{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:EE6FT336DFRNW4MKQ7IMN4GYXY","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":"4fb7e1081295f80b285251ad83ff290418933b30fc0d14b7ef68f04fb4079add","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T04:07:26Z","title_canon_sha256":"fb53a0c3de21dab911f8d9250717209a8890aae334bf8bcd0d094c67af95a965"},"schema_version":"1.0","source":{"id":"2310.14550","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.14550","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"arxiv_version","alias_value":"2310.14550v3","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14550","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"pith_short_12","alias_value":"EE6FT336DFRN","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"pith_short_16","alias_value":"EE6FT336DFRNW4MK","created_at":"2026-07-05T07:46:25Z"},{"alias_kind":"pith_short_8","alias_value":"EE6FT336","created_at":"2026-07-05T07:46:25Z"}],"graph_snapshots":[{"event_id":"sha256:54b71a2f4cd85c45cd85a1ea7be1415db19704e4ca38539ce9fa377ab0503898","target":"graph","created_at":"2026-07-05T07:46:25Z","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/2310.14550/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate the problem of corruption robustness in offline reinforcement learning (RL) with general function approximation, where an adversary can corrupt each sample in the offline dataset, and the corruption level $\\zeta\\geq0$ quantifies the cumulative corruption amount over $n$ episodes and $H$ steps. Our goal is to find a policy that is robust to such corruption and minimizes the suboptimality gap with respect to the optimal policy for the uncorrupted Markov decision processes (MDPs). Drawing inspiration from the uncertainty-weighting technique from the robust online RL setting \\citep{","authors_text":"Chenlu Ye, Quanquan Gu, Rui Yang, Tong Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T04:07:26Z","title":"Corruption-Robust Offline Reinforcement Learning with General Function Approximation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14550","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:feec1970b3073684bf0f1902f209de857408c7ecb03b29524a3f351effbcfa3b","target":"record","created_at":"2026-07-05T07:46:25Z","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":"4fb7e1081295f80b285251ad83ff290418933b30fc0d14b7ef68f04fb4079add","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-23T04:07:26Z","title_canon_sha256":"fb53a0c3de21dab911f8d9250717209a8890aae334bf8bcd0d094c67af95a965"},"schema_version":"1.0","source":{"id":"2310.14550","kind":"arxiv","version":3}},"canonical_sha256":"213c59ef7e1962db718a87d0c6f0d8be27bd9019da418d8d3be5ddf3d3608dfd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"213c59ef7e1962db718a87d0c6f0d8be27bd9019da418d8d3be5ddf3d3608dfd","first_computed_at":"2026-07-05T07:46:25.207633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:25.207633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"osFQGJ5voIez9rAEcoUTGZYZF2iMcwyxTv7arBQFQgaeRNxdbgtU5qVypLNznGL4DwsP/4HIkDcQ0Qme4SX9Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:25.208060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.14550","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:feec1970b3073684bf0f1902f209de857408c7ecb03b29524a3f351effbcfa3b","sha256:54b71a2f4cd85c45cd85a1ea7be1415db19704e4ca38539ce9fa377ab0503898"],"state_sha256":"57e4ecca990b214b504697467001ca4d01dd36bf569934169648d2c9f41311c6"}