{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:UTXU3BK7ENIAOHKDBR5MBZAMLN","short_pith_number":"pith:UTXU3BK7","canonical_record":{"source":{"id":"2210.13373","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T16:17:51Z","cross_cats_sorted":[],"title_canon_sha256":"64c338d313887604499caac1fbf8fabccd4c87bdc30b89dc6fde81cd1edccc3f","abstract_canon_sha256":"edbb3b19473e3169cd8c54352c97db1ad9e24cd32d4622ef64b7633e8ffe2851"},"schema_version":"1.0"},"canonical_sha256":"a4ef4d855f2350071d430c7ac0e40c5b5d791e32194f931a8a70f08c33075c94","source":{"kind":"arxiv","id":"2210.13373","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13373","created_at":"2026-07-05T05:28:48Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13373v3","created_at":"2026-07-05T05:28:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13373","created_at":"2026-07-05T05:28:48Z"},{"alias_kind":"pith_short_12","alias_value":"UTXU3BK7ENIA","created_at":"2026-07-05T05:28:48Z"},{"alias_kind":"pith_short_16","alias_value":"UTXU3BK7ENIAOHKD","created_at":"2026-07-05T05:28:48Z"},{"alias_kind":"pith_short_8","alias_value":"UTXU3BK7","created_at":"2026-07-05T05:28:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:UTXU3BK7ENIAOHKDBR5MBZAMLN","target":"record","payload":{"canonical_record":{"source":{"id":"2210.13373","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T16:17:51Z","cross_cats_sorted":[],"title_canon_sha256":"64c338d313887604499caac1fbf8fabccd4c87bdc30b89dc6fde81cd1edccc3f","abstract_canon_sha256":"edbb3b19473e3169cd8c54352c97db1ad9e24cd32d4622ef64b7633e8ffe2851"},"schema_version":"1.0"},"canonical_sha256":"a4ef4d855f2350071d430c7ac0e40c5b5d791e32194f931a8a70f08c33075c94","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:28:48.038509Z","signature_b64":"SnkjZE32vFVRf4epQJ/hSLSRSM/6vqsmXlb/ypLDEuALDrsVjepoWDtpuiGXb5eG1WqX6Ye1rJe5yQAQ2I/rAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4ef4d855f2350071d430c7ac0e40c5b5d791e32194f931a8a70f08c33075c94","last_reissued_at":"2026-07-05T05:28:48.037800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:28:48.037800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.13373","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":"2026-07-05T05:28:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSM8aTJki66q/v1e9KwJbO10lQbpk418YBsp105hl2NQOd/l5odMDPFduiWlU3h/mbMrBP3HFD421piBezF3CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T05:08:43.469236Z"},"content_sha256":"571ea4737de56855a7bfd48ccd15479c4140eea646ddfa83e9ad23b77dc5f2ec","schema_version":"1.0","event_id":"sha256:571ea4737de56855a7bfd48ccd15479c4140eea646ddfa83e9ad23b77dc5f2ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:UTXU3BK7ENIAOHKDBR5MBZAMLN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Byung-Jun Lee, Haanvid Lee, Jongmin Lee, Kee-Eung Kim, Wonseok Jeon, Yung-Kyun Noh, Yunseon Choi","submitted_at":"2022-10-24T16:17:51Z","abstract_excerpt":"We consider local kernel metric learning for off-policy evaluation (OPE) of deterministic policies in contextual bandits with continuous action spaces. Our work is motivated by practical scenarios where the target policy needs to be deterministic due to domain requirements, such as prescription of treatment dosage and duration in medicine. Although importance sampling (IS) provides a basic principle for OPE, it is ill-posed for the deterministic target policy with continuous actions. Our main idea is to relax the target policy and pose the problem as kernel-based estimation, where we learn the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13373","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/2210.13373/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":"2026-07-05T05:28:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jXNQnRRzhT4yPYhYEZay6RqqzH17e0LiYB4BQsdT4e/3vtaAOixkdDn4uOYFj9bhdv6pc5pC6Ynjfc4ytxd1Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T05:08:43.469629Z"},"content_sha256":"655e6453c84a70259c39008bdbd0c29142907324c2e0b31806841b3408e89742","schema_version":"1.0","event_id":"sha256:655e6453c84a70259c39008bdbd0c29142907324c2e0b31806841b3408e89742"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UTXU3BK7ENIAOHKDBR5MBZAMLN/bundle.json","state_url":"https://pith.science/pith/UTXU3BK7ENIAOHKDBR5MBZAMLN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