{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4KPO2WXPHX2WS6GQR2BKYTWD7C","short_pith_number":"pith:4KPO2WXP","schema_version":"1.0","canonical_sha256":"e29eed5aef3df56978d08e82ac4ec3f88bc700fba17e16f34ad2529d5939142d","source":{"kind":"arxiv","id":"2607.09866","version":1},"attestation_state":"computed","paper":{"title":"Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Di Hu, Jianlong Fu, Jian Tang, Jifan Li, Ji-Rong Wen, Pei Ren, Qingyang Gao, Wenbo Yu, Wenke Xia, Yinuo Zhao, Yixue Zhang, Yizhuo Zhang, Zhengping Che","submitted_at":"2026-07-10T18:01:05Z","abstract_excerpt":"Offline-to-online reinforcement learning is promising for generalizable robotic manipulation, yet its full-stack complexity obscures reproduction and diagnosis. Within such systems, value estimation plays a central role in prioritizing heterogeneous data for policy improvement. Despite its importance, the central question remains underexplored: how value-function reliability shapes policy optimization in offline-to-online reinforcement learning. To answer this question, we propose Robo-ValueRL, a unified framework that enables reliable value estimation and systematically traces its downstream "},"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":"2607.09866","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-10T18:01:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9b089a42c7616fdac66e21da340a4641d9a4bca14e8351d2ee328d89ef4907cf","abstract_canon_sha256":"d5147f4fc7fbc5753b5346411ab2681b9cb1e5ab3399e89321c9e827e9602715"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:40.557929Z","signature_b64":"hN8l3oudsrdqRptPXj+YMOfVu25dmtMgWlElg+CA4OXv5Nl7WYLGjEFuShkhDYu5WbTMgUvdauiFBNd2skdgCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e29eed5aef3df56978d08e82ac4ec3f88bc700fba17e16f34ad2529d5939142d","last_reissued_at":"2026-07-14T00:18:40.557090Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:40.557090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Di Hu, Jianlong Fu, Jian Tang, Jifan Li, Ji-Rong Wen, Pei Ren, Qingyang Gao, Wenbo Yu, Wenke Xia, Yinuo Zhao, Yixue Zhang, Yizhuo Zhang, Zhengping Che","submitted_at":"2026-07-10T18:01:05Z","abstract_excerpt":"Offline-to-online reinforcement learning is promising for generalizable robotic manipulation, yet its full-stack complexity obscures reproduction and diagnosis. Within such systems, value estimation plays a central role in prioritizing heterogeneous data for policy improvement. Despite its importance, the central question remains underexplored: how value-function reliability shapes policy optimization in offline-to-online reinforcement learning. To answer this question, we propose Robo-ValueRL, a unified framework that enables reliable value estimation and systematically traces its downstream "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09866","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/2607.09866/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":"2607.09866","created_at":"2026-07-14T00:18:40.557533+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09866v1","created_at":"2026-07-14T00:18:40.557533+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09866","created_at":"2026-07-14T00:18:40.557533+00:00"},{"alias_kind":"pith_short_12","alias_value":"4KPO2WXPHX2W","created_at":"2026-07-14T00:18:40.557533+00:00"},{"alias_kind":"pith_short_16","alias_value":"4KPO2WXPHX2WS6GQ","created_at":"2026-07-14T00:18:40.557533+00:00"},{"alias_kind":"pith_short_8","alias_value":"4KPO2WXP","created_at":"2026-07-14T00:18:40.557533+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/4KPO2WXPHX2WS6GQR2BKYTWD7C","json":"https://pith.science/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C.json","graph_json":"https://pith.science/api/pith-number/4KPO2WXPHX2WS6GQR2BKYTWD7C/graph.json","events_json":"https://pith.science/api/pith-number/4KPO2WXPHX2WS6GQR2BKYTWD7C/events.json","paper":"https://pith.science/paper/4KPO2WXP"},"agent_actions":{"view_html":"https://pith.science/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C","download_json":"https://pith.science/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C.json","view_paper":"https://pith.science/paper/4KPO2WXP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09866&json=true","fetch_graph":"https://pith.science/api/pith-number/4KPO2WXPHX2WS6GQR2BKYTWD7C/graph.json","fetch_events":"https://pith.science/api/pith-number/4KPO2WXPHX2WS6GQR2BKYTWD7C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C/action/storage_attestation","attest_author":"https://pith.science/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C/action/author_attestation","sign_citation":"https://pith.science/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C/action/citation_signature","submit_replication":"https://pith.science/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C/action/replication_record"}},"created_at":"2026-07-14T00:18:40.557533+00:00","updated_at":"2026-07-14T00:18:40.557533+00:00"}