{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5WNKS43IJ7SMPXR7DFZ74UYU2J","short_pith_number":"pith:5WNKS43I","canonical_record":{"source":{"id":"2310.12955","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T17:54:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"515387e6379fea2be07ae2b438cb563a7baae17afe1299e6b27fcbefc52c49bb","abstract_canon_sha256":"8ed6603b94cfa118bb9089ec7718ca03431de233e36159383b4d5f91cca3b9f3"},"schema_version":"1.0"},"canonical_sha256":"ed9aa973684fe4c7de3f1973fe5314d27245bfddea3939cf83d5a14602ed3d73","source":{"kind":"arxiv","id":"2310.12955","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12955","created_at":"2026-07-05T07:54:05Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12955v3","created_at":"2026-07-05T07:54:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12955","created_at":"2026-07-05T07:54:05Z"},{"alias_kind":"pith_short_12","alias_value":"5WNKS43IJ7SM","created_at":"2026-07-05T07:54:05Z"},{"alias_kind":"pith_short_16","alias_value":"5WNKS43IJ7SMPXR7","created_at":"2026-07-05T07:54:05Z"},{"alias_kind":"pith_short_8","alias_value":"5WNKS43I","created_at":"2026-07-05T07:54:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5WNKS43IJ7SMPXR7DFZ74UYU2J","target":"record","payload":{"canonical_record":{"source":{"id":"2310.12955","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T17:54:39Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"515387e6379fea2be07ae2b438cb563a7baae17afe1299e6b27fcbefc52c49bb","abstract_canon_sha256":"8ed6603b94cfa118bb9089ec7718ca03431de233e36159383b4d5f91cca3b9f3"},"schema_version":"1.0"},"canonical_sha256":"ed9aa973684fe4c7de3f1973fe5314d27245bfddea3939cf83d5a14602ed3d73","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:05.243718Z","signature_b64":"5xGSrxq9rdCpH9loFZdTgheYS3/lAAdFNlEPAbphtDvzuhAGd0iKslazIwPlXW8UepfPGC7jVltq9Q6orOXRCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed9aa973684fe4c7de3f1973fe5314d27245bfddea3939cf83d5a14602ed3d73","last_reissued_at":"2026-07-05T07:54:05.243191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:05.243191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.12955","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:54:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Hha6f4gy3EpcK8nPwtkbOScCrKO0itiQ3nUTCs1pnwhRnIcJOdxFxhmMlXH+847O4y45fid74aSqJHqVYjqCDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:43:36.954461Z"},"content_sha256":"da9a510abfa9228720244a98d762debb121358306c09ee6e0f6c186d74f50903","schema_version":"1.0","event_id":"sha256:da9a510abfa9228720244a98d762debb121358306c09ee6e0f6c186d74f50903"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5WNKS43IJ7SMPXR7DFZ74UYU2J","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Amy Zhang, Chongjie Zhang, Han Zhong, Jiawei Xu, Lei Han, Rui Yang, Tong Zhang","submitted_at":"2023-10-19T17:54:39Z","abstract_excerpt":"Offline reinforcement learning (RL) presents a promising approach for learning reinforced policies from offline datasets without the need for costly or unsafe interactions with the environment. However, datasets collected by humans in real-world environments are often noisy and may even be maliciously corrupted, which can significantly degrade the performance of offline RL. In this work, we first investigate the performance of current offline RL algorithms under comprehensive data corruption, including states, actions, rewards, and dynamics. Our extensive experiments reveal that implicit Q-lea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12955","kind":"arxiv","version":3},"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/2310.12955/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":"2026-07-05T07:54:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1kfmMuIhrBhLyjjeuDDlaA9ro7z/2wIYntihh/3tLTLnv3vogf3A+cqQDCsjvTAE0Yq0/rx8rx46ihTS1kF+CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:43:36.954981Z"},"content_sha256":"0bdf0790d391f7c027f4e04d02ccdf538e01974047f301c823b69eb3810d312f","schema_version":"1.0","event_id":"sha256:0bdf0790d391f7c027f4e04d02ccdf538e01974047f301c823b69eb3810d312f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5WNKS43IJ7SMPXR7DFZ74UYU2J/bundle.json","state_url":"https://pith.science/pith/5WNKS43IJ7SMPXR7DFZ74UYU2J/