{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MTPCHG33LSXM4FR3DOQVAZ7CVF","short_pith_number":"pith:MTPCHG33","schema_version":"1.0","canonical_sha256":"64de239b7b5caece163b1ba15067e2a95bae02539ef3323e5ab906740dc89df0","source":{"kind":"arxiv","id":"2212.07486","version":1},"attestation_state":"computed","paper":{"title":"Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brahma S. Pavse, Josiah P. Hanna","submitted_at":"2022-12-14T20:07:33Z","abstract_excerpt":"We consider the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of an evaluation policy, $\\pi_e$, using a fixed dataset, $\\mathcal{D}$, collected by one or more policies that may be different from $\\pi_e$. Current OPE algorithms may produce poor OPE estimates under policy distribution shift i.e., when the probability of a particular state-action pair occurring under $\\pi_e$ is very different from the probability of that same pair occurring in $\\mathcal{D}$ (Voloshin et al. 2021, Fu et al. 2021). In this work, we propose to im"},"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":"2212.07486","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-12-14T20:07:33Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"366e92a09711480009398387508bfdc782d938af8c05e7548179b3b4c9734bca","abstract_canon_sha256":"f4bdec4ec4304e0cf9cb357222b05c2487b14855b8b3a3c42f831c884b13f0be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:25:33.496458Z","signature_b64":"GdbhhpBzY+B1x4DsmKz8JM17oDmmGu39CKS5tFYwJPZDlp5MCXq2OwcZ2KD2OF2VN6ojXn2/cNn2KxCZEoeXBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64de239b7b5caece163b1ba15067e2a95bae02539ef3323e5ab906740dc89df0","last_reissued_at":"2026-07-05T05:25:33.495974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:25:33.495974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Marginalized Importance Sampling to High-Dimensional State-Spaces via State Abstraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Brahma S. Pavse, Josiah P. Hanna","submitted_at":"2022-12-14T20:07:33Z","abstract_excerpt":"We consider the problem of off-policy evaluation (OPE) in reinforcement learning (RL), where the goal is to estimate the performance of an evaluation policy, $\\pi_e$, using a fixed dataset, $\\mathcal{D}$, collected by one or more policies that may be different from $\\pi_e$. Current OPE algorithms may produce poor OPE estimates under policy distribution shift i.e., when the probability of a particular state-action pair occurring under $\\pi_e$ is very different from the probability of that same pair occurring in $\\mathcal{D}$ (Voloshin et al. 2021, Fu et al. 2021). In this work, we propose to im"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.07486","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/2212.07486/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":"2212.07486","created_at":"2026-07-05T05:25:33.496027+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.07486v1","created_at":"2026-07-05T05:25:33.496027+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.07486","created_at":"2026-07-05T05:25:33.496027+00:00"},{"alias_kind":"pith_short_12","alias_value":"MTPCHG33LSXM","created_at":"2026-07-05T05:25:33.496027+00:00"},{"alias_kind":"pith_short_16","alias_value":"MTPCHG33LSXM4FR3","created_at":"2026-07-05T05:25:33.496027+00:00"},{"alias_kind":"pith_short_8","alias_value":"MTPCHG33","created_at":"2026-07-05T05:25:33.496027+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.19395","citing_title":"Concept-driven Off Policy Evaluation","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF","json":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF.json","graph_json":"https://pith.science/api/pith-number/MTPCHG33LSXM4FR3DOQVAZ7CVF/graph.json","events_json":"https://pith.science/api/pith-number/MTPCHG33LSXM4FR3DOQVAZ7CVF/events.json","paper":"https://pith.science/paper/MTPCHG33"},"agent_actions":{"view_html":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF","download_json":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF.json","view_paper":"https://pith.science/paper/MTPCHG33","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.07486&json=true","fetch_graph":"https://pith.science/api/pith-number/MTPCHG33LSXM4FR3DOQVAZ7CVF/graph.json","fetch_events":"https://pith.science/api/pith-number/MTPCHG33LSXM4FR3DOQVAZ7CVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF/action/storage_attestation","attest_author":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF/action/author_attestation","sign_citation":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF/action/citation_signature","submit_replication":"https://pith.science/pith/MTPCHG33LSXM4FR3DOQVAZ7CVF/action/replication_record"}},"created_at":"2026-07-05T05:25:33.496027+00:00","updated_at":"2026-07-05T05:25:33.496027+00:00"}