{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:I7YKEDGHJ6RFEWQ77YNKQDPMBE","short_pith_number":"pith:I7YKEDGH","schema_version":"1.0","canonical_sha256":"47f0a20cc74fa2525a1ffe1aa80dec092a408d01f639f40066f1af531d3afd8c","source":{"kind":"arxiv","id":"1905.10116","version":2},"attestation_state":"computed","paper":{"title":"Semi-Parametric Efficient Policy Learning with Continuous Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"econ.EM","authors_text":"Greg Lewis, Mert Demirer, Vasilis Syrgkanis, Victor Chernozhukov","submitted_at":"2019-05-24T09:51:21Z","abstract_excerpt":"We consider off-policy evaluation and optimization with continuous action spaces. We focus on observational data where the data collection policy is unknown and needs to be estimated. We take a semi-parametric approach where the value function takes a known parametric form in the treatment, but we are agnostic on how it depends on the observed contexts. We propose a doubly robust off-policy estimate for this setting and show that off-policy optimization based on this estimate is robust to estimation errors of the policy function or the regression model. Our results also apply if the model does"},"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":"1905.10116","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"econ.EM","submitted_at":"2019-05-24T09:51:21Z","cross_cats_sorted":["cs.LG","math.ST","stat.ML","stat.TH"],"title_canon_sha256":"04b53b83e1eeb8888b0c97fe4408a2eb5fc69083e1fd910a8e57bda4939114e6","abstract_canon_sha256":"791653e646390dd16bc12ac607ef446aff98bb05247b06eb93b571b2e2e4e1ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:40:03.428007Z","signature_b64":"hyZ7xDrm7vAqfDgJs2VZyAwWVbqJwNiG4c0LKg1eGMb++VDl4hCnNMsBEqJvLm6Qc0sN76MyXXfPzFwyP6XgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47f0a20cc74fa2525a1ffe1aa80dec092a408d01f639f40066f1af531d3afd8c","last_reissued_at":"2026-05-17T23:40:03.427345Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:40:03.427345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semi-Parametric Efficient Policy Learning with Continuous Actions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.ST","stat.ML","stat.TH"],"primary_cat":"econ.EM","authors_text":"Greg Lewis, Mert Demirer, Vasilis Syrgkanis, Victor Chernozhukov","submitted_at":"2019-05-24T09:51:21Z","abstract_excerpt":"We consider off-policy evaluation and optimization with continuous action spaces. We focus on observational data where the data collection policy is unknown and needs to be estimated. We take a semi-parametric approach where the value function takes a known parametric form in the treatment, but we are agnostic on how it depends on the observed contexts. We propose a doubly robust off-policy estimate for this setting and show that off-policy optimization based on this estimate is robust to estimation errors of the policy function or the regression model. Our results also apply if the model does"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10116","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1905.10116","created_at":"2026-05-17T23:40:03.427441+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.10116v2","created_at":"2026-05-17T23:40:03.427441+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10116","created_at":"2026-05-17T23:40:03.427441+00:00"},{"alias_kind":"pith_short_12","alias_value":"I7YKEDGHJ6RF","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_16","alias_value":"I7YKEDGHJ6RFEWQ7","created_at":"2026-05-18T12:33:18.533446+00:00"},{"alias_kind":"pith_short_8","alias_value":"I7YKEDGH","created_at":"2026-05-18T12:33:18.533446+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12235","citing_title":"Optimal Policy Learning under Budget and Coverage Constraints","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I7YKEDGHJ6RFEWQ77YNKQDPMBE","json":"https://pith.science/pith/I7YKEDGHJ6RFEWQ77YNKQDPMBE.json","graph_json":"https://pith.science/api/pith-number/I7YKEDGHJ6RFEWQ77YNKQDPMBE/graph.json","events_json":"https://pith.science/api/pith-number/I7YKEDGHJ6RFEWQ77YNKQDPMBE/events.json","paper":"https://pith.science/paper/I7YKEDGH"},"agent_actions":{"view_html":"https://pith.science/pith/I7YKEDGHJ6RFEWQ77YNKQDPMBE","download_json":"https://pith.science/pith/I7YKEDGHJ6RFEWQ77YNKQDPMBE.json","view_paper":"https://pith.science/paper/I7YKEDGH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.10116&json=true","fetch_graph":"https://pith.science/api/pith-number/I7YKEDGHJ6RFEWQ77YNKQDPMBE/graph.json","fetch_events":"https://pith.science/api/pith-number/I7YKEDGHJ6RFEWQ77YNKQDPMBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I7YKEDGHJ6RFEWQ77YNKQDPMBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I7YKEDGHJ6RFEWQ77YNKQDPMBE/action/storage_attestation","attest_author":"https://pith.science/pith/I7YKEDGHJ6RFEWQ77YNKQDPMBE/action/author_attestation","sign_citation":"https://pith.science/pith/I7YKEDGHJ6RFEWQ77YNKQDPMBE/action/citation_signature","submit_replication":"https://pith.science/pith/I7YKEDGHJ6RFEWQ77YNKQDPMBE/action/replication_record"}},"created_at":"2026-05-17T23:40:03.427441+00:00","updated_at":"2026-05-17T23:40:03.427441+00:00"}