{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2011:L6OAUC6SKFSGZAFUIAUAM6DX4Z","short_pith_number":"pith:L6OAUC6S","canonical_record":{"source":{"id":"1108.5338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2011-08-26T15:54:38Z","cross_cats_sorted":[],"title_canon_sha256":"95c8d3894699c2d9024e46de0854bdd675a30c8239b6ee11332a88c2b36d230e","abstract_canon_sha256":"c205658f064d11167e4c395d52b6ef52f954b608dfb9cecbad3116e87dbeb7a9"},"schema_version":"1.0"},"canonical_sha256":"5f9c0a0bd251646c80b44028067877e66c11be4bc4cdbfd86092c0cb1512ed9c","source":{"kind":"arxiv","id":"1108.5338","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1108.5338","created_at":"2026-05-18T04:14:38Z"},{"alias_kind":"arxiv_version","alias_value":"1108.5338v1","created_at":"2026-05-18T04:14:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1108.5338","created_at":"2026-05-18T04:14:38Z"},{"alias_kind":"pith_short_12","alias_value":"L6OAUC6SKFSG","created_at":"2026-05-18T12:26:34Z"},{"alias_kind":"pith_short_16","alias_value":"L6OAUC6SKFSGZAFU","created_at":"2026-05-18T12:26:34Z"},{"alias_kind":"pith_short_8","alias_value":"L6OAUC6S","created_at":"2026-05-18T12:26:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2011:L6OAUC6SKFSGZAFUIAUAM6DX4Z","target":"record","payload":{"canonical_record":{"source":{"id":"1108.5338","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2011-08-26T15:54:38Z","cross_cats_sorted":[],"title_canon_sha256":"95c8d3894699c2d9024e46de0854bdd675a30c8239b6ee11332a88c2b36d230e","abstract_canon_sha256":"c205658f064d11167e4c395d52b6ef52f954b608dfb9cecbad3116e87dbeb7a9"},"schema_version":"1.0"},"canonical_sha256":"5f9c0a0bd251646c80b44028067877e66c11be4bc4cdbfd86092c0cb1512ed9c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T04:14:38.506539Z","signature_b64":"qgiUpSjONjPWA2n3rgQqOgeTJJDZI4CSyQS7Ke46kEmiaoO7jrDJ4k3ob/mSI15ywSdbImtl1/BAoIXYosahAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f9c0a0bd251646c80b44028067877e66c11be4bc4cdbfd86092c0cb1512ed9c","last_reissued_at":"2026-05-18T04:14:38.506116Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T04:14:38.506116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1108.5338","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":"2026-05-18T04:14:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LIY0mGnIaycHuWlD4QamsZS0hbAv92OASFELdoypHwWd7BFsCy9J7hvb21NQHDYQL2BifUHw1hy5cltaIXJ1Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T15:08:15.129609Z"},"content_sha256":"0ad76fd5fa11d62a3ca5a4339dfe875264079773b92dc98ca871c21e31c59898","schema_version":"1.0","event_id":"sha256:0ad76fd5fa11d62a3ca5a4339dfe875264079773b92dc98ca871c21e31c59898"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2011:L6OAUC6SKFSGZAFUIAUAM6DX4Z","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Penalized Q-Learning for Dynamic Treatment Regimes","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"stat.ME","authors_text":"Donglin Zeng, Michael R. Kosorok, Rui Song, Weiwei Wang","submitted_at":"2011-08-26T15:54:38Z","abstract_excerpt":"A dynamic treatment regime effectively incorporates both accrued information and long-term effects of treatment from specially designed clinical trials. As these become more and more popular in conjunction with longitudinal data from clinical studies, the development of statistical inference for optimal dynamic treatment regimes is a high priority. This is very challenging due to the difficulties arising form non-regularities in the treatment effect parameters. In this paper, we propose a new reinforcement learning framework called penalized Q-learning (PQ-learning), under which the non-regula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1108.5338","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":"2026-05-18T04:14:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TbvF77ofP3yJA1E6/iNVWr2QCsCJNWmb1VFcXSj5zMmFjicdZIycV2jnJM/GUoy1HF4nzA+OJI0BGpT1vER0BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T15:08:15.130203Z"},"content_sha256":"c45c1c23b7255685a8c8d9283dc664300121896e3c5a6c874acf7d632373e668","schema_version":"1.0","event_id":"sha256:c45c1c23b7255685a8c8d9283dc664300121896e3c5a6c874acf7d632373e668"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L6OAUC6SKFSGZAFUIAUAM6DX4Z/bundle.json","state_url":"https