{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:EI4GLGJHJEWRTYR5CCQCUQVPXI","short_pith_number":"pith:EI4GLGJH","canonical_record":{"source":{"id":"2310.05723","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T13:47:05Z","cross_cats_sorted":[],"title_canon_sha256":"5b45027f32c6e054c7a2fac854d3e417fb741ebe356b6085587548504da5049d","abstract_canon_sha256":"310ecb7ff0a47af80e1d8c4224ad5fc407a903e6f30a9842dd85e3e3005ba86e"},"schema_version":"1.0"},"canonical_sha256":"2238659927492d19e23d10a02a42afba272e3f439bb0e6386d232c362c746c77","source":{"kind":"arxiv","id":"2310.05723","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05723","created_at":"2026-07-05T08:34:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05723v3","created_at":"2026-07-05T08:34:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05723","created_at":"2026-07-05T08:34:56Z"},{"alias_kind":"pith_short_12","alias_value":"EI4GLGJHJEWR","created_at":"2026-07-05T08:34:56Z"},{"alias_kind":"pith_short_16","alias_value":"EI4GLGJHJEWRTYR5","created_at":"2026-07-05T08:34:56Z"},{"alias_kind":"pith_short_8","alias_value":"EI4GLGJH","created_at":"2026-07-05T08:34:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:EI4GLGJHJEWRTYR5CCQCUQVPXI","target":"record","payload":{"canonical_record":{"source":{"id":"2310.05723","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T13:47:05Z","cross_cats_sorted":[],"title_canon_sha256":"5b45027f32c6e054c7a2fac854d3e417fb741ebe356b6085587548504da5049d","abstract_canon_sha256":"310ecb7ff0a47af80e1d8c4224ad5fc407a903e6f30a9842dd85e3e3005ba86e"},"schema_version":"1.0"},"canonical_sha256":"2238659927492d19e23d10a02a42afba272e3f439bb0e6386d232c362c746c77","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:34:56.437467Z","signature_b64":"HGDlxGS1yIW4WrQ05wHJdtc+9XE5jZSnD8xmTW7iyIPWnfsLrBfuGLB1xG+vlyu8DjPy7grxvx7vct1qAZDNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2238659927492d19e23d10a02a42afba272e3f439bb0e6386d232c362c746c77","last_reissued_at":"2026-07-05T08:34:56.437053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:34:56.437053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.05723","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:34:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XdH7LNmkupU0B16GL7eN5Lm8Koaw4JNWAwG/9W3P41nrfbE6d1p17pcHIRbM5ILy5XSGX4o8WeyC1rwW4pjBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:49:54.858698Z"},"content_sha256":"64cf688272d0eb49159a80bd1568fe6787b177b4851cb9b23c7fc69887140d38","schema_version":"1.0","event_id":"sha256:64cf688272d0eb49159a80bd1568fe6787b177b4851cb9b23c7fc69887140d38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:EI4GLGJHJEWRTYR5CCQCUQVPXI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adam Jelley, Amos Storkey, Stefano V. Albrecht, Trevor McInroe","submitted_at":"2023-10-09T13:47:05Z","abstract_excerpt":"Offline pretraining with a static dataset followed by online fine-tuning (offline-to-online, or OtO) is a paradigm well matched to a real-world RL deployment process. In this scenario, we aim to find the best-performing policy within a limited budget of online interactions. Previous work in the OtO setting has focused on correcting for bias introduced by the policy-constraint mechanisms of offline RL algorithms. Such constraints keep the learned policy close to the behavior policy that collected the dataset, but we show this can unnecessarily limit policy performance if the behavior policy is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05723","kind":"arxiv","version":3},"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/2310.05723/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":"2026-07-05T08:34:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0sdmlSsQqZRRqhpSIu+qVY+neIuAT/A4LLlzaimXiKFSn+YfQCT+f0U6WezHnZ43IijuYW3M8lEe50VCkwyICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:49:54.859200Z"},"content_sha256":"c3150904eb379478cd88ca6672ba65d63dcec152efa360d7bd94328006e0a5f5","schema_version":"1.0","event_id":"sha256:c3150904eb379478cd88ca6672ba65d63dcec152efa360d7bd94328006e0a5f5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EI4GLGJHJEWRTYR5CCQCUQVPXI/bundle.json","state_url":"https://pith.science/pith/EI4GLGJHJEWRTYR5CCQCUQVPXI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