{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CR7KTLAS362DBU3HTAZMHGM3BA","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":"42e80e0751898f152b0cdc3f96753e66cdc0ba7c30f9f2ca40fb9159bcf2f0ac","cross_cats_sorted":["stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-14T05:33:19Z","title_canon_sha256":"4c9dd3eb22947d4524bc7b31fde91bdb082982f6ee46c57b1c0a667d2784e9ba"},"schema_version":"1.0","source":{"id":"2210.07536","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.07536","created_at":"2026-07-05T05:06:38Z"},{"alias_kind":"arxiv_version","alias_value":"2210.07536v1","created_at":"2026-07-05T05:06:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.07536","created_at":"2026-07-05T05:06:38Z"},{"alias_kind":"pith_short_12","alias_value":"CR7KTLAS362D","created_at":"2026-07-05T05:06:38Z"},{"alias_kind":"pith_short_16","alias_value":"CR7KTLAS362DBU3H","created_at":"2026-07-05T05:06:38Z"},{"alias_kind":"pith_short_8","alias_value":"CR7KTLAS","created_at":"2026-07-05T05:06:38Z"}],"graph_snapshots":[{"event_id":"sha256:5a4f5e7f90d18e65748b9d68721c4e6fa4e05053af1390d7e63ffba934f0f48f","target":"graph","created_at":"2026-07-05T05:06:38Z","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/2210.07536/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Randomized experiments (a.k.a. A/B tests) are a powerful tool for estimating treatment effects, to inform decisions making in business, healthcare and other applications. In many problems, the treatment has a lasting effect that evolves over time. A limitation with randomized experiments is that they do not easily extend to measure long-term effects, since running long experiments is time-consuming and expensive. In this paper, we take a reinforcement learning (RL) approach that estimates the average reward in a Markov process. Motivated by real-world scenarios where the observed state transit","authors_text":"Lihong Li, Stephanie Zhang, Yiheng Duan, Ziyang Tang","cross_cats":["stat.ME","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-14T05:33:19Z","title":"A Reinforcement Learning Approach to Estimating Long-term Treatment Effects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.07536","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:d050cc90b2081b86efd53405388218fb99acda995726b7e48ac104bfecbe2580","target":"record","created_at":"2026-07-05T05:06:38Z","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":"42e80e0751898f152b0cdc3f96753e66cdc0ba7c30f9f2ca40fb9159bcf2f0ac","cross_cats_sorted":["stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-14T05:33:19Z","title_canon_sha256":"4c9dd3eb22947d4524bc7b31fde91bdb082982f6ee46c57b1c0a667d2784e9ba"},"schema_version":"1.0","source":{"id":"2210.07536","kind":"arxiv","version":1}},"canonical_sha256":"147ea9ac12dfb430d3679832c3999b0814c2c49b40017fd894be018ae408735d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"147ea9ac12dfb430d3679832c3999b0814c2c49b40017fd894be018ae408735d","first_computed_at":"2026-07-05T05:06:38.487867Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:06:38.487867Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1tKdhHpgeRdiVBa/N4RtwCBNkRyAk4lcQ8hoNV2UcRNcq1QhGcdMiF9SM4QvQwNt2S8jtUqucwMtKkrUHnlPBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:06:38.488201Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.07536","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d050cc90b2081b86efd53405388218fb99acda995726b7e48ac104bfecbe2580","sha256:5a4f5e7f90d18e65748b9d68721c4e6fa4e05053af1390d7e63ffba934f0f48f"],"state_sha256":"04d0beadea6c6be24ac9a597b3e2cafe5d20ce80a9c2ed51cd9ea2dbddb7c514"}