{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:37X5GREOWHDQG6XAY223VGB7HD","short_pith_number":"pith:37X5GREO","canonical_record":{"source":{"id":"2405.04307","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-05-07T13:29:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"75ad4000c0c1d3a7021255b8a886887faee968fb7dbd6339c9f2b35062663c30","abstract_canon_sha256":"12fc76960d06550cf1a3076287677c23ae0ba73fa605daf885f7802f256b0a57"},"schema_version":"1.0"},"canonical_sha256":"dfefd3448eb1c7037ae0c6b5ba983f38c25a2673bc7a3ba4dff38c70f24046de","source":{"kind":"arxiv","id":"2405.04307","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04307","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04307v1","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04307","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"pith_short_12","alias_value":"37X5GREOWHDQ","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"pith_short_16","alias_value":"37X5GREOWHDQG6XA","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"pith_short_8","alias_value":"37X5GREO","created_at":"2026-07-05T08:16:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:37X5GREOWHDQG6XAY223VGB7HD","target":"record","payload":{"canonical_record":{"source":{"id":"2405.04307","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-05-07T13:29:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"75ad4000c0c1d3a7021255b8a886887faee968fb7dbd6339c9f2b35062663c30","abstract_canon_sha256":"12fc76960d06550cf1a3076287677c23ae0ba73fa605daf885f7802f256b0a57"},"schema_version":"1.0"},"canonical_sha256":"dfefd3448eb1c7037ae0c6b5ba983f38c25a2673bc7a3ba4dff38c70f24046de","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:35.035295Z","signature_b64":"Y0ZKKw6pNDLwHwmBL32VRCVqhIIOnNcVrom2ovt0NzimKR9ryMIsYvf6KiZnmyl/j/dmpXRGucGGjGwHjBM1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dfefd3448eb1c7037ae0c6b5ba983f38c25a2673bc7a3ba4dff38c70f24046de","last_reissued_at":"2026-07-05T08:16:35.034761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:35.034761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.04307","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":"2026-07-05T08:16:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"peYy8eQxxjX4mxAOdgKIJkGOihr9XWHJtUpUpieayb5yp3LzGuxRc92eL1JTFAdPDJ7qijQkRCy5vB+hnjo6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:14:49.961987Z"},"content_sha256":"dbd799493111496d32ca6d5277aaf5e1667da18586e85682e75003454ad48532","schema_version":"1.0","event_id":"sha256:dbd799493111496d32ca6d5277aaf5e1667da18586e85682e75003454ad48532"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:37X5GREOWHDQG6XAY223VGB7HD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Offline Reinforcement Learning with Inaccurate Simulators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.RO","authors_text":"Feng Wu, Haoyuan Sun, Jinming Ma, Yiwen Hou","submitted_at":"2024-05-07T13:29:41Z","abstract_excerpt":"Offline reinforcement learning (RL) provides a promising approach to avoid costly online interaction with the real environment. However, the performance of offline RL highly depends on the quality of the datasets, which may cause extrapolation error in the learning process. In many robotic applications, an inaccurate simulator is often available. However, the data directly collected from the inaccurate simulator cannot be directly used in offline RL due to the well-known exploration-exploitation dilemma and the dynamic gap between inaccurate simulation and the real environment. To address thes"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04307","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/2405.04307/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":"2026-07-05T08:16:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5R0/EZL9tmNRNkG9lWoKUz4T+r2b5RGj9z/z3AoenD8jPcSBWbE7b4ayOlPczGHm+4Tk2OquX+tjdX48YoEPDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T02:14:49.962503Z"},"content_sha256":"1f6bab88c6e4de92f49273e320064f1aaecfd8fcc49bc7098d7aa9ebf4728829","schema_version":"1.0","event_id":"sha256:1f6bab88c6e4de92f49273e320064f1aaecfd8fcc49bc7098d7aa9ebf4728829"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/37X5GREOWHDQG6XAY223VGB7HD/bundle.json","state_url":"https