{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SL4M7I3P5V76JLV7IWSQUB3M6T","short_pith_number":"pith:SL4M7I3P","schema_version":"1.0","canonical_sha256":"92f8cfa36fed7fe4aebf45a50a076cf4f5921e68bec2f49416ce8ac054f3b81b","source":{"kind":"arxiv","id":"2306.08719","version":4},"attestation_state":"computed","paper":{"title":"Off-policy Evaluation in Doubly Inhomogeneous Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Chengchun Shi, Lan Wang, Zeyu Bian, Zhengling Qi","submitted_at":"2023-06-14T19:48:30Z","abstract_excerpt":"This work aims to study off-policy evaluation (OPE) under scenarios where two key reinforcement learning (RL) assumptions -- temporal stationarity and individual homogeneity are both violated. To handle the ``double inhomogeneities\", we propose a class of latent factor models for the reward and observation transition functions, under which we develop a general OPE framework that consists of both model-based and model-free approaches. To our knowledge, this is the first paper that develops statistically sound OPE methods in offline RL with double inhomogeneities. It contributes to a deeper unde"},"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":"2306.08719","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2023-06-14T19:48:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3fd2b7c7ce2524fcfc8a4b1fabdea541788cabae726d2942e493e70c96ff5fab","abstract_canon_sha256":"c4b53332d4b0d07d4a2deb6e37e3220733bfa90829d1a3add6f81b71304d20e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:56:13.058624Z","signature_b64":"+EQCgoxk+5zdK34GwA1FcZn1odLfPI8Blb1BMFkJPCdzQSnJQBgItLh8BxyMqDU1YP/jKc3DAzshCcbUT1BZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92f8cfa36fed7fe4aebf45a50a076cf4f5921e68bec2f49416ce8ac054f3b81b","last_reissued_at":"2026-07-05T08:56:13.058196Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:56:13.058196Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Off-policy Evaluation in Doubly Inhomogeneous Environments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ME","authors_text":"Chengchun Shi, Lan Wang, Zeyu Bian, Zhengling Qi","submitted_at":"2023-06-14T19:48:30Z","abstract_excerpt":"This work aims to study off-policy evaluation (OPE) under scenarios where two key reinforcement learning (RL) assumptions -- temporal stationarity and individual homogeneity are both violated. To handle the ``double inhomogeneities\", we propose a class of latent factor models for the reward and observation transition functions, under which we develop a general OPE framework that consists of both model-based and model-free approaches. To our knowledge, this is the first paper that develops statistically sound OPE methods in offline RL with double inhomogeneities. It contributes to a deeper unde"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.08719","kind":"arxiv","version":4},"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/2306.08719/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":"2306.08719","created_at":"2026-07-05T08:56:13.058252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.08719v4","created_at":"2026-07-05T08:56:13.058252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.08719","created_at":"2026-07-05T08:56:13.058252+00:00"},{"alias_kind":"pith_short_12","alias_value":"SL4M7I3P5V76","created_at":"2026-07-05T08:56:13.058252+00:00"},{"alias_kind":"pith_short_16","alias_value":"SL4M7I3P5V76JLV7","created_at":"2026-07-05T08:56:13.058252+00:00"},{"alias_kind":"pith_short_8","alias_value":"SL4M7I3P","created_at":"2026-07-05T08:56:13.058252+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SL4M7I3P5V76JLV7IWSQUB3M6T","json":"https://pith.science/pith/SL4M7I3P5V76JLV7IWSQUB3M6T.json","graph_json":"https://pith.science/api/pith-number/SL4M7I3P5V76JLV7IWSQUB3M6T/graph.json","events_json":"https://pith.science/api/pith-number/SL4M7I3P5V76JLV7IWSQUB3M6T/events.json","paper":"https://pith.science/paper/SL4M7I3P"},"agent_actions":{"view_html":"https://pith.science/pith/SL4M7I3P5V76JLV7IWSQUB3M6T","download_json":"https://pith.science/pith/SL4M7I3P5V76JLV7IWSQUB3M6T.json","view_paper":"https://pith.science/paper/SL4M7I3P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.08719&json=true","fetch_graph":"https://pith.science/api/pith-number/SL4M7I3P5V76JLV7IWSQUB3M6T/graph.json","fetch_events":"https://pith.science/api/pith-number/SL4M7I3P5V76JLV7IWSQUB3M6T/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SL4M7I3P5V76JLV7IWSQUB3M6T/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SL4M7I3P5V76JLV7IWSQUB3M6T/action/storage_attestation","attest_author":"https://pith.science/pith/SL4M7I3P5V76JLV7IWSQUB3M6T/action/author_attestation","sign_citation":"https://pith.science/pith/SL4M7I3P5V76JLV7IWSQUB3M6T/action/citation_signature","submit_replication":"https://pith.science/pith/SL4M7I3P5V76JLV7IWSQUB3M6T/action/replication_record"}},"created_at":"2026-07-05T08:56:13.058252+00:00","updated_at":"2026-07-05T08:56:13.058252+00:00"}