{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PEVUTGEGMV43GJE54LQP7UACTP","short_pith_number":"pith:PEVUTGEG","canonical_record":{"source":{"id":"2310.17966","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-27T08:30:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dbe7796ee71b37596a2fd901bf59d1161ba34237afbb78838d8c1819fcdb40ec","abstract_canon_sha256":"91a43e08628c8ca07e11632c925b677d859caec886621abeae3258dfd904c992"},"schema_version":"1.0"},"canonical_sha256":"792b4998866579b3249de2e0ffd0029bf6a537cbe966c1ee9431c6bebbbbc48c","source":{"kind":"arxiv","id":"2310.17966","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17966","created_at":"2026-07-05T07:06:37Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17966v2","created_at":"2026-07-05T07:06:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17966","created_at":"2026-07-05T07:06:37Z"},{"alias_kind":"pith_short_12","alias_value":"PEVUTGEGMV43","created_at":"2026-07-05T07:06:37Z"},{"alias_kind":"pith_short_16","alias_value":"PEVUTGEGMV43GJE5","created_at":"2026-07-05T07:06:37Z"},{"alias_kind":"pith_short_8","alias_value":"PEVUTGEG","created_at":"2026-07-05T07:06:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PEVUTGEGMV43GJE54LQP7UACTP","target":"record","payload":{"canonical_record":{"source":{"id":"2310.17966","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-27T08:30:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dbe7796ee71b37596a2fd901bf59d1161ba34237afbb78838d8c1819fcdb40ec","abstract_canon_sha256":"91a43e08628c8ca07e11632c925b677d859caec886621abeae3258dfd904c992"},"schema_version":"1.0"},"canonical_sha256":"792b4998866579b3249de2e0ffd0029bf6a537cbe966c1ee9431c6bebbbbc48c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:37.957226Z","signature_b64":"TAzIuyGwPYb+dTPX8PIyg0hSfF3fEgXKCSgiUg6QnVNP6Hlb7//zEo4j2L2qaZtmKPLXAY6t45Mb6oHc/TUZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"792b4998866579b3249de2e0ffd0029bf6a537cbe966c1ee9431c6bebbbbc48c","last_reissued_at":"2026-07-05T07:06:37.956633Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:37.956633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.17966","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:06:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vScHhSDkYTXQo6XwRhF1VPFA8JGZskCoBdCAPW1gc/+rDvtJPIZvxQYMTFT7QPQTHlv8NGN3VOGn2yTFUAhTCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T10:24:12.764711Z"},"content_sha256":"434ff986dcc73634693b9be102c929b3a94e8873b079fccd7d5a33a6bf1cc92b","schema_version":"1.0","event_id":"sha256:434ff986dcc73634693b9be102c929b3a94e8873b079fccd7d5a33a6bf1cc92b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PEVUTGEGMV43GJE54LQP7UACTP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Gao Huang, Hao Chen, Jiawei Gao, Liwei Wu, Matthieu Gaetan Lin, Ning Jia, Qisen Yang, Shenzhi Wang, Shiji Song","submitted_at":"2023-10-27T08:30:54Z","abstract_excerpt":"Offline-to-online reinforcement learning (RL) is a training paradigm that combines pre-training on a pre-collected dataset with fine-tuning in an online environment. However, the incorporation of online fine-tuning can intensify the well-known distributional shift problem. Existing solutions tackle this problem by imposing a policy constraint on the policy improvement objective in both offline and online learning. They typically advocate a single balance between policy improvement and constraints across diverse data collections. This one-size-fits-all manner may not optimally leverage each col"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17966","kind":"arxiv","version":2},"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/2310.17966/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":"2026-07-05T07:06:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X/iJycCtA24z1D6G9jpAzBNOKYHi5ucGTrGfF+tISghVmm0busqj+JQVKjPO+RPgq+zTmjUrmQTY1e/NZSvRDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-19T10:24:12.765080Z"},"content_sha256":"f07f2d3bf2229ac5c199bb304ae64b4c76152ee0926a1070e85dd66e39e2d6eb","schema_version":"1.0","event_id":"sha256:f07f2d3bf2229ac5c199bb304ae64b4c76152ee0926a1070e85dd66e39e2d6eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP/bundle.json","state_url":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