UTXU3BK7ENIAOHKDBR5MBZAMLN/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":"2026-07-12T05:08:43Z","links":{"resolver":"https://pith.science/pith/UTXU3BK7ENIAOHKDBR5MBZAMLN","bundle":"https://pith.science/pith/UTXU3BK7ENIAOHKDBR5MBZAMLN/bundle.json","state":"https://pith.science/pith/UTXU3BK7ENIAOHKDBR5MBZAMLN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UTXU3BK7ENIAOHKDBR5MBZAMLN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:UTXU3BK7ENIAOHKDBR5MBZAMLN","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":"edbb3b19473e3169cd8c54352c97db1ad9e24cd32d4622ef64b7633e8ffe2851","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T16:17:51Z","title_canon_sha256":"64c338d313887604499caac1fbf8fabccd4c87bdc30b89dc6fde81cd1edccc3f"},"schema_version":"1.0","source":{"id":"2210.13373","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.13373","created_at":"2026-07-05T05:28:48Z"},{"alias_kind":"arxiv_version","alias_value":"2210.13373v3","created_at":"2026-07-05T05:28:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.13373","created_at":"2026-07-05T05:28:48Z"},{"alias_kind":"pith_short_12","alias_value":"UTXU3BK7ENIA","created_at":"2026-07-05T05:28:48Z"},{"alias_kind":"pith_short_16","alias_value":"UTXU3BK7ENIAOHKD","created_at":"2026-07-05T05:28:48Z"},{"alias_kind":"pith_short_8","alias_value":"UTXU3BK7","created_at":"2026-07-05T05:28:48Z"}],"graph_snapshots":[{"event_id":"sha256:655e6453c84a70259c39008bdbd0c29142907324c2e0b31806841b3408e89742","target":"graph","created_at":"2026-07-05T05:28:48Z","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/2210.13373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We consider local kernel metric learning for off-policy evaluation (OPE) of deterministic policies in contextual bandits with continuous action spaces. Our work is motivated by practical scenarios where the target policy needs to be deterministic due to domain requirements, such as prescription of treatment dosage and duration in medicine. Although importance sampling (IS) provides a basic principle for OPE, it is ill-posed for the deterministic target policy with continuous actions. Our main idea is to relax the target policy and pose the problem as kernel-based estimation, where we learn the","authors_text":"Byung-Jun Lee, Haanvid Lee, Jongmin Lee, Kee-Eung Kim, Wonseok Jeon, Yung-Kyun Noh, Yunseon Choi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T16:17:51Z","title":"Local Metric Learning for Off-Policy Evaluation in Contextual Bandits with Continuous Actions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.13373","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":"sha256:571ea4737de56855a7bfd48ccd15479c4140eea646ddfa83e9ad23b77dc5f2ec","target":"record","created_at":"2026-07-05T05:28:48Z","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":"edbb3b19473e3169cd8c54352c97db1ad9e24cd32d4622ef64b7633e8ffe2851","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-10-24T16:17:51Z","title_canon_sha256":"64c338d313887604499caac1fbf8fabccd4c87bdc30b89dc6fde81cd1edccc3f"},"schema_version":"1.0","source":{"id":"2210.13373","kind":"arxiv","version":3}},"canonical_sha256":"a4ef4d855f2350071d430c7ac0e40c5b5d791e32194f931a8a70f08c33075c94","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a4ef4d855f2350071d430c7ac0e40c5b5d791e32194f931a8a70f08c33075c94","first_computed_at":"2026-07-05T05:28:48.037800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:28:48.037800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SnkjZE32vFVRf4epQJ/hSLSRSM/6vqsmXlb/ypLDEuALDrsVjepoWDtpuiGXb5eG1WqX6Ye1rJe5yQAQ2I/rAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:28:48.038509Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.13373","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:571ea4737de56855a7bfd48ccd15479c4140eea646ddfa83e9ad23b77dc5f2ec","sha256:655e6453c84a70259c39008bdbd0c29142907324c2e0b31806841b3408e89742"],"state_sha256":"1be3ee233052988c0bdf3a1e310535ec482db8e028ce3dd28a2ba6eb7acf1ba9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9mqY54d/pccb99fVHD5Dyp0UAx67cYvVPxzaXoUplsPIoxKbmBCwjkcUZP6UrnRTiKfWSE12BljbfkTcjo/PDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T05:08:43.471759Z","bundle_sha256":"ed77db122b32bc2cc051023b78bef25be0f4a93c930bf63bbbfd389c10cc120e"}}