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5WNKS43IJ7SMPXR7DFZ74UYU2J/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":"2026-08-08T03:43:36Z","links":{"resolver":"https://pith.science/pith/5WNKS43IJ7SMPXR7DFZ74UYU2J","bundle":"https://pith.science/pith/5WNKS43IJ7SMPXR7DFZ74UYU2J/bundle.json","state":"https://pith.science/pith/5WNKS43IJ7SMPXR7DFZ74UYU2J/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5WNKS43IJ7SMPXR7DFZ74UYU2J/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5WNKS43IJ7SMPXR7DFZ74UYU2J","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":"8ed6603b94cfa118bb9089ec7718ca03431de233e36159383b4d5f91cca3b9f3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T17:54:39Z","title_canon_sha256":"515387e6379fea2be07ae2b438cb563a7baae17afe1299e6b27fcbefc52c49bb"},"schema_version":"1.0","source":{"id":"2310.12955","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.12955","created_at":"2026-07-05T07:54:05Z"},{"alias_kind":"arxiv_version","alias_value":"2310.12955v3","created_at":"2026-07-05T07:54:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12955","created_at":"2026-07-05T07:54:05Z"},{"alias_kind":"pith_short_12","alias_value":"5WNKS43IJ7SM","created_at":"2026-07-05T07:54:05Z"},{"alias_kind":"pith_short_16","alias_value":"5WNKS43IJ7SMPXR7","created_at":"2026-07-05T07:54:05Z"},{"alias_kind":"pith_short_8","alias_value":"5WNKS43I","created_at":"2026-07-05T07:54:05Z"}],"graph_snapshots":[{"event_id":"sha256:0bdf0790d391f7c027f4e04d02ccdf538e01974047f301c823b69eb3810d312f","target":"graph","created_at":"2026-07-05T07:54:05Z","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/2310.12955/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning (RL) presents a promising approach for learning reinforced policies from offline datasets without the need for costly or unsafe interactions with the environment. However, datasets collected by humans in real-world environments are often noisy and may even be maliciously corrupted, which can significantly degrade the performance of offline RL. In this work, we first investigate the performance of current offline RL algorithms under comprehensive data corruption, including states, actions, rewards, and dynamics. Our extensive experiments reveal that implicit Q-lea","authors_text":"Amy Zhang, Chongjie Zhang, Han Zhong, Jiawei Xu, Lei Han, Rui Yang, Tong Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T17:54:39Z","title":"Towards Robust Offline Reinforcement Learning under Diverse Data Corruption"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12955","kind":"arxiv","version":3},"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:da9a510abfa9228720244a98d762debb121358306c09ee6e0f6c186d74f50903","target":"record","created_at":"2026-07-05T07:54:05Z","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":"8ed6603b94cfa118bb9089ec7718ca03431de233e36159383b4d5f91cca3b9f3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-19T17:54:39Z","title_canon_sha256":"515387e6379fea2be07ae2b438cb563a7baae17afe1299e6b27fcbefc52c49bb"},"schema_version":"1.0","source":{"id":"2310.12955","kind":"arxiv","version":3}},"canonical_sha256":"ed9aa973684fe4c7de3f1973fe5314d27245bfddea3939cf83d5a14602ed3d73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed9aa973684fe4c7de3f1973fe5314d27245bfddea3939cf83d5a14602ed3d73","first_computed_at":"2026-07-05T07:54:05.243191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:05.243191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5xGSrxq9rdCpH9loFZdTgheYS3/lAAdFNlEPAbphtDvzuhAGd0iKslazIwPlXW8UepfPGC7jVltq9Q6orOXRCg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:05.243718Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.12955","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da9a510abfa9228720244a98d762debb121358306c09ee6e0f6c186d74f50903","sha256:0bdf0790d391f7c027f4e04d02ccdf538e01974047f301c823b69eb3810d312f"],"state_sha256":"52539e6acac3dad9eebc00f114f9648bafb16de179b65cf4f9253b7f45519ea3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sOtHYdjR3xtOoWUzlv2AwztCg0X7aZrudiU6O288FkqExY4OS0Tc/qb7AqSQ89OdLFko6OeFOIa5pFJJ6JAsAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:43:36.960236Z","bundle_sha256":"5cf86febc55b2e24d501c0ce259af0beb217db8fcb09710af2d3dfa160bedad4"}}