PEVUTGEGMV43GJE54LQP7UACTP/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":"2026-07-19T10:24:12Z","links":{"resolver":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP","bundle":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP/bundle.json","state":"https://pith.science/pith/PEVUTGEGMV43GJE54LQP7UACTP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PEVUTGEGMV43GJE54LQP7UACTP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PEVUTGEGMV43GJE54LQP7UACTP","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":"91a43e08628c8ca07e11632c925b677d859caec886621abeae3258dfd904c992","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-27T08:30:54Z","title_canon_sha256":"dbe7796ee71b37596a2fd901bf59d1161ba34237afbb78838d8c1819fcdb40ec"},"schema_version":"1.0","source":{"id":"2310.17966","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.17966","created_at":"2026-07-05T07:06:37Z"},{"alias_kind":"arxiv_version","alias_value":"2310.17966v2","created_at":"2026-07-05T07:06:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.17966","created_at":"2026-07-05T07:06:37Z"},{"alias_kind":"pith_short_12","alias_value":"PEVUTGEGMV43","created_at":"2026-07-05T07:06:37Z"},{"alias_kind":"pith_short_16","alias_value":"PEVUTGEGMV43GJE5","created_at":"2026-07-05T07:06:37Z"},{"alias_kind":"pith_short_8","alias_value":"PEVUTGEG","created_at":"2026-07-05T07:06:37Z"}],"graph_snapshots":[{"event_id":"sha256:f07f2d3bf2229ac5c199bb304ae64b4c76152ee0926a1070e85dd66e39e2d6eb","target":"graph","created_at":"2026-07-05T07:06:37Z","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/2310.17966/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline-to-online reinforcement learning (RL) is a training paradigm that combines pre-training on a pre-collected dataset with fine-tuning in an online environment. However, the incorporation of online fine-tuning can intensify the well-known distributional shift problem. Existing solutions tackle this problem by imposing a policy constraint on the policy improvement objective in both offline and online learning. They typically advocate a single balance between policy improvement and constraints across diverse data collections. This one-size-fits-all manner may not optimally leverage each col","authors_text":"Gao Huang, Hao Chen, Jiawei Gao, Liwei Wu, Matthieu Gaetan Lin, Ning Jia, Qisen Yang, Shenzhi Wang, Shiji Song","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-27T08:30:54Z","title":"Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.17966","kind":"arxiv","version":2},"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":"sha256:434ff986dcc73634693b9be102c929b3a94e8873b079fccd7d5a33a6bf1cc92b","target":"record","created_at":"2026-07-05T07:06:37Z","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":"91a43e08628c8ca07e11632c925b677d859caec886621abeae3258dfd904c992","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-27T08:30:54Z","title_canon_sha256":"dbe7796ee71b37596a2fd901bf59d1161ba34237afbb78838d8c1819fcdb40ec"},"schema_version":"1.0","source":{"id":"2310.17966","kind":"arxiv","version":2}},"canonical_sha256":"792b4998866579b3249de2e0ffd0029bf6a537cbe966c1ee9431c6bebbbbc48c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"792b4998866579b3249de2e0ffd0029bf6a537cbe966c1ee9431c6bebbbbc48c","first_computed_at":"2026-07-05T07:06:37.956633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:37.956633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TAzIuyGwPYb+dTPX8PIyg0hSfF3fEgXKCSgiUg6QnVNP6Hlb7//zEo4j2L2qaZtmKPLXAY6t45Mb6oHc/TUZCw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:37.957226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.17966","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:434ff986dcc73634693b9be102c929b3a94e8873b079fccd7d5a33a6bf1cc92b","sha256:f07f2d3bf2229ac5c199bb304ae64b4c76152ee0926a1070e85dd66e39e2d6eb"],"state_sha256":"21cf06297892afd409a706cc8e96df12a19e189e1086e341a51043bd9039f3e3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rc7NLUjPjS/ZC5JpMSwk9lIgMEJrWDn54som1mLJ5GfhrUo+AGCwUbr6BnM6lwyUIh0mPiuDowBEoT6HHKs7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-19T10:24:12.767149Z","bundle_sha256":"1dd719366ccbc7d792d228406d479ffcff53f8218579beaa4cb302112d9d422e"}}