{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:KN7S7E2OWGFX5QDBLJ7EQF2F4F","short_pith_number":"pith:KN7S7E2O","canonical_record":{"source":{"id":"2312.03991","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-07T02:17:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4de358289498ff660bb2854c01d0b973f74ee1c0ef4ed5a3afdc1c4abd47aa1a","abstract_canon_sha256":"026a0a54b1e354b0cadeee53f45765a4b0647fc4837441a60f3287322b78b0c3"},"schema_version":"1.0"},"canonical_sha256":"537f2f934eb18b7ec0615a7e481745e16e473f59c93e4596ec50cfeaf27ce9f3","source":{"kind":"arxiv","id":"2312.03991","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.03991","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"arxiv_version","alias_value":"2312.03991v2","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03991","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"pith_short_12","alias_value":"KN7S7E2OWGFX","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"pith_short_16","alias_value":"KN7S7E2OWGFX5QDB","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"pith_short_8","alias_value":"KN7S7E2O","created_at":"2026-07-05T08:08:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:KN7S7E2OWGFX5QDBLJ7EQF2F4F","target":"record","payload":{"canonical_record":{"source":{"id":"2312.03991","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-07T02:17:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4de358289498ff660bb2854c01d0b973f74ee1c0ef4ed5a3afdc1c4abd47aa1a","abstract_canon_sha256":"026a0a54b1e354b0cadeee53f45765a4b0647fc4837441a60f3287322b78b0c3"},"schema_version":"1.0"},"canonical_sha256":"537f2f934eb18b7ec0615a7e481745e16e473f59c93e4596ec50cfeaf27ce9f3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:53.322147Z","signature_b64":"HrttV6PnMe5ln5lonJRsD34h75ap9PRMbhAGkfl7+BPW/OTGvnp0dLSq/ExzgaB0cp3Z4jNbqHBpC34S3aTTBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"537f2f934eb18b7ec0615a7e481745e16e473f59c93e4596ec50cfeaf27ce9f3","last_reissued_at":"2026-07-05T08:08:53.321677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:53.321677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.03991","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":"2026-07-05T08:08:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RiVqplz84e3nLG70GY9BDH9VK4ta6jlXuguuVWpusbfPkSw3/VEvoZKE/hkvE3hlZpCbZKLc7bvB5cAawZ5HDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:13:00.155386Z"},"content_sha256":"df53670241fb11765c726feff1813896392d63faaeae3280c030bb1d4fca337a","schema_version":"1.0","event_id":"sha256:df53670241fb11765c726feff1813896392d63faaeae3280c030bb1d4fca337a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:KN7S7E2OWGFX5QDBLJ7EQF2F4F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MICRO: Model-Based Offline Reinforcement Learning with a Conservative Bellman Operator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"De-Xing Huang, Guotao Li, Hao Li, Mei-Jiang Gui, Tian-Yu Xiang, Xiao-Hu Zhou, Xiao-Yin Liu, Zeng-Guang Hou","submitted_at":"2023-12-07T02:17:45Z","abstract_excerpt":"Offline reinforcement learning (RL) faces a significant challenge of distribution shift. Model-free offline RL penalizes the Q value for out-of-distribution (OOD) data or constrains the policy closed to the behavior policy to tackle this problem, but this inhibits the exploration of the OOD region. Model-based offline RL, which uses the trained environment model to generate more OOD data and performs conservative policy optimization within that model, has become an effective method for this problem. However, the current model-based algorithms rarely consider agent robustness when incorporating"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03991","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/2312.03991/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":"2026-07-05T08:08:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SUGORh/PHdfLVVvDkarlOvcXNmbvFOwaHx2+W+XE72hjZEmZ4GWM62sAgkMrXNaqgdJyHApFXZSwTNQCNn0jAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T07:13:00.155792Z"},"content_sha256":"83a1d08b12cd19ba8538b2a4da766691344b95ee086f71d2e53514befd580f31","schema_version":"1.0","event_id":"sha256:83a1d08b12cd19ba8538b2a4da766691344b95ee086f71d2e53514befd580f31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KN7S7E2OWGFX5QDBLJ7EQF2F4F/bundle.json","