://pith.science/pith/37X5GREOWHDQG6XAY223VGB7HD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/37X5GREOWHDQG6XAY223VGB7HD/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":"2026-08-11T02:14:49Z","links":{"resolver":"https://pith.science/pith/37X5GREOWHDQG6XAY223VGB7HD","bundle":"https://pith.science/pith/37X5GREOWHDQG6XAY223VGB7HD/bundle.json","state":"https://pith.science/pith/37X5GREOWHDQG6XAY223VGB7HD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/37X5GREOWHDQG6XAY223VGB7HD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:37X5GREOWHDQG6XAY223VGB7HD","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":"12fc76960d06550cf1a3076287677c23ae0ba73fa605daf885f7802f256b0a57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-05-07T13:29:41Z","title_canon_sha256":"75ad4000c0c1d3a7021255b8a886887faee968fb7dbd6339c9f2b35062663c30"},"schema_version":"1.0","source":{"id":"2405.04307","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.04307","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"arxiv_version","alias_value":"2405.04307v1","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04307","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"pith_short_12","alias_value":"37X5GREOWHDQ","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"pith_short_16","alias_value":"37X5GREOWHDQG6XA","created_at":"2026-07-05T08:16:35Z"},{"alias_kind":"pith_short_8","alias_value":"37X5GREO","created_at":"2026-07-05T08:16:35Z"}],"graph_snapshots":[{"event_id":"sha256:1f6bab88c6e4de92f49273e320064f1aaecfd8fcc49bc7098d7aa9ebf4728829","target":"graph","created_at":"2026-07-05T08:16:35Z","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/2405.04307/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) provides a promising approach to avoid costly online interaction with the real environment. However, the performance of offline RL highly depends on the quality of the datasets, which may cause extrapolation error in the learning process. In many robotic applications, an inaccurate simulator is often available. However, the data directly collected from the inaccurate simulator cannot be directly used in offline RL due to the well-known exploration-exploitation dilemma and the dynamic gap between inaccurate simulation and the real environment. To address thes","authors_text":"Feng Wu, Haoyuan Sun, Jinming Ma, Yiwen Hou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-05-07T13:29:41Z","title":"Improving Offline Reinforcement Learning with Inaccurate Simulators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04307","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:dbd799493111496d32ca6d5277aaf5e1667da18586e85682e75003454ad48532","target":"record","created_at":"2026-07-05T08:16:35Z","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":"12fc76960d06550cf1a3076287677c23ae0ba73fa605daf885f7802f256b0a57","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2024-05-07T13:29:41Z","title_canon_sha256":"75ad4000c0c1d3a7021255b8a886887faee968fb7dbd6339c9f2b35062663c30"},"schema_version":"1.0","source":{"id":"2405.04307","kind":"arxiv","version":1}},"canonical_sha256":"dfefd3448eb1c7037ae0c6b5ba983f38c25a2673bc7a3ba4dff38c70f24046de","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dfefd3448eb1c7037ae0c6b5ba983f38c25a2673bc7a3ba4dff38c70f24046de","first_computed_at":"2026-07-05T08:16:35.034761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:16:35.034761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Y0ZKKw6pNDLwHwmBL32VRCVqhIIOnNcVrom2ovt0NzimKR9ryMIsYvf6KiZnmyl/j/dmpXRGucGGjGwHjBM1Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:16:35.035295Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.04307","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbd799493111496d32ca6d5277aaf5e1667da18586e85682e75003454ad48532","sha256:1f6bab88c6e4de92f49273e320064f1aaecfd8fcc49bc7098d7aa9ebf4728829"],"state_sha256":"936bdf276617c6d37af9e9aee3b8a55f78d4466ee5833f9077cdf206174ef30d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pN5owD9KpHM1RBQzDwi5ehVRHAma9dwrEXDCScYvjjYqe7mVxLQaUCmlfRCFUeBXtVG09AhipDKmAEAr+1nCAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T02:14:49.967739Z","bundle_sha256":"8eda0c71ab1b801ad404eac5f124850dfecb4c69751c7fce9a2ffb66f3658796"}}