{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IHIFATGUK5SQXFLVP6I6IGV6U5","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":"78bbe9ca4db1d0d0b4224562b720b2563922fe2c80888c8e24eaf246b4c5cfb5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-03-18T14:51:19Z","title_canon_sha256":"2aaf9bfd654e848d6fa986f185a093fd9054a5872b10c11b6835a1712dc5ee32"},"schema_version":"1.0","source":{"id":"2403.11841","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11841","created_at":"2026-07-05T07:57:32Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11841v1","created_at":"2026-07-05T07:57:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11841","created_at":"2026-07-05T07:57:32Z"},{"alias_kind":"pith_short_12","alias_value":"IHIFATGUK5SQ","created_at":"2026-07-05T07:57:32Z"},{"alias_kind":"pith_short_16","alias_value":"IHIFATGUK5SQXFLV","created_at":"2026-07-05T07:57:32Z"},{"alias_kind":"pith_short_8","alias_value":"IHIFATGU","created_at":"2026-07-05T07:57:32Z"}],"graph_snapshots":[{"event_id":"sha256:e6c394629eec855ad531f52ac81827286099e6986e9c1acf146cdbf194d984f3","target":"graph","created_at":"2026-07-05T07:57:32Z","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/2403.11841/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In real-world scenarios, datasets collected from randomized experiments are often constrained by size, due to limitations in time and budget. As a result, leveraging large observational datasets becomes a more attractive option for achieving high-quality policy learning. However, most existing offline reinforcement learning (RL) methods depend on two key assumptions--unconfoundedness and positivity--which frequently do not hold in observational data contexts. Recognizing these challenges, we propose a novel policy learning algorithm, PESsimistic CAusal Learning (PESCAL). We utilize the mediato","authors_text":"Chengchun Shi, Danyang Wang, Shikai Luo, Will Wei Sun","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-03-18T14:51:19Z","title":"Pessimistic Causal Reinforcement Learning with Mediators for Confounded Offline Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11841","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":"sha256:83eb6793ddfa9489e896ee60f35e4800210a3f23cd63869908a247612785e791","target":"record","created_at":"2026-07-05T07:57:32Z","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":"78bbe9ca4db1d0d0b4224562b720b2563922fe2c80888c8e24eaf246b4c5cfb5","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-03-18T14:51:19Z","title_canon_sha256":"2aaf9bfd654e848d6fa986f185a093fd9054a5872b10c11b6835a1712dc5ee32"},"schema_version":"1.0","source":{"id":"2403.11841","kind":"arxiv","version":1}},"canonical_sha256":"41d0504cd457650b95757f91e41abea758807a2914df9f0eb22bb949dc075731","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41d0504cd457650b95757f91e41abea758807a2914df9f0eb22bb949dc075731","first_computed_at":"2026-07-05T07:57:32.377820Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:32.377820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X0//cdeZuMJyDiNKxmabrBO3WAynVQTHaxbn+1lY0HiiY+tpjm2JrF6j44qerVfQWEhWrxU4fur609MDap40AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:32.378267Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11841","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83eb6793ddfa9489e896ee60f35e4800210a3f23cd63869908a247612785e791","sha256:e6c394629eec855ad531f52ac81827286099e6986e9c1acf146cdbf194d984f3"],"state_sha256":"a93cc63d83d8c8dcc096da54bbc9c4df5af04c1e766afcc4a27262f341ef60bc"}