{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IHIFATGUK5SQXFLVP6I6IGV6U5","short_pith_number":"pith:IHIFATGU","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"},"canonical_sha256":"41d0504cd457650b95757f91e41abea758807a2914df9f0eb22bb949dc075731","source":{"kind":"arxiv","id":"2403.11841","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IHIFATGUK5SQXFLVP6I6IGV6U5","target":"record","payload":{"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"},"canonical_sha256":"41d0504cd457650b95757f91e41abea758807a2914df9f0eb22bb949dc075731","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"},"source_kind":"arxiv","source_id":"2403.11841","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:57:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WdzBkm40ogg5LSE6vCwdw4SptLxmkgGOeSCGoEfYscvchSFuUyh7JLfERhMWm2YUu6ROoLEDVMHLhpJ5IFXEAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T07:48:10.149346Z"},"content_sha256":"83eb6793ddfa9489e896ee60f35e4800210a3f23cd63869908a247612785e791","schema_version":"1.0","event_id":"sha256:83eb6793ddfa9489e896ee60f35e4800210a3f23cd63869908a247612785e791"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IHIFATGUK5SQXFLVP6I6IGV6U5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:57:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ceoNxjCIixpLhSWrnkxUn/+RocuiacbGW4i7r35pR1VHpswMZQwzw+Y4cU7m8ovdxzI51OH3qNHOqYUpLlZgAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T07:48:10.149907Z"},"content_sha256":"e6c394629eec855ad531f52ac81827286099e6986e9c1acf146cdbf194d984f3","schema_version":"1.0","event_id":"sha256:e6c394629eec855ad531f52ac81827286099e6986e9c1acf146cdbf194d984f3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5/bundle.json","state_url":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IHIFATGUK5SQXFLVP6I6IGV6U5/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":"2026-08-11T07:48:10Z","links":{"resolver":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5","bundle":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5/bundle.json","state":"https://pith.science/pith/IHIFATGUK5SQXFLVP6I6IGV6U5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IHIFATGUK5SQXFLVP6I6IGV6U5/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sazewo7RQSAjIiXIEJfqS+D+5UXJISAhmHHdxl+a0trbWWtvFUdYraCkluk20GquBWzEPq6w0R4KrVqi3IaJDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T07:48:10.154518Z","bundle_sha256":"3928fa14c3866fb88887a29a4455bd31ca7a9f07e5113521f516417f36a54358"}}