{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2012:Q5YTG43OS2PPYYUVHVC3NMBLLE","short_pith_number":"pith:Q5YTG43O","schema_version":"1.0","canonical_sha256":"877133736e969efc62953d45b6b02b59349ed37e389ccc01060303b7ea53e44d","source":{"kind":"arxiv","id":"1205.6659","version":1},"attestation_state":"computed","paper":{"title":"Q-learning with censored data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Michael R. Kosorok, Yair Goldberg","submitted_at":"2012-05-30T13:08:21Z","abstract_excerpt":"We develop methodology for a multistage decision problem with flexible number of stages in which the rewards are survival times that are subject to censoring. We present a novel Q-learning algorithm that is adjusted for censored data and allows a flexible number of stages. We provide finite sample bounds on the generalization error of the policy learned by the algorithm, and show that when the optimal Q-function belongs to the approximation space, the expected survival time for policies obtained by the algorithm converges to that of the optimal policy. We simulate a multistage clinical trial w"},"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":"1205.6659","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2012-05-30T13:08:21Z","cross_cats_sorted":["stat.TH"],"title_canon_sha256":"8234238d4b6f9e283bfc32bd6732fff3bacebbcabe06b3ae123b9d2249f18d5d","abstract_canon_sha256":"5fdd63d5badcdb9ac7c4cf808f2ef839fc3d6b7118dba9cd549e242665b9204e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:54:38.297306Z","signature_b64":"HvRI5DEIfl50RyoH2ZkEllRHwTfhb+HxQrKWWry6oedQj3NmezJArl3v1fmJ9r9l1/NCjyz+F7o5opxdOUcsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"877133736e969efc62953d45b6b02b59349ed37e389ccc01060303b7ea53e44d","last_reissued_at":"2026-05-18T03:54:38.296633Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:54:38.296633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Q-learning with censored data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.TH"],"primary_cat":"math.ST","authors_text":"Michael R. Kosorok, Yair Goldberg","submitted_at":"2012-05-30T13:08:21Z","abstract_excerpt":"We develop methodology for a multistage decision problem with flexible number of stages in which the rewards are survival times that are subject to censoring. We present a novel Q-learning algorithm that is adjusted for censored data and allows a flexible number of stages. We provide finite sample bounds on the generalization error of the policy learned by the algorithm, and show that when the optimal Q-function belongs to the approximation space, the expected survival time for policies obtained by the algorithm converges to that of the optimal policy. We simulate a multistage clinical trial w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.6659","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":""},"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":"1205.6659","created_at":"2026-05-18T03:54:38.296732+00:00"},{"alias_kind":"arxiv_version","alias_value":"1205.6659v1","created_at":"2026-05-18T03:54:38.296732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.6659","created_at":"2026-05-18T03:54:38.296732+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q5YTG43OS2PP","created_at":"2026-05-18T12:27:18.751474+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q5YTG43OS2PPYYUV","created_at":"2026-05-18T12:27:18.751474+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q5YTG43O","created_at":"2026-05-18T12:27:18.751474+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/Q5YTG43OS2PPYYUVHVC3NMBLLE","json":"https://pith.science/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE.json","graph_json":"https://pith.science/api/pith-number/Q5YTG43OS2PPYYUVHVC3NMBLLE/graph.json","events_json":"https://pith.science/api/pith-number/Q5YTG43OS2PPYYUVHVC3NMBLLE/events.json","paper":"https://pith.science/paper/Q5YTG43O"},"agent_actions":{"view_html":"https://pith.science/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE","download_json":"https://pith.science/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE.json","view_paper":"https://pith.science/paper/Q5YTG43O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1205.6659&json=true","fetch_graph":"https://pith.science/api/pith-number/Q5YTG43OS2PPYYUVHVC3NMBLLE/graph.json","fetch_events":"https://pith.science/api/pith-number/Q5YTG43OS2PPYYUVHVC3NMBLLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE/action/storage_attestation","attest_author":"https://pith.science/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE/action/author_attestation","sign_citation":"https://pith.science/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE/action/citation_signature","submit_replication":"https://pith.science/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE/action/replication_record"}},"created_at":"2026-05-18T03:54:38.296732+00:00","updated_at":"2026-05-18T03:54:38.296732+00:00"}