{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LPPVE5O4S22MD276WYTXQOZI46","short_pith_number":"pith:LPPVE5O4","canonical_record":{"source":{"id":"2306.12755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-22T09:17:23Z","cross_cats_sorted":[],"title_canon_sha256":"373415b6e1a8ce13f4102722c294371e472951c2ff19121fddba73b3e12c1303","abstract_canon_sha256":"8ea2ad3c7f0e1b76b24d13c1efbee5a1e2eae62c346584d0a1f891e797c31313"},"schema_version":"1.0"},"canonical_sha256":"5bdf5275dc96b4c1ebfeb627783b28e7926703e5cd3bd7f1bd130dd3bd93677e","source":{"kind":"arxiv","id":"2306.12755","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.12755","created_at":"2026-07-05T06:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"2306.12755v1","created_at":"2026-07-05T06:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12755","created_at":"2026-07-05T06:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"LPPVE5O4S22M","created_at":"2026-07-05T06:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"LPPVE5O4S22MD276","created_at":"2026-07-05T06:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"LPPVE5O4","created_at":"2026-07-05T06:23:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LPPVE5O4S22MD276WYTXQOZI46","target":"record","payload":{"canonical_record":{"source":{"id":"2306.12755","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-22T09:17:23Z","cross_cats_sorted":[],"title_canon_sha256":"373415b6e1a8ce13f4102722c294371e472951c2ff19121fddba73b3e12c1303","abstract_canon_sha256":"8ea2ad3c7f0e1b76b24d13c1efbee5a1e2eae62c346584d0a1f891e797c31313"},"schema_version":"1.0"},"canonical_sha256":"5bdf5275dc96b4c1ebfeb627783b28e7926703e5cd3bd7f1bd130dd3bd93677e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:23:47.720790Z","signature_b64":"PqVmF84TsxOtfjxU05HnO2IJBygHBxqUTxixEwpluhzx6iPdasJ00WgR+HKIXwI+wUtV6sR6ADLtskgIwNnoBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bdf5275dc96b4c1ebfeb627783b28e7926703e5cd3bd7f1bd130dd3bd93677e","last_reissued_at":"2026-07-05T06:23:47.720310Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:23:47.720310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.12755","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":"2026-07-05T06:23:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"it4Wx0yjZ4leR9mmTb3ca2IZpruy6I3FW9mpyUNKDDLnmPfjvv8XPbmlwEkyTJnL30EuAr+LM9SPYvmgY0Q9DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:03:06.574611Z"},"content_sha256":"c43c61fb67df0d23d0462f38a5fa1b7c862be2c312a0076db045d79009cef3c0","schema_version":"1.0","event_id":"sha256:c43c61fb67df0d23d0462f38a5fa1b7c862be2c312a0076db045d79009cef3c0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LPPVE5O4S22MD276WYTXQOZI46","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Donglin Wang, Jinxin Liu, Sibo Gai, Yachen Kang, Zhenyu Wei, Zifeng Zhuang, Ziqi Zhang","submitted_at":"2023-06-22T09:17:23Z","abstract_excerpt":"Offline reinforcement learning (RL) aims to learn a policy using only pre-collected and fixed data. Although avoiding the time-consuming online interactions in RL, it poses challenges for out-of-distribution (OOD) state actions and often suffers from data inefficiency for training. Despite many efforts being devoted to addressing OOD state actions, the latter (data inefficiency) receives little attention in offline RL. To address this, this paper proposes the cross-domain offline RL, which assumes offline data incorporate additional source-domain data from varying transition dynamics (environm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12755","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/2306.12755/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":"2026-07-05T06:23:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OmozXbOKUKrahuuUX7CH1aQWRXguW1u0F1CAnxTRbWka0QxcF9x4eLlPz6YkSzRPOWiMWOQE+X2nA9gBsX4XCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T21:03:06.575309Z"},"content_sha256":"233deb6dbe80b02a45e8f95ea475aeb49a8096aa118688764bd3c825c32f329b","schema_version":"1.0","event_id":"sha256:233deb6dbe80b02a45e8f95ea475aeb49a8096aa118688764bd3c825c32f329b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LPPVE5O4S22MD276WYTXQOZI46/bundle.json","state_url":"https://pith.science/pith/LPPVE5O4S22MD276WYTXQOZI46/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LPPVE5O4S22MD276WYTXQOZI46/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":"2026-08-13T21:03:06Z","links":{"resolver":"https://pith.science/pith/LPPVE5O4S22MD276WYTXQOZI46","bundle":"https://pith.science/pith/LPPVE5O4S22MD276WYTXQOZI46/bundle.json","state":"https://pith.science/pith/LPPVE5O4S22MD276WYTXQOZI46/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LPPVE5O4S22MD276WYTXQOZI46/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LPPVE5O4S22MD276WYTXQOZI46","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":"8ea2ad3c7f0e1b76b24d13c1efbee5a1e2eae62c346584d0a1f891e797c31313","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-22T09:17:23Z","title_canon_sha256":"373415b6e1a8ce13f4102722c294371e472951c2ff19121fddba73b3e12c1303"},"schema_version":"1.0","source":{"id":"2306.12755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.12755","created_at":"2026-07-05T06:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"2306.12755v1","created_at":"2026-07-05T06:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.12755","created_at":"2026-07-05T06:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"LPPVE5O4S22M","created_at":"2026-07-05T06:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"LPPVE5O4S22MD276","created_at":"2026-07-05T06:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"LPPVE5O4","created_at":"2026-07-05T06:23:47Z"}],"graph_snapshots":[{"event_id":"sha256:233deb6dbe80b02a45e8f95ea475aeb49a8096aa118688764bd3c825c32f329b","target":"graph","created_at":"2026-07-05T06:23:47Z","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/2306.12755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) aims to learn a policy using only pre-collected and fixed data. Although avoiding the time-consuming online interactions in RL, it poses challenges for out-of-distribution (OOD) state actions and often suffers from data inefficiency for training. Despite many efforts being devoted to addressing OOD state actions, the latter (data inefficiency) receives little attention in offline RL. To address this, this paper proposes the cross-domain offline RL, which assumes offline data incorporate additional source-domain data from varying transition dynamics (environm","authors_text":"Donglin Wang, Jinxin Liu, Sibo Gai, Yachen Kang, Zhenyu Wei, Zifeng Zhuang, Ziqi Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-22T09:17:23Z","title":"Beyond OOD State Actions: Supported Cross-Domain Offline Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.12755","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:c43c61fb67df0d23d0462f38a5fa1b7c862be2c312a0076db045d79009cef3c0","target":"record","created_at":"2026-07-05T06:23:47Z","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":"8ea2ad3c7f0e1b76b24d13c1efbee5a1e2eae62c346584d0a1f891e797c31313","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-06-22T09:17:23Z","title_canon_sha256":"373415b6e1a8ce13f4102722c294371e472951c2ff19121fddba73b3e12c1303"},"schema_version":"1.0","source":{"id":"2306.12755","kind":"arxiv","version":1}},"canonical_sha256":"5bdf5275dc96b4c1ebfeb627783b28e7926703e5cd3bd7f1bd130dd3bd93677e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bdf5275dc96b4c1ebfeb627783b28e7926703e5cd3bd7f1bd130dd3bd93677e","first_computed_at":"2026-07-05T06:23:47.720310Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:23:47.720310Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PqVmF84TsxOtfjxU05HnO2IJBygHBxqUTxixEwpluhzx6iPdasJ00WgR+HKIXwI+wUtV6sR6ADLtskgIwNnoBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:23:47.720790Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.12755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c43c61fb67df0d23d0462f38a5fa1b7c862be2c312a0076db045d79009cef3c0","sha256:233deb6dbe80b02a45e8f95ea475aeb49a8096aa118688764bd3c825c32f329b"],"state_sha256":"7ed71c5ddd1ffade561d2ebb4fb269dfdc65d7dcad130f7b7d9a3be9dd3b58d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9FshD0E5GUaz+oAXcu4/QvR4UXcllpevP3tM8DC9PdjV/n6LFpqs9feOtaD6yxJKdnP7tXxggyofiElLx+AxAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T21:03:06.581018Z","bundle_sha256":"6d3ed641d8dd4b91a9655b30614ee47fdaae82aacb12e485e46b9df946cecab0"}}