{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AGHN4TOJXLPDUZDZTZW67HDW2Q","short_pith_number":"pith:AGHN4TOJ","canonical_record":{"source":{"id":"2311.03695","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-07T03:50:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6fca59c59ca3ff12815ee4eab279760ce71caf629a0545b7be34571225b40b34","abstract_canon_sha256":"602edf38364d91fa62e7aa4cbd5ed2e3eb478303e0e7fbf2c615802d0ff077fa"},"schema_version":"1.0"},"canonical_sha256":"018ede4dc9bade3a64799e6def9c76d40ac1823fabd25bce703097d4ad0f4a40","source":{"kind":"arxiv","id":"2311.03695","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.03695","created_at":"2026-07-05T07:10:03Z"},{"alias_kind":"arxiv_version","alias_value":"2311.03695v1","created_at":"2026-07-05T07:10:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03695","created_at":"2026-07-05T07:10:03Z"},{"alias_kind":"pith_short_12","alias_value":"AGHN4TOJXLPD","created_at":"2026-07-05T07:10:03Z"},{"alias_kind":"pith_short_16","alias_value":"AGHN4TOJXLPDUZDZ","created_at":"2026-07-05T07:10:03Z"},{"alias_kind":"pith_short_8","alias_value":"AGHN4TOJ","created_at":"2026-07-05T07:10:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AGHN4TOJXLPDUZDZTZW67HDW2Q","target":"record","payload":{"canonical_record":{"source":{"id":"2311.03695","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-07T03:50:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6fca59c59ca3ff12815ee4eab279760ce71caf629a0545b7be34571225b40b34","abstract_canon_sha256":"602edf38364d91fa62e7aa4cbd5ed2e3eb478303e0e7fbf2c615802d0ff077fa"},"schema_version":"1.0"},"canonical_sha256":"018ede4dc9bade3a64799e6def9c76d40ac1823fabd25bce703097d4ad0f4a40","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:10:03.392606Z","signature_b64":"5tRFm9+i9q9a8esXDyHH7eY/iTiK5R5d3VgEiZUFQ9pNYsPYAOMp8Sm9OUzKJUQUlfGa2H4e+cBffOWPdNV2Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"018ede4dc9bade3a64799e6def9c76d40ac1823fabd25bce703097d4ad0f4a40","last_reissued_at":"2026-07-05T07:10:03.392157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:10:03.392157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.03695","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":"2026-07-05T07:10:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OIJDwMWRT4OOU1rGsWx/vFDuDcXXGt5CCBHL6MPM8rqMT5U8Z99TcY4moAfO4sP3bUTTqegOMgMLUHNmf51iDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:02:30.289774Z"},"content_sha256":"f8e6e1abcd30b3b52d40bf883e370c05d85ba63179d689bbad3be61ac670da4e","schema_version":"1.0","event_id":"sha256:f8e6e1abcd30b3b52d40bf883e370c05d85ba63179d689bbad3be61ac670da4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AGHN4TOJXLPDUZDZTZW67HDW2Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Context Shift Reduction for Offline Meta-Reinforcement Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fan Wu, Jiaming Guo, Ling Li, Qi Guo, Qi Yi, Rui Zhang, Ruizhi Chen, Shaohui Peng, Siming Lan, Xing Hu, Yunji Chen, Yunkai Gao, Zidong Du","submitted_at":"2023-11-07T03:50:01Z","abstract_excerpt":"Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks. However, the context shift problem arises due to the distribution discrepancy between the contexts used for training (from the behavior policy) and testing (from the exploration policy). The context shift problem leads to incorrect task inference and further deteriorates the generalization ability of the meta-policy. Existing OMRL methods either overlook this problem or attempt to mitigate it with additional information. In this paper, we propose a n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03695","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/2311.03695/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":"2026-07-05T07:10:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NGeSO3xPBe5Zbh8wp0IaGvcbOhPR2xAfHO+nAoVS0NME91EQnFlQ847A4smBIpOgjXRtr8LZIbgnUaRrAfIPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:02:30.290141Z"},"content_sha256":"95f6de5f64c3c31c8e3a89bbf0470728b494367e0669d018cbebf795e8d2ca67","schema_version":"1.0","event_id":"sha256:95f6de5f64c3c31c8e3a89bbf0470728b494367e0669d018cbebf795e8d2ca67"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AGHN4TOJXLPDUZDZTZW67HDW2Q/bundle.json","state_url":"https://pith.science/pith/AGHN4TOJXLPDUZDZTZW67HDW2Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AGHN4TOJXLPDUZDZTZW67HDW2Q/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":"2026-07-07T10:02:30Z","links":{"resolver":"https://pith.science/pith/AGHN4TOJXLPDUZDZTZW67HDW2Q","bundle":"https://pith.science/pith/AGHN4TOJXLPDUZDZTZW67HDW2Q/bundle.json","state":"https://pith.science/pith/AGHN4TOJXLPDUZDZTZW67HDW2Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AGHN4TOJXLPDUZDZTZW67HDW2Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AGHN4TOJXLPDUZDZTZW67HDW2Q","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":"602edf38364d91fa62e7aa4cbd5ed2e3eb478303e0e7fbf2c615802d0ff077fa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-07T03:50:01Z","title_canon_sha256":"6fca59c59ca3ff12815ee4eab279760ce71caf629a0545b7be34571225b40b34"},"schema_version":"1.0","source":{"id":"2311.03695","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.03695","created_at":"2026-07-05T07:10:03Z"},{"alias_kind":"arxiv_version","alias_value":"2311.03695v1","created_at":"2026-07-05T07:10:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.03695","created_at":"2026-07-05T07:10:03Z"},{"alias_kind":"pith_short_12","alias_value":"AGHN4TOJXLPD","created_at":"2026-07-05T07:10:03Z"},{"alias_kind":"pith_short_16","alias_value":"AGHN4TOJXLPDUZDZ","created_at":"2026-07-05T07:10:03Z"},{"alias_kind":"pith_short_8","alias_value":"AGHN4TOJ","created_at":"2026-07-05T07:10:03Z"}],"graph_snapshots":[{"event_id":"sha256:95f6de5f64c3c31c8e3a89bbf0470728b494367e0669d018cbebf795e8d2ca67","target":"graph","created_at":"2026-07-05T07:10:03Z","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/2311.03695/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline meta-reinforcement learning (OMRL) utilizes pre-collected offline datasets to enhance the agent's generalization ability on unseen tasks. However, the context shift problem arises due to the distribution discrepancy between the contexts used for training (from the behavior policy) and testing (from the exploration policy). The context shift problem leads to incorrect task inference and further deteriorates the generalization ability of the meta-policy. Existing OMRL methods either overlook this problem or attempt to mitigate it with additional information. In this paper, we propose a n","authors_text":"Fan Wu, Jiaming Guo, Ling Li, Qi Guo, Qi Yi, Rui Zhang, Ruizhi Chen, Shaohui Peng, Siming Lan, Xing Hu, Yunji Chen, Yunkai Gao, Zidong Du","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-07T03:50:01Z","title":"Context Shift Reduction for Offline Meta-Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.03695","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:f8e6e1abcd30b3b52d40bf883e370c05d85ba63179d689bbad3be61ac670da4e","target":"record","created_at":"2026-07-05T07:10:03Z","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":"602edf38364d91fa62e7aa4cbd5ed2e3eb478303e0e7fbf2c615802d0ff077fa","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2023-11-07T03:50:01Z","title_canon_sha256":"6fca59c59ca3ff12815ee4eab279760ce71caf629a0545b7be34571225b40b34"},"schema_version":"1.0","source":{"id":"2311.03695","kind":"arxiv","version":1}},"canonical_sha256":"018ede4dc9bade3a64799e6def9c76d40ac1823fabd25bce703097d4ad0f4a40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"018ede4dc9bade3a64799e6def9c76d40ac1823fabd25bce703097d4ad0f4a40","first_computed_at":"2026-07-05T07:10:03.392157Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:10:03.392157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5tRFm9+i9q9a8esXDyHH7eY/iTiK5R5d3VgEiZUFQ9pNYsPYAOMp8Sm9OUzKJUQUlfGa2H4e+cBffOWPdNV2Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T07:10:03.392606Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.03695","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f8e6e1abcd30b3b52d40bf883e370c05d85ba63179d689bbad3be61ac670da4e","sha256:95f6de5f64c3c31c8e3a89bbf0470728b494367e0669d018cbebf795e8d2ca67"],"state_sha256":"5201ef5f2e688883fac2d1996023d703afce9b70df5d177a6d207d919bf5d6c8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e/FT7eJbfApsTuPm90vSnFnNVgQL0OZntiEwlL9eLbgNrqc83Ng1UxeMwM9V3O4vhXnvs61bP4C6X8pciOQWBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:02:30.292048Z","bundle_sha256":"099ba5fb19fc11ee427f6168ebb8a5db915b5898a3670de7b142de690d6b79eb"}}