{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FULZGDGU5G4NFXOTCXX32ICZ66","short_pith_number":"pith:FULZGDGU","schema_version":"1.0","canonical_sha256":"2d17930cd4e9b8d2ddd315efbd2059f7a4a87a100d8311e8e6254926287f3d06","source":{"kind":"arxiv","id":"2607.02431","version":1},"attestation_state":"computed","paper":{"title":"WorldSample: Closed-loop Real-robot RL with World Modelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bofang Jia, Le Xu, Xinyang Song, Yuquan Xue, Zeyi Liu, Zhengyi Gu, Zhenyu Wu, Ziwei Wang","submitted_at":"2026-07-02T17:00:37Z","abstract_excerpt":"Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing robots to improve through trial-and-error interaction beyond the states observed in demonstrations. However, deploying RL on real robots remains constrained by high interaction costs, since each physical rollout is costly and reflects only one realized action-outcome path. To address this challenge, we propose WorldSample, a physically grounded data augmentation framework for real-robot RL that closes a real-synthetic loop between physical rollouts, world-model generation, and "},"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":"2607.02431","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-02T17:00:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3c328276ed9daa436bce144e644ff69516abc3d17c610a9b420e0b6d53d013ab","abstract_canon_sha256":"6c3fb45acff8aaf3ea6a2ae5f457cf3fbd5aeea09ae31e7e980c65ff0e7b52fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:59.073634Z","signature_b64":"m4945zEM9eDdLZFHMCkc8EGwsW0w0CH+oc6kBCy7/DuysVhA5bkpOCz9juxXr3fF1J1742OlgilW+PRsk2MQCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d17930cd4e9b8d2ddd315efbd2059f7a4a87a100d8311e8e6254926287f3d06","last_reissued_at":"2026-07-03T01:17:59.073232Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:59.073232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WorldSample: Closed-loop Real-robot RL with World Modelling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Bofang Jia, Le Xu, Xinyang Song, Yuquan Xue, Zeyi Liu, Zhengyi Gu, Zhenyu Wu, Ziwei Wang","submitted_at":"2026-07-02T17:00:37Z","abstract_excerpt":"Reinforcement learning (RL) can overcome the demonstration-coverage limitation of imitation learning (IL) by allowing robots to improve through trial-and-error interaction beyond the states observed in demonstrations. However, deploying RL on real robots remains constrained by high interaction costs, since each physical rollout is costly and reflects only one realized action-outcome path. To address this challenge, we propose WorldSample, a physically grounded data augmentation framework for real-robot RL that closes a real-synthetic loop between physical rollouts, world-model generation, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.02431","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/2607.02431/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":"2607.02431","created_at":"2026-07-03T01:17:59.073288+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.02431v1","created_at":"2026-07-03T01:17:59.073288+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.02431","created_at":"2026-07-03T01:17:59.073288+00:00"},{"alias_kind":"pith_short_12","alias_value":"FULZGDGU5G4N","created_at":"2026-07-03T01:17:59.073288+00:00"},{"alias_kind":"pith_short_16","alias_value":"FULZGDGU5G4NFXOT","created_at":"2026-07-03T01:17:59.073288+00:00"},{"alias_kind":"pith_short_8","alias_value":"FULZGDGU","created_at":"2026-07-03T01:17:59.073288+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/FULZGDGU5G4NFXOTCXX32ICZ66","json":"https://pith.science/pith/FULZGDGU5G4NFXOTCXX32ICZ66.json","graph_json":"https://pith.science/api/pith-number/FULZGDGU5G4NFXOTCXX32ICZ66/graph.json","events_json":"https://pith.science/api/pith-number/FULZGDGU5G4NFXOTCXX32ICZ66/events.json","paper":"https://pith.science/paper/FULZGDGU"},"agent_actions":{"view_html":"https://pith.science/pith/FULZGDGU5G4NFXOTCXX32ICZ66","download_json":"https://pith.science/pith/FULZGDGU5G4NFXOTCXX32ICZ66.json","view_paper":"https://pith.science/paper/FULZGDGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.02431&json=true","fetch_graph":"https://pith.science/api/pith-number/FULZGDGU5G4NFXOTCXX32ICZ66/graph.json","fetch_events":"https://pith.science/api/pith-number/FULZGDGU5G4NFXOTCXX32ICZ66/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FULZGDGU5G4NFXOTCXX32ICZ66/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FULZGDGU5G4NFXOTCXX32ICZ66/action/storage_attestation","attest_author":"https://pith.science/pith/FULZGDGU5G4NFXOTCXX32ICZ66/action/author_attestation","sign_citation":"https://pith.science/pith/FULZGDGU5G4NFXOTCXX32ICZ66/action/citation_signature","submit_replication":"https://pith.science/pith/FULZGDGU5G4NFXOTCXX32ICZ66/action/replication_record"}},"created_at":"2026-07-03T01:17:59.073288+00:00","updated_at":"2026-07-03T01:17:59.073288+00:00"}