{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:MVRQELBDABKEN4EJL2O2HEALMF","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":"c7d40a24dded4dbf345552e4ac6ffa6336566b223fec56f8bdf2be066611ae6c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T21:27:22Z","title_canon_sha256":"0b48ff52626c8f0ae10001deafa02c4264c7774cadaed56ef6bb69aa98499587"},"schema_version":"1.0","source":{"id":"2306.01157","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.01157","created_at":"2026-07-05T06:16:38Z"},{"alias_kind":"arxiv_version","alias_value":"2306.01157v1","created_at":"2026-07-05T06:16:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.01157","created_at":"2026-07-05T06:16:38Z"},{"alias_kind":"pith_short_12","alias_value":"MVRQELBDABKE","created_at":"2026-07-05T06:16:38Z"},{"alias_kind":"pith_short_16","alias_value":"MVRQELBDABKEN4EJ","created_at":"2026-07-05T06:16:38Z"},{"alias_kind":"pith_short_8","alias_value":"MVRQELBD","created_at":"2026-07-05T06:16:38Z"}],"graph_snapshots":[{"event_id":"sha256:f5f85a64e083bc5bf0d9617af9387ac2858671c6da503968c6bb9206bf7ff668","target":"graph","created_at":"2026-07-05T06:16:38Z","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/2306.01157/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A prominent challenge of offline reinforcement learning (RL) is the issue of hidden confounding: unobserved variables may influence both the actions taken by the agent and the observed outcomes. Hidden confounding can compromise the validity of any causal conclusion drawn from data and presents a major obstacle to effective offline RL. In the present paper, we tackle the problem of hidden confounding in the nonidentifiable setting. We propose a definition of uncertainty due to hidden confounding bias, termed delphic uncertainty, which uses variation over world models compatible with the observ","authors_text":"Aliz\\'ee Pace, Bernhard Sch\\\"olkopf, Gunnar R\\\"atsch, Guy Tennenholtz, Hugo Y\\`eche","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T21:27:22Z","title":"Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.01157","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":"sha256:9d01ec6064167df9751cf3f763782f5f1703e17a0c4eccfbdf2e473df1f501db","target":"record","created_at":"2026-07-05T06:16:38Z","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":"c7d40a24dded4dbf345552e4ac6ffa6336566b223fec56f8bdf2be066611ae6c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-06-01T21:27:22Z","title_canon_sha256":"0b48ff52626c8f0ae10001deafa02c4264c7774cadaed56ef6bb69aa98499587"},"schema_version":"1.0","source":{"id":"2306.01157","kind":"arxiv","version":1}},"canonical_sha256":"6563022c23005446f0895e9da3900b61608894f2b9176007cb0de9546e065cf2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6563022c23005446f0895e9da3900b61608894f2b9176007cb0de9546e065cf2","first_computed_at":"2026-07-05T06:16:38.786562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:38.786562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"N9B/mfPRh77cSinO3lB4Ibz6WJXSxub6a3Wi+7IBbE3I7tGQHVoP5Mrv0CDe6Kol60jFuDTiEOteijOF21/2Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:38.786986Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.01157","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9d01ec6064167df9751cf3f763782f5f1703e17a0c4eccfbdf2e473df1f501db","sha256:f5f85a64e083bc5bf0d9617af9387ac2858671c6da503968c6bb9206bf7ff668"],"state_sha256":"b7b0a1c0921525abf55fbc7d0387c0c8f1403c1a09af2e24c27115648659c2b0"}