state_url":"https://pith.science/pith/KN7S7E2OWGFX5QDBLJ7EQF2F4F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KN7S7E2OWGFX5QDBLJ7EQF2F4F/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":"2026-07-07T07:13:00Z","links":{"resolver":"https://pith.science/pith/KN7S7E2OWGFX5QDBLJ7EQF2F4F","bundle":"https://pith.science/pith/KN7S7E2OWGFX5QDBLJ7EQF2F4F/bundle.json","state":"https://pith.science/pith/KN7S7E2OWGFX5QDBLJ7EQF2F4F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KN7S7E2OWGFX5QDBLJ7EQF2F4F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:KN7S7E2OWGFX5QDBLJ7EQF2F4F","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":"026a0a54b1e354b0cadeee53f45765a4b0647fc4837441a60f3287322b78b0c3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-07T02:17:45Z","title_canon_sha256":"4de358289498ff660bb2854c01d0b973f74ee1c0ef4ed5a3afdc1c4abd47aa1a"},"schema_version":"1.0","source":{"id":"2312.03991","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.03991","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"arxiv_version","alias_value":"2312.03991v2","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03991","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"pith_short_12","alias_value":"KN7S7E2OWGFX","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"pith_short_16","alias_value":"KN7S7E2OWGFX5QDB","created_at":"2026-07-05T08:08:53Z"},{"alias_kind":"pith_short_8","alias_value":"KN7S7E2O","created_at":"2026-07-05T08:08:53Z"}],"graph_snapshots":[{"event_id":"sha256:83a1d08b12cd19ba8538b2a4da766691344b95ee086f71d2e53514befd580f31","target":"graph","created_at":"2026-07-05T08:08:53Z","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/2312.03991/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) faces a significant challenge of distribution shift. Model-free offline RL penalizes the Q value for out-of-distribution (OOD) data or constrains the policy closed to the behavior policy to tackle this problem, but this inhibits the exploration of the OOD region. Model-based offline RL, which uses the trained environment model to generate more OOD data and performs conservative policy optimization within that model, has become an effective method for this problem. However, the current model-based algorithms rarely consider agent robustness when incorporating","authors_text":"De-Xing Huang, Guotao Li, Hao Li, Mei-Jiang Gui, Tian-Yu Xiang, Xiao-Hu Zhou, Xiao-Yin Liu, Zeng-Guang Hou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-07T02:17:45Z","title":"MICRO: Model-Based Offline Reinforcement Learning with a Conservative Bellman Operator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03991","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:df53670241fb11765c726feff1813896392d63faaeae3280c030bb1d4fca337a","target":"record","created_at":"2026-07-05T08:08:53Z","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":"026a0a54b1e354b0cadeee53f45765a4b0647fc4837441a60f3287322b78b0c3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-12-07T02:17:45Z","title_canon_sha256":"4de358289498ff660bb2854c01d0b973f74ee1c0ef4ed5a3afdc1c4abd47aa1a"},"schema_version":"1.0","source":{"id":"2312.03991","kind":"arxiv","version":2}},"canonical_sha256":"537f2f934eb18b7ec0615a7e481745e16e473f59c93e4596ec50cfeaf27ce9f3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"537f2f934eb18b7ec0615a7e481745e16e473f59c93e4596ec50cfeaf27ce9f3","first_computed_at":"2026-07-05T08:08:53.321677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:53.321677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HrttV6PnMe5ln5lonJRsD34h75ap9PRMbhAGkfl7+BPW/OTGvnp0dLSq/ExzgaB0cp3Z4jNbqHBpC34S3aTTBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:53.322147Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.03991","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df53670241fb11765c726feff1813896392d63faaeae3280c030bb1d4fca337a","sha256:83a1d08b12cd19ba8538b2a4da766691344b95ee086f71d2e53514befd580f31"],"state_sha256":"303787b450d67e7fd8947fd1ca68a701dcc4a745afc3bc68c538999ccb20b2c1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pbbZuZnF6wDQgEWXIiv7mIKTBAZzdcu3E6b1E8tsBiSPOL+nUxpbgO9ro5jEQRKPFythSUgCfz9f3QCvCarPAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T07:13:00.159399Z","bundle_sha256":"dfe5864c20577b97e73b15a63967775a6f8fbf9262c9b257a13cc2500d085cc7"}}