{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QAPBVY3ASRBJFODTFQ5RK55HPF","short_pith_number":"pith:QAPBVY3A","canonical_record":{"source":{"id":"2410.08537","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T05:16:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3d1303fa2871cb437503230a96b77fe4849ae6b374883096ca54bf108fdd09f4","abstract_canon_sha256":"5b3e9bab9344b70308613f0d3fca30d74879037f7c4d21ce1c5c4dcf45867cda"},"schema_version":"1.0"},"canonical_sha256":"801e1ae360944292b8732c3b1577a77953e1d9e7922b91fdae52c79ae3320c20","source":{"kind":"arxiv","id":"2410.08537","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08537","created_at":"2026-07-05T09:19:13Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08537v1","created_at":"2026-07-05T09:19:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08537","created_at":"2026-07-05T09:19:13Z"},{"alias_kind":"pith_short_12","alias_value":"QAPBVY3ASRBJ","created_at":"2026-07-05T09:19:13Z"},{"alias_kind":"pith_short_16","alias_value":"QAPBVY3ASRBJFODT","created_at":"2026-07-05T09:19:13Z"},{"alias_kind":"pith_short_8","alias_value":"QAPBVY3A","created_at":"2026-07-05T09:19:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QAPBVY3ASRBJFODTFQ5RK55HPF","target":"record","payload":{"canonical_record":{"source":{"id":"2410.08537","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T05:16:23Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"3d1303fa2871cb437503230a96b77fe4849ae6b374883096ca54bf108fdd09f4","abstract_canon_sha256":"5b3e9bab9344b70308613f0d3fca30d74879037f7c4d21ce1c5c4dcf45867cda"},"schema_version":"1.0"},"canonical_sha256":"801e1ae360944292b8732c3b1577a77953e1d9e7922b91fdae52c79ae3320c20","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:13.729983Z","signature_b64":"S21XkdbvdXP2YlkfNvrWisQORxP6vaIFFxgOMQrdROrj8dgpgqcvlJi8JzrF0WYsehNG5Eqr3PnQa7ydpDuQAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"801e1ae360944292b8732c3b1577a77953e1d9e7922b91fdae52c79ae3320c20","last_reissued_at":"2026-07-05T09:19:13.729492Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:13.729492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.08537","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":"2026-07-05T09:19:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LCYXmT9mHJrGAdXr5GCO/RV2f/OGrVSEpVYRIraxW3Kt/1DgIl6IE41z27wO6v1kG1RQdxlGV8470qrH0oUJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:46:43.379224Z"},"content_sha256":"f83926e647c960191fef6cfffda5fe76978fd95a6b253e2e1eb9c9ccde220059","schema_version":"1.0","event_id":"sha256:f83926e647c960191fef6cfffda5fe76978fd95a6b253e2e1eb9c9ccde220059"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QAPBVY3ASRBJFODTFQ5RK55HPF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Offline Policy Learning with Observational Data from Multiple Sources","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Aldo Gael Carranza, Susan Athey","submitted_at":"2024-10-11T05:16:23Z","abstract_excerpt":"We consider the problem of using observational bandit feedback data from multiple heterogeneous data sources to learn a personalized decision policy that robustly generalizes across diverse target settings. To achieve this, we propose a minimax regret optimization objective to ensure uniformly low regret under general mixtures of the source distributions. We develop a policy learning algorithm tailored to this objective, combining doubly robust offline policy evaluation techniques and no-regret learning algorithms for minimax optimization. Our regret analysis shows that this approach achieves "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08537","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.08537/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":"2026-07-05T09:19:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ct+vJnzDODCsIPlzEiEM6v+zz0XHaIGNf39bDrsW8+WHNMW16JbWcAmYLceESNrTzHuXll1WU/Rxo0W+fkbNCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T17:46:43.379737Z"},"content_sha256":"63926f00231e2ce6ffcb9c6773b3cdebe26cb17892526c4d92e122d440073956","schema_version":"1.0","event_id":"sha256:63926f00231e2ce6ffcb9c6773b3cdebe26cb17892526c4d92e122d440073956"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF/bundle.json","state_url":