EI4GLGJHJEWRTYR5CCQCUQVPXI/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":"2026-08-11T08:49:54Z","links":{"resolver":"https://pith.science/pith/EI4GLGJHJEWRTYR5CCQCUQVPXI","bundle":"https://pith.science/pith/EI4GLGJHJEWRTYR5CCQCUQVPXI/bundle.json","state":"https://pith.science/pith/EI4GLGJHJEWRTYR5CCQCUQVPXI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EI4GLGJHJEWRTYR5CCQCUQVPXI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EI4GLGJHJEWRTYR5CCQCUQVPXI","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":"310ecb7ff0a47af80e1d8c4224ad5fc407a903e6f30a9842dd85e3e3005ba86e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T13:47:05Z","title_canon_sha256":"5b45027f32c6e054c7a2fac854d3e417fb741ebe356b6085587548504da5049d"},"schema_version":"1.0","source":{"id":"2310.05723","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05723","created_at":"2026-07-05T08:34:56Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05723v3","created_at":"2026-07-05T08:34:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05723","created_at":"2026-07-05T08:34:56Z"},{"alias_kind":"pith_short_12","alias_value":"EI4GLGJHJEWR","created_at":"2026-07-05T08:34:56Z"},{"alias_kind":"pith_short_16","alias_value":"EI4GLGJHJEWRTYR5","created_at":"2026-07-05T08:34:56Z"},{"alias_kind":"pith_short_8","alias_value":"EI4GLGJH","created_at":"2026-07-05T08:34:56Z"}],"graph_snapshots":[{"event_id":"sha256:c3150904eb379478cd88ca6672ba65d63dcec152efa360d7bd94328006e0a5f5","target":"graph","created_at":"2026-07-05T08:34:56Z","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/2310.05723/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline pretraining with a static dataset followed by online fine-tuning (offline-to-online, or OtO) is a paradigm well matched to a real-world RL deployment process. In this scenario, we aim to find the best-performing policy within a limited budget of online interactions. Previous work in the OtO setting has focused on correcting for bias introduced by the policy-constraint mechanisms of offline RL algorithms. Such constraints keep the learned policy close to the behavior policy that collected the dataset, but we show this can unnecessarily limit policy performance if the behavior policy is ","authors_text":"Adam Jelley, Amos Storkey, Stefano V. Albrecht, Trevor McInroe","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T13:47:05Z","title":"Planning to Go Out-of-Distribution in Offline-to-Online Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05723","kind":"arxiv","version":3},"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":"sha256:64cf688272d0eb49159a80bd1568fe6787b177b4851cb9b23c7fc69887140d38","target":"record","created_at":"2026-07-05T08:34:56Z","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":"310ecb7ff0a47af80e1d8c4224ad5fc407a903e6f30a9842dd85e3e3005ba86e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-10-09T13:47:05Z","title_canon_sha256":"5b45027f32c6e054c7a2fac854d3e417fb741ebe356b6085587548504da5049d"},"schema_version":"1.0","source":{"id":"2310.05723","kind":"arxiv","version":3}},"canonical_sha256":"2238659927492d19e23d10a02a42afba272e3f439bb0e6386d232c362c746c77","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2238659927492d19e23d10a02a42afba272e3f439bb0e6386d232c362c746c77","first_computed_at":"2026-07-05T08:34:56.437053Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:34:56.437053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HGDlxGS1yIW4WrQ05wHJdtc+9XE5jZSnD8xmTW7iyIPWnfsLrBfuGLB1xG+vlyu8DjPy7grxvx7vct1qAZDNBw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:34:56.437467Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05723","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:64cf688272d0eb49159a80bd1568fe6787b177b4851cb9b23c7fc69887140d38","sha256:c3150904eb379478cd88ca6672ba65d63dcec152efa360d7bd94328006e0a5f5"],"state_sha256":"b56fc892a83f6362967047d5227546e20bd7cabbb13846ae535abc7bc919a3ee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IbG2IsLM1XpmXHp3WfyoUsLWoTjHRCP/Ow/e3AMBtbKzehWmyDZrrbwfQL4d1Q3SPx2kRoBPC4J4AgnS8hmwDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:49:54.864253Z","bundle_sha256":"5cdb8b61b5910f4c8a6135fe601ac7d45ca1602a9042fd2d1866ac8488e28121"}}