{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:35HMAGKJ6NL2GW26CPKZAW7V7I","short_pith_number":"pith:35HMAGKJ","canonical_record":{"source":{"id":"2406.08697","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-06-12T23:41:43Z","cross_cats_sorted":["cs.LG","math.OC","stat.ME"],"title_canon_sha256":"accc73fbe2d00b1d2eaa4d3a65c2f9a3cc738c3bb742603e5b0ca43ff3ee91be","abstract_canon_sha256":"623e761ec2eb960741b4d52a66cd43ae1f8598852a30ade335c90fc8b336575a"},"schema_version":"1.0"},"canonical_sha256":"df4ec01949f357a35b5e13d5905bf5fa1b4a09d8766b845d4fff51a5105f74ff","source":{"kind":"arxiv","id":"2406.08697","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08697","created_at":"2026-07-05T11:31:39Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08697v3","created_at":"2026-07-05T11:31:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08697","created_at":"2026-07-05T11:31:39Z"},{"alias_kind":"pith_short_12","alias_value":"35HMAGKJ6NL2","created_at":"2026-07-05T11:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"35HMAGKJ6NL2GW26","created_at":"2026-07-05T11:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"35HMAGKJ","created_at":"2026-07-05T11:31:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:35HMAGKJ6NL2GW26CPKZAW7V7I","target":"record","payload":{"canonical_record":{"source":{"id":"2406.08697","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-06-12T23:41:43Z","cross_cats_sorted":["cs.LG","math.OC","stat.ME"],"title_canon_sha256":"accc73fbe2d00b1d2eaa4d3a65c2f9a3cc738c3bb742603e5b0ca43ff3ee91be","abstract_canon_sha256":"623e761ec2eb960741b4d52a66cd43ae1f8598852a30ade335c90fc8b336575a"},"schema_version":"1.0"},"canonical_sha256":"df4ec01949f357a35b5e13d5905bf5fa1b4a09d8766b845d4fff51a5105f74ff","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:39.117112Z","signature_b64":"gKRU/JuFVdDHU33pc6NT68NSdsC+tzlzPk013KTMeEgy/um26aMNlXydnxLZbAVFSVB4lck67cn5Sv+/12q1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df4ec01949f357a35b5e13d5905bf5fa1b4a09d8766b845d4fff51a5105f74ff","last_reissued_at":"2026-07-05T11:31:39.116613Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:39.116613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.08697","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1J4L4yAyzEb0+8Jzu1T8ZxvxGijVqenqBpBRoCKDLYF5tu/XCFsirbkEI2M3rtWb2IxsJv7+GA0nZ9mwjdY8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:38:38.371580Z"},"content_sha256":"8130b670428596ddf64e389032a45be4dfc8410f874fbf6c245b9fc2c3beb357","schema_version":"1.0","event_id":"sha256:8130b670428596ddf64e389032a45be4dfc8410f874fbf6c245b9fc2c3beb357"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:35HMAGKJ6NL2GW26CPKZAW7V7I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Structured Difference-of-Q via Orthogonal Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","math.OC","stat.ME"],"primary_cat":"stat.ML","authors_text":"Angela Zhou, Defu Cao","submitted_at":"2024-06-12T23:41:43Z","abstract_excerpt":"Offline reinforcement learning is important in many settings with available observational data but the inability to deploy new policies online due to safety, cost, and other concerns. Many recent advances in causal inference and machine learning target estimation of causal contrast functions such as CATE, which is sufficient for optimizing decisions and can adapt to potentially smoother structure. We develop a dynamic generalization of the R-learner (Nie and Wager 2021, Lewis and Syrgkanis 2021) for estimating and optimizing the difference of $Q^\\pi$-functions, $Q^\\pi(s,1)-Q^\\pi(s,0)$ (which c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08697","kind":"arxiv","version":3},"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/2406.08697/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:31:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VoaVFNSX4OMLDeP4cv59n0gxTi8ZlxwualJIY5OWA+rOacq3OhaKfqWz/QYsiNWabSq3NLNCazEnh1prST92Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T01:38:38.372096Z"},"content_sha256":"b252d84e1da90d33a872499d3fd3ee46df829419df00aa78a112ebbb25a18b48","schema_version":"1.0","event_id":"sha256:b252d84e1da90d33a872499d3fd3ee46df829419df00aa78a112ebbb25a18b48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/35HMAGKJ6NL2GW26CPKZAW7V7I/bundle.json","state_url":"https://pith.science/pith/35HMAGKJ6NL2GW26CPKZAW7V7I