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QAPBVY3ASRBJFODTFQ5RK55HPF/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":"2026-08-20T17:46:43Z","links":{"resolver":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF","bundle":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF/bundle.json","state":"https://pith.science/pith/QAPBVY3ASRBJFODTFQ5RK55HPF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QAPBVY3ASRBJFODTFQ5RK55HPF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QAPBVY3ASRBJFODTFQ5RK55HPF","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":"5b3e9bab9344b70308613f0d3fca30d74879037f7c4d21ce1c5c4dcf45867cda","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T05:16:23Z","title_canon_sha256":"3d1303fa2871cb437503230a96b77fe4849ae6b374883096ca54bf108fdd09f4"},"schema_version":"1.0","source":{"id":"2410.08537","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.08537","created_at":"2026-07-05T09:19:13Z"},{"alias_kind":"arxiv_version","alias_value":"2410.08537v1","created_at":"2026-07-05T09:19:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.08537","created_at":"2026-07-05T09:19:13Z"},{"alias_kind":"pith_short_12","alias_value":"QAPBVY3ASRBJ","created_at":"2026-07-05T09:19:13Z"},{"alias_kind":"pith_short_16","alias_value":"QAPBVY3ASRBJFODT","created_at":"2026-07-05T09:19:13Z"},{"alias_kind":"pith_short_8","alias_value":"QAPBVY3A","created_at":"2026-07-05T09:19:13Z"}],"graph_snapshots":[{"event_id":"sha256:63926f00231e2ce6ffcb9c6773b3cdebe26cb17892526c4d92e122d440073956","target":"graph","created_at":"2026-07-05T09:19:13Z","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/2410.08537/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider the problem of using observational bandit feedback data from multiple heterogeneous data sources to learn a personalized decision policy that robustly generalizes across diverse target settings. To achieve this, we propose a minimax regret optimization objective to ensure uniformly low regret under general mixtures of the source distributions. We develop a policy learning algorithm tailored to this objective, combining doubly robust offline policy evaluation techniques and no-regret learning algorithms for minimax optimization. Our regret analysis shows that this approach achieves ","authors_text":"Aldo Gael Carranza, Susan Athey","cross_cats":["stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T05:16:23Z","title":"Robust Offline Policy Learning with Observational Data from Multiple Sources"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.08537","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:f83926e647c960191fef6cfffda5fe76978fd95a6b253e2e1eb9c9ccde220059","target":"record","created_at":"2026-07-05T09:19:13Z","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":"5b3e9bab9344b70308613f0d3fca30d74879037f7c4d21ce1c5c4dcf45867cda","cross_cats_sorted":["stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-11T05:16:23Z","title_canon_sha256":"3d1303fa2871cb437503230a96b77fe4849ae6b374883096ca54bf108fdd09f4"},"schema_version":"1.0","source":{"id":"2410.08537","kind":"arxiv","version":1}},"canonical_sha256":"801e1ae360944292b8732c3b1577a77953e1d9e7922b91fdae52c79ae3320c20","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"801e1ae360944292b8732c3b1577a77953e1d9e7922b91fdae52c79ae3320c20","first_computed_at":"2026-07-05T09:19:13.729492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:19:13.729492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S21XkdbvdXP2YlkfNvrWisQORxP6vaIFFxgOMQrdROrj8dgpgqcvlJi8JzrF0WYsehNG5Eqr3PnQa7ydpDuQAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:19:13.729983Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.08537","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f83926e647c960191fef6cfffda5fe76978fd95a6b253e2e1eb9c9ccde220059","sha256:63926f00231e2ce6ffcb9c6773b3cdebe26cb17892526c4d92e122d440073956"],"state_sha256":"9ee34749c59546e1eb92caa2be13560c2b3f1cf0fccd93b75172a22fe42f338b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l1i8NHdHo1ftEeo/kTxdtgYjBkE+m2IzOG3k0TVnoR8/nviu4x8fwHTyFMbvE9Z7t/d+79BiWLHzy79f0wweCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T17:46:43.383439Z","bundle_sha256":"65cdee0c4d9fb92b56edde2ab66ba0061ead93243d38dd4c6a84a025862c234b"}}