{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:Q5YTG43OS2PPYYUVHVC3NMBLLE","short_pith_number":"pith:Q5YTG43O","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"},"canonical_sha256":"877133736e969efc62953d45b6b02b59349ed37e389ccc01060303b7ea53e44d","source":{"kind":"arxiv","id":"1205.6659","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.6659","created_at":"2026-05-18T03:54:38Z"},{"alias_kind":"arxiv_version","alias_value":"1205.6659v1","created_at":"2026-05-18T03:54:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.6659","created_at":"2026-05-18T03:54:38Z"},{"alias_kind":"pith_short_12","alias_value":"Q5YTG43OS2PP","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"Q5YTG43OS2PPYYUV","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"Q5YTG43O","created_at":"2026-05-18T12:27:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:Q5YTG43OS2PPYYUVHVC3NMBLLE","target":"record","payload":{"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"},"canonical_sha256":"877133736e969efc62953d45b6b02b59349ed37e389ccc01060303b7ea53e44d","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"},"source_kind":"arxiv","source_id":"1205.6659","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:54:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZkF++/XJ3aJuKN2af+2to5DzRO6xT1bqjuDfMsx/nyq+WnHtj5oM05tMhUcSUUCK3fbtex+KWXh014H5S+SbBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T23:19:31.308059Z"},"content_sha256":"a8b3703b244b6e71bab8f1dfe67c376d0fcb6ca13b2c74d8e01b620c3ff7b50b","schema_version":"1.0","event_id":"sha256:a8b3703b244b6e71bab8f1dfe67c376d0fcb6ca13b2c74d8e01b620c3ff7b50b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:Q5YTG43OS2PPYYUVHVC3NMBLLE","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:54:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h/W1sGznqWj349lrswr/flocIr3rYHjSNhgSk6Kf8WVVtJQMXoKIluK4xO/yYOC3tOIEbDsbqwS8NUrSUrCYCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-22T23:19:31.308415Z"},"content_sha256":"320fcce676d0cd0f5cf6541979d36e555696ce2b5d8ffd8086f11b16b87dfceb","schema_version":"1.0","event_id":"sha256:320fcce676d0cd0f5cf6541979d36e555696ce2b5d8ffd8086f11b16b87dfceb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE/bundle.json","state_url":"https://pith.science/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-22T23:19:31Z","links":{"resolver":"https://pith.science/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE","bundle":"https://pith.science/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE/bundle.json","state":"https://pith.science/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q5YTG43OS2PPYYUVHVC3NMBLLE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:Q5YTG43OS2PPYYUVHVC3NMBLLE","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":"5fdd63d5badcdb9ac7c4cf808f2ef839fc3d6b7118dba9cd549e242665b9204e","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2012-05-30T13:08:21Z","title_canon_sha256":"8234238d4b6f9e283bfc32bd6732fff3bacebbcabe06b3ae123b9d2249f18d5d"},"schema_version":"1.0","source":{"id":"1205.6659","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1205.6659","created_at":"2026-05-18T03:54:38Z"},{"alias_kind":"arxiv_version","alias_value":"1205.6659v1","created_at":"2026-05-18T03:54:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1205.6659","created_at":"2026-05-18T03:54:38Z"},{"alias_kind":"pith_short_12","alias_value":"Q5YTG43OS2PP","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_16","alias_value":"Q5YTG43OS2PPYYUV","created_at":"2026-05-18T12:27:18Z"},{"alias_kind":"pith_short_8","alias_value":"Q5YTG43O","created_at":"2026-05-18T12:27:18Z"}],"graph_snapshots":[{"event_id":"sha256:320fcce676d0cd0f5cf6541979d36e555696ce2b5d8ffd8086f11b16b87dfceb","target":"graph","created_at":"2026-05-18T03:54:38Z","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"},"paper":{"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","authors_text":"Michael R. Kosorok, Yair Goldberg","cross_cats":["stat.TH"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2012-05-30T13:08:21Z","title":"Q-learning with censored data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1205.6659","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:a8b3703b244b6e71bab8f1dfe67c376d0fcb6ca13b2c74d8e01b620c3ff7b50b","target":"record","created_at":"2026-05-18T03:54:38Z","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":"5fdd63d5badcdb9ac7c4cf808f2ef839fc3d6b7118dba9cd549e242665b9204e","cross_cats_sorted":["stat.TH"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"math.ST","submitted_at":"2012-05-30T13:08:21Z","title_canon_sha256":"8234238d4b6f9e283bfc32bd6732fff3bacebbcabe06b3ae123b9d2249f18d5d"},"schema_version":"1.0","source":{"id":"1205.6659","kind":"arxiv","version":1}},"canonical_sha256":"877133736e969efc62953d45b6b02b59349ed37e389ccc01060303b7ea53e44d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"877133736e969efc62953d45b6b02b59349ed37e389ccc01060303b7ea53e44d","first_computed_at":"2026-05-18T03:54:38.296633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:54:38.296633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HvRI5DEIfl50RyoH2ZkEllRHwTfhb+HxQrKWWry6oedQj3NmezJArl3v1fmJ9r9l1/NCjyz+F7o5opxdOUcsBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:54:38.297306Z","signed_message":"canonical_sha256_bytes"},"source_id":"1205.6659","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8b3703b244b6e71bab8f1dfe67c376d0fcb6ca13b2c74d8e01b620c3ff7b50b","sha256:320fcce676d0cd0f5cf6541979d36e555696ce2b5d8ffd8086f11b16b87dfceb"],"state_sha256":"886198aca09fb1c1b3fc6495d1cb2de56538c0dd33c6b089765e7d6ae554778b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S2k4L5SZsIC2sS0eqSZrKAApf/Wo9LwYCWABWb8wFxjhgJH28Gr9qxjrZfrvzzBs1+1pPaYRIpwh2TQ9jchLBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-22T23:19:31.310381Z","bundle_sha256":"0c384e3ab2dfba175e972bf1336becb070550f4a287b099da59a7aca68e82233"}}