{"alias_kind":"arxiv_version","alias_value":"2602.12628v4","created_at":"2026-06-05T01:15:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12628","created_at":"2026-06-05T01:15:20Z"},{"alias_kind":"pith_short_12","alias_value":"2LJSLGYN4M2Q","created_at":"2026-06-05T01:15:20Z"},{"alias_kind":"pith_short_16","alias_value":"2LJSLGYN4M2QF2DI","created_at":"2026-06-05T01:15:20Z"},{"alias_kind":"pith_short_8","alias_value":"2LJSLGYN","created_at":"2026-06-05T01:15:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2LJSLGYN4M2QF2DIBMLB5LFKE7","target":"record","payload":{"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"},"canonical_sha256":"d2d3259b0de33502e8680b161eacaa27e28810dfc2555e8b81db6060cbb0fed7","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"},"source_kind":"arxiv","source_id":"2602.12628","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uMGX1qup6oS1ce1DekseM/X77cLoV0fqowb+GHqHfasFFbGbTD1RenzypPhDSLTnhgVnomV8Mntmb5r6R5bMBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:10:50.282068Z"},"content_sha256":"1925fcfd0132db3a884acfceb0f7e93e349f5707d22e9767fee484e100aacc99","schema_version":"1.0","event_id":"sha256:1925fcfd0132db3a884acfceb0f7e93e349f5707d22e9767fee484e100aacc99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2LJSLGYN4M2QF2DIBMLB5LFKE7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-05T01:15:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QK/He/O+l+t33DLdPub+NAxTh16Fp5ipqe7yyy8gDzpy7a+/WzdditZxjhmzJeeuRE6WGT4zSxI37BizmSFqBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T14:10:50.282669Z"},"content_sha256":"d62cf218615f791dad6c31867f008f5d57fe85fef182d59dd631f3726d04466a","schema_version":"1.0","event_id":"sha256:d62cf218615f791dad6c31867f008f5d57fe85fef182d59dd631f3726d04466a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7/bundle.json","state_url":"https://pith.science/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-07T14:10:50Z","links":{"resolver":"https://pith.science/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7","bundle":"https://pith.science/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7/bundle.json","state":"https://pith.science/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2LJSLGYN4M2QF2DIBMLB5LFKE7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2LJSLGYN4M2QF2DIBMLB5LFKE7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"ce0bcdf0b2772b722300ed10a65e8588eaf4f6b0d110cc6237e62bbbd6dcb866","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-13T05:15:50Z","title_canon_sha256":"6ed32f2e7d030247bc226870f80d602a4f4bd24dd1b7bd93e48facfe8c2a2b94"},"schema_version":"1.0","source":{"id":"2602.12628","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.12628","created_at":"2026-06-05T01:15:20Z"},{"alias_kind":"arxiv_version","alias_value":"2602.12628v4","created_at":"2026-06-05T01:15:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.12628","created_at":"2026-06-05T01:15:20Z"},{"alias_kind":"pith_short_12","alias_value":"2LJSLGYN4M2Q","created_at":"2026-06-05T01:15:20Z"},{"alias_kind":"pith_short_16","alias_value":"2LJSLGYN4M2QF2DI","created_at":"2026-06-05T01:15:20Z"},{"alias_kind":"pith_short_8","alias_value":"2LJSLGYN","created_at":"2026-06-05T01:15:20Z"}],"graph_snapshots":[{"event_id":"sha256:d62cf218615f791dad6c31867f008f5d57fe85fef182d59dd631f3726d04466a","target":"graph","created_at":"2026-06-05T01:15:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2602.12628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Chao Yu, Feng Gao, Hongzhi Zang, Jiakai Zhou, Kang Chen, Liangzhi Shi, Shuaihang Chen, Tonghe Zhang, Weinan Zhang, Yinuo Chen, Yu Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-13T05:15:50Z","title":"Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.12628","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1925fcfd0132db3a884acfceb0f7e93e349f5707d22e9767fee484e100aacc99","target":"record","created_at":"2026-06-05T01:15:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"ce0bcdf0b2772b722300ed10a65e8588eaf4f6b0d110cc6237e62bbbd6dcb866","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-02-13T05:15:50Z","title_canon_sha256":"6ed32f2e7d030247bc226870f80d602a4f4bd24dd1b7bd93e48facfe8c2a2b94"},"schema_version":"1.0","source":{"id":"2602.12628","kind":"arxiv","version":4}},"canonical_sha256":"d2d3259b0de33502e8680b161eacaa27e28810dfc2555e8b81db6060cbb0fed7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2d3259b0de33502e8680b161eacaa27e28810dfc2555e8b81db6060cbb0fed7","first_computed_at":"2026-06-05T01:15:20.218542Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-05T01:15:20.218542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HwVQ83woMnYyvV8kyJgoah6fnc1rcsUAc/nSnBkpON7DUIqIMYEtrn814SGSlVFrwSMA4mWCYpfAlLxbWZjsBQ==","signature_status":"signed_v1","signed_at":"2026-06-05T01:15:20.219100Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.12628","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1925fcfd0132db3a884acfceb0f7e93e349f5707d22e9767fee484e100aacc99","sha256:d62cf218615f791dad6c31867f008f5d57fe85fef182d59dd631f3726d04466a"],"state_sha256":"f06dc091bf80f07888680d44c344fcea4620ad915f35b1907c461291f910b636"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KBz/kUNtwFv+VNCCrd+s6DV0zmRZOW8FvjMw8W8PGAHSNZc1OKHN32lCM88kb0TpKXiUjokGQd4G6ppFPzWoAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T14:10:50.285947Z","bundle_sha256":"09f5cde2e37e55ca549e69320cfe7f018140acfab2ec84e26e1f1b54b4b7dc4f"}}