{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:IHIFATGUK5SQXFLVP6I6IGV6U5","short_pith_number":"pith:IHIFATGU","schema_version":"1.0","canonical_sha256":"41d0504cd457650b95757f91e41abea758807a2914df9f0eb22bb949dc075731","source":{"kind":"arxiv","id":"2403.11841","version":1},"attestation_state":"computed","paper":{"title":"Pessimistic Causal Reinforcement Learning with Mediators for Confounded Offline Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Chengchun Shi, Danyang Wang, Shikai Luo, Will Wei Sun","submitted_at":"2024-03-18T14:51:19Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.11841","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-03-18T14:51:19Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2aaf9bfd654e848d6fa986f185a093fd9054a5872b10c11b6835a1712dc5ee32","abstract_canon_sha256":"78bbe9ca4db1d0d0b4224562b720b2563922fe2c80888c8e24eaf246b4c5cfb5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:32.378267Z","signature_b64":"X0//cdeZuMJyDiNKxmabrBO3WAynVQTHaxbn+1lY0HiiY+tpjm2JrF6j44qerVfQWEhWrxU4fur609MDap40AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"41d0504cd457650b95757f91e41abea758807a2914df9f0eb22bb949dc075731","last_reissued_at":"2026-07-05T07:57:32.377820Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:32.377820Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pessimistic Causal Reinforcement Learning with Mediators for Confounded Offline Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"stat.ML","authors_text":"Chengchun Shi, Danyang Wang, Shikai Luo, Will Wei Sun","submitted_at":"2024-03-18T14:51:19Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11841","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/2403.11841/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.11841","created_at":"2026-07-05T07:57:32.377896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11841v1","created_at":"2026-07-05T07:57:32.377896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11841","created_at":"2026-07-05T07:57:32.377896+00:00"},{"alias_kind":"pith_short_12","alias_value":"IHIFATGUK5SQ","created_at":"2026-07-05T07:57:32.377896+00:00"},{"alias_kind":"pith_short_16","alias_value":"IHIFATGUK5SQXFLV","created_at":"2026-07-05T07:57:32.377896+00:00"},{"alias_kind":"pith_short_8","alias_value":"IHIFATGU","created_at":"2026-07-05T07:57:32.377896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.19002","citing_title":"Semi-pessimistic Reinforcement Learning","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5","json":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5.json","graph_json":"https://pith.science/api/pith-number/IHIFATGUK5SQXFLVP6I6IGV6U5/graph.json","events_json":"https://pith.science/api/pith-number/IHIFATGUK5SQXFLVP6I6IGV6U5/events.json","paper":"https://pith.science/paper/IHIFATGU"},"agent_actions":{"view_html":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5","download_json":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5.json","view_paper":"https://pith.science/paper/IHIFATGU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11841&json=true","fetch_graph":"https://pith.science/api/pith-number/IHIFATGUK5SQXFLVP6I6IGV6U5/graph.json","fetch_events":"https://pith.science/api/pith-number/IHIFATGUK5SQXFLVP6I6IGV6U5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5/action/storage_attestation","attest_author":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5/action/author_attestation","sign_citation":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5/action/citation_signature","submit_replication":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5/action/replication_record"}},"created_at":"2026-07-05T07:57:32.377896+00:00","updated_at":"2026-07-05T07:57:32.377896+00:00"}