{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:T7FSR75PNZZXCPTOYZOTX5JHR2","short_pith_number":"pith:T7FSR75P","schema_version":"1.0","canonical_sha256":"9fcb28ffaf6e73713e6ec65d3bf5278e827d62973bd3852464d60f8a1f1885ee","source":{"kind":"arxiv","id":"2606.18953","version":1},"attestation_state":"computed","paper":{"title":"Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Heecheol Kim, Jaegul Choo, Katsushi Ikeuchi, Kinam Kim, Namiko Saito, Yasuyuki Matsushita","submitted_at":"2026-06-17T11:36:54Z","abstract_excerpt":"Vision-Language-Action (VLA) models can generalize across diverse manipulation tasks, but their imitation-learning-based policies remain brittle in precise physical interactions due to compounding execution errors; Can a reinforcement learning policy trained purely in simulation improve the robustness of real-world VLAs zero-shot? Residual RL, which learns a corrective policy on top of a frozen VLA, offers a natural framework, but existing approaches face a fundamental sim-to-real dilemma: privileged-state methods require lossy distillation for deployment; image-based methods suffer from the v"},"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":"2606.18953","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-17T11:36:54Z","cross_cats_sorted":[],"title_canon_sha256":"bf7a53723763f61da77d0994ec65eaeaccdfdd946befa5e28abc1ee953c86711","abstract_canon_sha256":"540851bfe887d5ead4548cfa1faebd04c8eb17884e2d64378e0814bbbf52010e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:52.770642Z","signature_b64":"lvOnWhUaqpisafNVSAeBzQV4XYejCqTtgSQpcH+qGia5Ffa7t7tqdnUKIgEPeYO1al3EfiwK55KN7tkCL86KCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fcb28ffaf6e73713e6ec65d3bf5278e827d62973bd3852464d60f8a1f1885ee","last_reissued_at":"2026-06-19T16:11:52.770253Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:52.770253Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Heecheol Kim, Jaegul Choo, Katsushi Ikeuchi, Kinam Kim, Namiko Saito, Yasuyuki Matsushita","submitted_at":"2026-06-17T11:36:54Z","abstract_excerpt":"Vision-Language-Action (VLA) models can generalize across diverse manipulation tasks, but their imitation-learning-based policies remain brittle in precise physical interactions due to compounding execution errors; Can a reinforcement learning policy trained purely in simulation improve the robustness of real-world VLAs zero-shot? Residual RL, which learns a corrective policy on top of a frozen VLA, offers a natural framework, but existing approaches face a fundamental sim-to-real dilemma: privileged-state methods require lossy distillation for deployment; image-based methods suffer from the v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18953","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/2606.18953/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":"2606.18953","created_at":"2026-06-19T16:11:52.770323+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18953v1","created_at":"2026-06-19T16:11:52.770323+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18953","created_at":"2026-06-19T16:11:52.770323+00:00"},{"alias_kind":"pith_short_12","alias_value":"T7FSR75PNZZX","created_at":"2026-06-19T16:11:52.770323+00:00"},{"alias_kind":"pith_short_16","alias_value":"T7FSR75PNZZXCPTO","created_at":"2026-06-19T16:11:52.770323+00:00"},{"alias_kind":"pith_short_8","alias_value":"T7FSR75P","created_at":"2026-06-19T16:11:52.770323+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/T7FSR75PNZZXCPTOYZOTX5JHR2","json":"https://pith.science/pith/T7FSR75PNZZXCPTOYZOTX5JHR2.json","graph_json":"https://pith.science/api/pith-number/T7FSR75PNZZXCPTOYZOTX5JHR2/graph.json","events_json":"https://pith.science/api/pith-number/T7FSR75PNZZXCPTOYZOTX5JHR2/events.json","paper":"https://pith.science/paper/T7FSR75P"},"agent_actions":{"view_html":"https://pith.science/pith/T7FSR75PNZZXCPTOYZOTX5JHR2","download_json":"https://pith.science/pith/T7FSR75PNZZXCPTOYZOTX5JHR2.json","view_paper":"https://pith.science/paper/T7FSR75P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18953&json=true","fetch_graph":"https://pith.science/api/pith-number/T7FSR75PNZZXCPTOYZOTX5JHR2/graph.json","fetch_events":"https://pith.science/api/pith-number/T7FSR75PNZZXCPTOYZOTX5JHR2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T7FSR75PNZZXCPTOYZOTX5JHR2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T7FSR75PNZZXCPTOYZOTX5JHR2/action/storage_attestation","attest_author":"https://pith.science/pith/T7FSR75PNZZXCPTOYZOTX5JHR2/action/author_attestation","sign_citation":"https://pith.science/pith/T7FSR75PNZZXCPTOYZOTX5JHR2/action/citation_signature","submit_replication":"https://pith.science/pith/T7FSR75PNZZXCPTOYZOTX5JHR2/action/replication_record"}},"created_at":"2026-06-19T16:11:52.770323+00:00","updated_at":"2026-06-19T16:11:52.770323+00:00"}