{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:4KPO2WXPHX2WS6GQR2BKYTWD7C","short_pith_number":"pith:4KPO2WXP","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"},"canonical_sha256":"e29eed5aef3df56978d08e82ac4ec3f88bc700fba17e16f34ad2529d5939142d","source":{"kind":"arxiv","id":"2607.09866","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09866","created_at":"2026-07-14T00:18:40Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09866v1","created_at":"2026-07-14T00:18:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09866","created_at":"2026-07-14T00:18:40Z"},{"alias_kind":"pith_short_12","alias_value":"4KPO2WXPHX2W","created_at":"2026-07-14T00:18:40Z"},{"alias_kind":"pith_short_16","alias_value":"4KPO2WXPHX2WS6GQ","created_at":"2026-07-14T00:18:40Z"},{"alias_kind":"pith_short_8","alias_value":"4KPO2WXP","created_at":"2026-07-14T00:18:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:4KPO2WXPHX2WS6GQR2BKYTWD7C","target":"record","payload":{"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"},"canonical_sha256":"e29eed5aef3df56978d08e82ac4ec3f88bc700fba17e16f34ad2529d5939142d","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"},"source_kind":"arxiv","source_id":"2607.09866","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T00:18:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HRzXbgK1M14mgZku212UaszRnqgnmwM+iULCUePn88EF9Mtgmr6ZdiPCWAe/6CgtbuVDL5m8M5RMDPflw+DgCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T02:00:26.542072Z"},"content_sha256":"61fb72c9cf8bf6209dc4f034935f0f9bff0279b110ffed28a5e5cc9938d3e639","schema_version":"1.0","event_id":"sha256:61fb72c9cf8bf6209dc4f034935f0f9bff0279b110ffed28a5e5cc9938d3e639"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:4KPO2WXPHX2WS6GQR2BKYTWD7C","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-14T00:18:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8VEBeBgIuYG68Fw9mNbaBlh4+Ewfpad35KTcl/V4iUD3IriKymJi6aqnuET7D13Z9qo15UwlmPVePhGzKrBVBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T02:00:26.542587Z"},"content_sha256":"1006d8f7bca7280fd14a8aeb003c357bfd91b9480069920901064ada005c713a","schema_version":"1.0","event_id":"sha256:1006d8f7bca7280fd14a8aeb003c357bfd91b9480069920901064ada005c713a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C/bundle.json","state_url":"https://pith.science/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C/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":"2026-08-03T02:00:26Z","links":{"resolver":"https://pith.science/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C","bundle":"https://pith.science/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C/bundle.json","state":"https://pith.science/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4KPO2WXPHX2WS6GQR2BKYTWD7C/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4KPO2WXPHX2WS6GQR2BKYTWD7C","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":"d5147f4fc7fbc5753b5346411ab2681b9cb1e5ab3399e89321c9e827e9602715","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-10T18:01:05Z","title_canon_sha256":"9b089a42c7616fdac66e21da340a4641d9a4bca14e8351d2ee328d89ef4907cf"},"schema_version":"1.0","source":{"id":"2607.09866","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.09866","created_at":"2026-07-14T00:18:40Z"},{"alias_kind":"arxiv_version","alias_value":"2607.09866v1","created_at":"2026-07-14T00:18:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09866","created_at":"2026-07-14T00:18:40Z"},{"alias_kind":"pith_short_12","alias_value":"4KPO2WXPHX2W","created_at":"2026-07-14T00:18:40Z"},{"alias_kind":"pith_short_16","alias_value":"4KPO2WXPHX2WS6GQ","created_at":"2026-07-14T00:18:40Z"},{"alias_kind":"pith_short_8","alias_value":"4KPO2WXP","created_at":"2026-07-14T00:18:40Z"}],"graph_snapshots":[{"event_id":"sha256:1006d8f7bca7280fd14a8aeb003c357bfd91b9480069920901064ada005c713a","target":"graph","created_at":"2026-07-14T00:18:40Z","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/2607.09866/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","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","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-10T18:01:05Z","title":"Robo-ValueRL: Reliable Value Estimation for Offline-to-Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09866","kind":"arxiv","version":1},"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":"sha256:61fb72c9cf8bf6209dc4f034935f0f9bff0279b110ffed28a5e5cc9938d3e639","target":"record","created_at":"2026-07-14T00:18:40Z","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":"d5147f4fc7fbc5753b5346411ab2681b9cb1e5ab3399e89321c9e827e9602715","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-07-10T18:01:05Z","title_canon_sha256":"9b089a42c7616fdac66e21da340a4641d9a4bca14e8351d2ee328d89ef4907cf"},"schema_version":"1.0","source":{"id":"2607.09866","kind":"arxiv","version":1}},"canonical_sha256":"e29eed5aef3df56978d08e82ac4ec3f88bc700fba17e16f34ad2529d5939142d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e29eed5aef3df56978d08e82ac4ec3f88bc700fba17e16f34ad2529d5939142d","first_computed_at":"2026-07-14T00:18:40.557090Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-14T00:18:40.557090Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hN8l3oudsrdqRptPXj+YMOfVu25dmtMgWlElg+CA4OXv5Nl7WYLGjEFuShkhDYu5WbTMgUvdauiFBNd2skdgCQ==","signature_status":"signed_v1","signed_at":"2026-07-14T00:18:40.557929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.09866","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61fb72c9cf8bf6209dc4f034935f0f9bff0279b110ffed28a5e5cc9938d3e639","sha256:1006d8f7bca7280fd14a8aeb003c357bfd91b9480069920901064ada005c713a"],"state_sha256":"609914b16926e7490fd8a997c0a69d8f0694970e3b022634d6dcd6b67ffd7c57"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WQUKeBr98SU559U4bolH//JrEMf9kHkl/jdzmKZPvPSRN907qKAckH9fIxtYk86U7+aNtl4fDLF5f8wuDZAzCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T02:00:26.547520Z","bundle_sha256":"359cc79b0f0170794b6aecdb241b8b0769215582abb68103415ae1760d610e52"}}