{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7BQDFQL3RDEIYYA4TB7MC2LDCX","short_pith_number":"pith:7BQDFQL3","canonical_record":{"source":{"id":"2410.18626","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T10:35:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e561d890ab78cd77649d3304008130846d941159febd3be452a2cecfdff6584f","abstract_canon_sha256":"45751c041e106f7ea030b57fc8218ffa59f9995396fd99ed6b46ee5998627329"},"schema_version":"1.0"},"canonical_sha256":"f86032c17b88c88c601c987ec1696315fadc272da3538882d958f50031698770","source":{"kind":"arxiv","id":"2410.18626","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18626","created_at":"2026-07-05T10:17:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18626v2","created_at":"2026-07-05T10:17:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18626","created_at":"2026-07-05T10:17:51Z"},{"alias_kind":"pith_short_12","alias_value":"7BQDFQL3RDEI","created_at":"2026-07-05T10:17:51Z"},{"alias_kind":"pith_short_16","alias_value":"7BQDFQL3RDEIYYA4","created_at":"2026-07-05T10:17:51Z"},{"alias_kind":"pith_short_8","alias_value":"7BQDFQL3","created_at":"2026-07-05T10:17:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7BQDFQL3RDEIYYA4TB7MC2LDCX","target":"record","payload":{"canonical_record":{"source":{"id":"2410.18626","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T10:35:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e561d890ab78cd77649d3304008130846d941159febd3be452a2cecfdff6584f","abstract_canon_sha256":"45751c041e106f7ea030b57fc8218ffa59f9995396fd99ed6b46ee5998627329"},"schema_version":"1.0"},"canonical_sha256":"f86032c17b88c88c601c987ec1696315fadc272da3538882d958f50031698770","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:51.074916Z","signature_b64":"0Gw4R9zTQZ9NYbPIQSyxRa3ERsDqtI1LRgyoCbmgL8HPURcFZSsYiGn8grpZ3biL15eJ39h/GXrpMUBuXqtpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f86032c17b88c88c601c987ec1696315fadc272da3538882d958f50031698770","last_reissued_at":"2026-07-05T10:17:51.074389Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:51.074389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.18626","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":"2026-07-05T10:17:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZBngxWQ4kw622S7NMA6cdElTwnIKJQAzcowl4PMcaOoi6+2HJfCLR49a9yvUWILGmWV03znucX6T/Mz2KFkEBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:05:52.607489Z"},"content_sha256":"84fada2da1f3b89c2372f2c8d1871c9e968d2054e8e8df2dde90d1e39e074924","schema_version":"1.0","event_id":"sha256:84fada2da1f3b89c2372f2c8d1871c9e968d2054e8e8df2dde90d1e39e074924"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7BQDFQL3RDEIYYA4TB7MC2LDCX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Haochi Wu, Liyu Zhang, Mingyang Sun, Quan Kong, Ruilong Deng, Xu Wan","submitted_at":"2024-10-24T10:35:02Z","abstract_excerpt":"Offline-to-online (O2O) reinforcement learning (RL) pre-trains models on offline data and refines policies through online fine-tuning. However, existing O2O RL algorithms typically require maintaining the tedious offline datasets to mitigate the effects of out-of-distribution (OOD) data, which significantly limits their efficiency in exploiting online samples. To address this deficiency, we introduce a new paradigm for O2O RL called State-Action-Conditional Offline \\Model Guidance (SAMG). It freezes the pre-trained offline critic to provide compact offline understanding for each state-action s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18626","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/2410.18626/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":"2026-07-05T10:17:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c7H4HC83eHENAhneOnpRRzorlzqjMs0TuKN33Wj0DY4cuE3gt80R3bfzty5TZdKaKuHhjqKVebsZj9gyGh13DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T08:05:52.608089Z"},"content_sha256":"e7e04249e0107565236acb4f5c06cc8af1dcc4d2c82810502b6faf7dbb998beb","schema_version":"1.0","event_id":"sha256:e7e04249e0107565236acb4f5c06cc8af1dcc4d2c82810502b6faf7dbb998beb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX/bundle.json","state_url":"https://pith.science/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX/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":"2026-08-22T08:05:52Z","links":{"resolver":"https://pith.science/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX","bundle":"https://pith.science/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX/bundle.json","state":"https://pith.science/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7BQDFQL3RDEIYYA4TB7MC2LDCX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7BQDFQL3RDEIYYA4TB7MC2LDCX","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":"45751c041e106f7ea030b57fc8218ffa59f9995396fd99ed6b46ee5998627329","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T10:35:02Z","title_canon_sha256":"e561d890ab78cd77649d3304008130846d941159febd3be452a2cecfdff6584f"},"schema_version":"1.0","source":{"id":"2410.18626","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.18626","created_at":"2026-07-05T10:17:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.18626v2","created_at":"2026-07-05T10:17:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18626","created_at":"2026-07-05T10:17:51Z"},{"alias_kind":"pith_short_12","alias_value":"7BQDFQL3RDEI","created_at":"2026-07-05T10:17:51Z"},{"alias_kind":"pith_short_16","alias_value":"7BQDFQL3RDEIYYA4","created_at":"2026-07-05T10:17:51Z"},{"alias_kind":"pith_short_8","alias_value":"7BQDFQL3","created_at":"2026-07-05T10:17:51Z"}],"graph_snapshots":[{"event_id":"sha256:e7e04249e0107565236acb4f5c06cc8af1dcc4d2c82810502b6faf7dbb998beb","target":"graph","created_at":"2026-07-05T10:17:51Z","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/2410.18626/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline-to-online (O2O) reinforcement learning (RL) pre-trains models on offline data and refines policies through online fine-tuning. However, existing O2O RL algorithms typically require maintaining the tedious offline datasets to mitigate the effects of out-of-distribution (OOD) data, which significantly limits their efficiency in exploiting online samples. To address this deficiency, we introduce a new paradigm for O2O RL called State-Action-Conditional Offline \\Model Guidance (SAMG). It freezes the pre-trained offline critic to provide compact offline understanding for each state-action s","authors_text":"Haochi Wu, Liyu Zhang, Mingyang Sun, Quan Kong, Ruilong Deng, Xu Wan","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T10:35:02Z","title":"SAMG: Offline-to-Online Reinforcement Learning via State-Action-Conditional Offline Model Guidance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18626","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":"sha256:84fada2da1f3b89c2372f2c8d1871c9e968d2054e8e8df2dde90d1e39e074924","target":"record","created_at":"2026-07-05T10:17:51Z","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":"45751c041e106f7ea030b57fc8218ffa59f9995396fd99ed6b46ee5998627329","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-24T10:35:02Z","title_canon_sha256":"e561d890ab78cd77649d3304008130846d941159febd3be452a2cecfdff6584f"},"schema_version":"1.0","source":{"id":"2410.18626","kind":"arxiv","version":2}},"canonical_sha256":"f86032c17b88c88c601c987ec1696315fadc272da3538882d958f50031698770","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f86032c17b88c88c601c987ec1696315fadc272da3538882d958f50031698770","first_computed_at":"2026-07-05T10:17:51.074389Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:17:51.074389Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Gw4R9zTQZ9NYbPIQSyxRa3ERsDqtI1LRgyoCbmgL8HPURcFZSsYiGn8grpZ3biL15eJ39h/GXrpMUBuXqtpCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:17:51.074916Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.18626","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84fada2da1f3b89c2372f2c8d1871c9e968d2054e8e8df2dde90d1e39e074924","sha256:e7e04249e0107565236acb4f5c06cc8af1dcc4d2c82810502b6faf7dbb998beb"],"state_sha256":"b09c3f8babdd6eee35fa6b29c420ff0bdcaf9ece572d3c396fcff18a4ee593e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m0og+iRTT0IH7kOcdy/7aJTKpeNHxx5vgZZHafRnmYxwQANjyahAeTgiDvqCRI1YC46Ix+kh2/jiV7kuu6jUDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T08:05:52.612739Z","bundle_sha256":"d90dfc6c9ef4ddcb5a753a4d800fbce4d09174488ae344a5f3bb4a97ec7d1ac5"}}