://pith.science/pith/L6OAUC6SKFSGZAFUIAUAM6DX4Z/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L6OAUC6SKFSGZAFUIAUAM6DX4Z/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":"2026-06-09T15:08:15Z","links":{"resolver":"https://pith.science/pith/L6OAUC6SKFSGZAFUIAUAM6DX4Z","bundle":"https://pith.science/pith/L6OAUC6SKFSGZAFUIAUAM6DX4Z/bundle.json","state":"https://pith.science/pith/L6OAUC6SKFSGZAFUIAUAM6DX4Z/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L6OAUC6SKFSGZAFUIAUAM6DX4Z/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2011:L6OAUC6SKFSGZAFUIAUAM6DX4Z","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":"c205658f064d11167e4c395d52b6ef52f954b608dfb9cecbad3116e87dbeb7a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2011-08-26T15:54:38Z","title_canon_sha256":"95c8d3894699c2d9024e46de0854bdd675a30c8239b6ee11332a88c2b36d230e"},"schema_version":"1.0","source":{"id":"1108.5338","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1108.5338","created_at":"2026-05-18T04:14:38Z"},{"alias_kind":"arxiv_version","alias_value":"1108.5338v1","created_at":"2026-05-18T04:14:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1108.5338","created_at":"2026-05-18T04:14:38Z"},{"alias_kind":"pith_short_12","alias_value":"L6OAUC6SKFSG","created_at":"2026-05-18T12:26:34Z"},{"alias_kind":"pith_short_16","alias_value":"L6OAUC6SKFSGZAFU","created_at":"2026-05-18T12:26:34Z"},{"alias_kind":"pith_short_8","alias_value":"L6OAUC6S","created_at":"2026-05-18T12:26:34Z"}],"graph_snapshots":[{"event_id":"sha256:c45c1c23b7255685a8c8d9283dc664300121896e3c5a6c874acf7d632373e668","target":"graph","created_at":"2026-05-18T04:14:38Z","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":"A dynamic treatment regime effectively incorporates both accrued information and long-term effects of treatment from specially designed clinical trials. As these become more and more popular in conjunction with longitudinal data from clinical studies, the development of statistical inference for optimal dynamic treatment regimes is a high priority. This is very challenging due to the difficulties arising form non-regularities in the treatment effect parameters. In this paper, we propose a new reinforcement learning framework called penalized Q-learning (PQ-learning), under which the non-regula","authors_text":"Donglin Zeng, Michael R. Kosorok, Rui Song, Weiwei Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2011-08-26T15:54:38Z","title":"Penalized Q-Learning for Dynamic Treatment Regimes"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1108.5338","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":"sha256:0ad76fd5fa11d62a3ca5a4339dfe875264079773b92dc98ca871c21e31c59898","target":"record","created_at":"2026-05-18T04:14:38Z","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":"c205658f064d11167e4c395d52b6ef52f954b608dfb9cecbad3116e87dbeb7a9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2011-08-26T15:54:38Z","title_canon_sha256":"95c8d3894699c2d9024e46de0854bdd675a30c8239b6ee11332a88c2b36d230e"},"schema_version":"1.0","source":{"id":"1108.5338","kind":"arxiv","version":1}},"canonical_sha256":"5f9c0a0bd251646c80b44028067877e66c11be4bc4cdbfd86092c0cb1512ed9c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f9c0a0bd251646c80b44028067877e66c11be4bc4cdbfd86092c0cb1512ed9c","first_computed_at":"2026-05-18T04:14:38.506116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T04:14:38.506116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qgiUpSjONjPWA2n3rgQqOgeTJJDZI4CSyQS7Ke46kEmiaoO7jrDJ4k3ob/mSI15ywSdbImtl1/BAoIXYosahAg==","signature_status":"signed_v1","signed_at":"2026-05-18T04:14:38.506539Z","signed_message":"canonical_sha256_bytes"},"source_id":"1108.5338","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ad76fd5fa11d62a3ca5a4339dfe875264079773b92dc98ca871c21e31c59898","sha256:c45c1c23b7255685a8c8d9283dc664300121896e3c5a6c874acf7d632373e668"],"state_sha256":"6e2f8dfdeedb1a3d4b2605179c8a65882f732ef7fed8403900322a503a3fa697"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BEtuyRdfyekISfHaXisPJpv3ogFnlS0jF8oGNKYaReHryeUq+c0M1KVxksbSEKtQB673OOLdPN5F9gMuff5zBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T15:08:15.133183Z","bundle_sha256":"cd9099117f0a0a0ac3b882e6ed659495fec3b621471a78b1143d6d81b253d66c"}}