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/35HMAGKJ6NL2GW26CPKZAW7V7I/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":"2026-08-09T01:38:38Z","links":{"resolver":"https://pith.science/pith/35HMAGKJ6NL2GW26CPKZAW7V7I","bundle":"https://pith.science/pith/35HMAGKJ6NL2GW26CPKZAW7V7I/bundle.json","state":"https://pith.science/pith/35HMAGKJ6NL2GW26CPKZAW7V7I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/35HMAGKJ6NL2GW26CPKZAW7V7I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:35HMAGKJ6NL2GW26CPKZAW7V7I","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":"623e761ec2eb960741b4d52a66cd43ae1f8598852a30ade335c90fc8b336575a","cross_cats_sorted":["cs.LG","math.OC","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-06-12T23:41:43Z","title_canon_sha256":"accc73fbe2d00b1d2eaa4d3a65c2f9a3cc738c3bb742603e5b0ca43ff3ee91be"},"schema_version":"1.0","source":{"id":"2406.08697","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.08697","created_at":"2026-07-05T11:31:39Z"},{"alias_kind":"arxiv_version","alias_value":"2406.08697v3","created_at":"2026-07-05T11:31:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.08697","created_at":"2026-07-05T11:31:39Z"},{"alias_kind":"pith_short_12","alias_value":"35HMAGKJ6NL2","created_at":"2026-07-05T11:31:39Z"},{"alias_kind":"pith_short_16","alias_value":"35HMAGKJ6NL2GW26","created_at":"2026-07-05T11:31:39Z"},{"alias_kind":"pith_short_8","alias_value":"35HMAGKJ","created_at":"2026-07-05T11:31:39Z"}],"graph_snapshots":[{"event_id":"sha256:b252d84e1da90d33a872499d3fd3ee46df829419df00aa78a112ebbb25a18b48","target":"graph","created_at":"2026-07-05T11:31:39Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.08697/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Offline reinforcement learning is important in many settings with available observational data but the inability to deploy new policies online due to safety, cost, and other concerns. Many recent advances in causal inference and machine learning target estimation of causal contrast functions such as CATE, which is sufficient for optimizing decisions and can adapt to potentially smoother structure. We develop a dynamic generalization of the R-learner (Nie and Wager 2021, Lewis and Syrgkanis 2021) for estimating and optimizing the difference of $Q^\\pi$-functions, $Q^\\pi(s,1)-Q^\\pi(s,0)$ (which c","authors_text":"Angela Zhou, Defu Cao","cross_cats":["cs.LG","math.OC","stat.ME"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-06-12T23:41:43Z","title":"Structured Difference-of-Q via Orthogonal Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.08697","kind":"arxiv","version":3},"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":"sha256:8130b670428596ddf64e389032a45be4dfc8410f874fbf6c245b9fc2c3beb357","target":"record","created_at":"2026-07-05T11:31:39Z","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":"623e761ec2eb960741b4d52a66cd43ae1f8598852a30ade335c90fc8b336575a","cross_cats_sorted":["cs.LG","math.OC","stat.ME"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2024-06-12T23:41:43Z","title_canon_sha256":"accc73fbe2d00b1d2eaa4d3a65c2f9a3cc738c3bb742603e5b0ca43ff3ee91be"},"schema_version":"1.0","source":{"id":"2406.08697","kind":"arxiv","version":3}},"canonical_sha256":"df4ec01949f357a35b5e13d5905bf5fa1b4a09d8766b845d4fff51a5105f74ff","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df4ec01949f357a35b5e13d5905bf5fa1b4a09d8766b845d4fff51a5105f74ff","first_computed_at":"2026-07-05T11:31:39.116613Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:39.116613Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gKRU/JuFVdDHU33pc6NT68NSdsC+tzlzPk013KTMeEgy/um26aMNlXydnxLZbAVFSVB4lck67cn5Sv+/12q1CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:39.117112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.08697","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8130b670428596ddf64e389032a45be4dfc8410f874fbf6c245b9fc2c3beb357","sha256:b252d84e1da90d33a872499d3fd3ee46df829419df00aa78a112ebbb25a18b48"],"state_sha256":"977c5c9ebd299e8aed424aa4fab17291d3288549404624e5f57af8c8b74b0e0a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AbYEQHqCYNWahMD+GggYbNBWibrX1VVCDb0L/i/T8An/B58Sujs35hvkaFqWQ+4EBVCBap1k7zTixaX4ScDxAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T01:38:38.377532Z","bundle_sha256":"41de9a47ad0b05b94ef443b185b0bfdfb4f33f6e4d3d4d0acf4474ad8f8daeb3"}}