{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Z4MKOTPZGADBX4YFG2IY442Z32","short_pith_number":"pith:Z4MKOTPZ","canonical_record":{"source":{"id":"2401.06514","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-12T11:27:55Z","cross_cats_sorted":[],"title_canon_sha256":"6c466ab45f409141655167e3b2ed492f9414d53972ad4839f6d4d62d9c49668d","abstract_canon_sha256":"d5397b84fd42ea3dd95f2d7f0b13c1ed90824a6618dacdb753784bf40028af7c"},"schema_version":"1.0"},"canonical_sha256":"cf18a74df930061bf30536918e7359debe43981220abc849643429cb2a469aec","source":{"kind":"arxiv","id":"2401.06514","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06514","created_at":"2026-07-05T07:33:01Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06514v1","created_at":"2026-07-05T07:33:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06514","created_at":"2026-07-05T07:33:01Z"},{"alias_kind":"pith_short_12","alias_value":"Z4MKOTPZGADB","created_at":"2026-07-05T07:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"Z4MKOTPZGADBX4YF","created_at":"2026-07-05T07:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"Z4MKOTPZ","created_at":"2026-07-05T07:33:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Z4MKOTPZGADBX4YFG2IY442Z32","target":"record","payload":{"canonical_record":{"source":{"id":"2401.06514","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-12T11:27:55Z","cross_cats_sorted":[],"title_canon_sha256":"6c466ab45f409141655167e3b2ed492f9414d53972ad4839f6d4d62d9c49668d","abstract_canon_sha256":"d5397b84fd42ea3dd95f2d7f0b13c1ed90824a6618dacdb753784bf40028af7c"},"schema_version":"1.0"},"canonical_sha256":"cf18a74df930061bf30536918e7359debe43981220abc849643429cb2a469aec","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:33:01.001015Z","signature_b64":"wD9xouzJ7ePqJ+G3G4APKormt2/6d4D6t6JFeqJaOROXk6EuOEX5/Uf5Fjqb26+tl/xlYxj93JT6+2GSFUwEBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf18a74df930061bf30536918e7359debe43981220abc849643429cb2a469aec","last_reissued_at":"2026-07-05T07:33:01.000607Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:33:01.000607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.06514","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":"2026-07-05T07:33:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WzOZcTGp+nOSW3BTSdgYIGMRaye8U9+a4d/KbJSuiYqFUF9C1lIn/COtPmu5oj+q+dfWCB7xMplfTJeVX4E6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:18:09.794031Z"},"content_sha256":"54c3c0a5f5e6c422409b4f344c0f75385250e606008245a3f6af989e407f79a5","schema_version":"1.0","event_id":"sha256:54c3c0a5f5e6c422409b4f344c0f75385250e606008245a3f6af989e407f79a5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Z4MKOTPZGADBX4YFG2IY442Z32","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Personalized Reinforcement Learning with a Budget of Policies","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Dmitry Ivanov, Omer Ben-Porat","submitted_at":"2024-01-12T11:27:55Z","abstract_excerpt":"Personalization in machine learning (ML) tailors models' decisions to the individual characteristics of users. While this approach has seen success in areas like recommender systems, its expansion into high-stakes fields such as healthcare and autonomous driving is hindered by the extensive regulatory approval processes involved. To address this challenge, we propose a novel framework termed represented Markov Decision Processes (r-MDPs) that is designed to balance the need for personalization with the regulatory constraints. In an r-MDP, we cater to a diverse user population, each with unique"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06514","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/2401.06514/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":"2026-07-05T07:33:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hvAbZRrM7zMcbKWDbprpHt+O0orOfidrD+azUuQjR7hd1sstg+A1L8EGuI/uoNoxpSlD9o02DE1sKpDKHG2KAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T07:18:09.794430Z"},"content_sha256":"26ef79115b6075d1abcc272155b8c2ed893b239f6979356e2d0f499658a9b5bc","schema_version":"1.0","event_id":"sha256:26ef79115b6075d1abcc272155b8c2ed893b239f6979356e2d0f499658a9b5bc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32/bundle.json","state_url":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z4MKOTPZGADBX4YFG2IY442Z32/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":"2026-07-08T07:18:09Z","links":{"resolver":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32","bundle":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32/bundle.json","state":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z4MKOTPZGADBX4YFG2IY442Z32/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z4MKOTPZGADBX4YFG2IY442Z32","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":"d5397b84fd42ea3dd95f2d7f0b13c1ed90824a6618dacdb753784bf40028af7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-12T11:27:55Z","title_canon_sha256":"6c466ab45f409141655167e3b2ed492f9414d53972ad4839f6d4d62d9c49668d"},"schema_version":"1.0","source":{"id":"2401.06514","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06514","created_at":"2026-07-05T07:33:01Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06514v1","created_at":"2026-07-05T07:33:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06514","created_at":"2026-07-05T07:33:01Z"},{"alias_kind":"pith_short_12","alias_value":"Z4MKOTPZGADB","created_at":"2026-07-05T07:33:01Z"},{"alias_kind":"pith_short_16","alias_value":"Z4MKOTPZGADBX4YF","created_at":"2026-07-05T07:33:01Z"},{"alias_kind":"pith_short_8","alias_value":"Z4MKOTPZ","created_at":"2026-07-05T07:33:01Z"}],"graph_snapshots":[{"event_id":"sha256:26ef79115b6075d1abcc272155b8c2ed893b239f6979356e2d0f499658a9b5bc","target":"graph","created_at":"2026-07-05T07:33:01Z","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/2401.06514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Personalization in machine learning (ML) tailors models' decisions to the individual characteristics of users. While this approach has seen success in areas like recommender systems, its expansion into high-stakes fields such as healthcare and autonomous driving is hindered by the extensive regulatory approval processes involved. To address this challenge, we propose a novel framework termed represented Markov Decision Processes (r-MDPs) that is designed to balance the need for personalization with the regulatory constraints. In an r-MDP, we cater to a diverse user population, each with unique","authors_text":"Dmitry Ivanov, Omer Ben-Porat","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-12T11:27:55Z","title":"Personalized Reinforcement Learning with a Budget of Policies"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06514","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":"sha256:54c3c0a5f5e6c422409b4f344c0f75385250e606008245a3f6af989e407f79a5","target":"record","created_at":"2026-07-05T07:33:01Z","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":"d5397b84fd42ea3dd95f2d7f0b13c1ed90824a6618dacdb753784bf40028af7c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-01-12T11:27:55Z","title_canon_sha256":"6c466ab45f409141655167e3b2ed492f9414d53972ad4839f6d4d62d9c49668d"},"schema_version":"1.0","source":{"id":"2401.06514","kind":"arxiv","version":1}},"canonical_sha256":"cf18a74df930061bf30536918e7359debe43981220abc849643429cb2a469aec","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf18a74df930061bf30536918e7359debe43981220abc849643429cb2a469aec","first_computed_at":"2026-07-05T07:33:01.000607Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:33:01.000607Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wD9xouzJ7ePqJ+G3G4APKormt2/6d4D6t6JFeqJaOROXk6EuOEX5/Uf5Fjqb26+tl/xlYxj93JT6+2GSFUwEBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:33:01.001015Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06514","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54c3c0a5f5e6c422409b4f344c0f75385250e606008245a3f6af989e407f79a5","sha256:26ef79115b6075d1abcc272155b8c2ed893b239f6979356e2d0f499658a9b5bc"],"state_sha256":"964dcfd05c4bb209d776d533abda1b226cfc6234f97b134e24dcf7e669455d79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"94SDPxTXHxjx5jqEi146vUO6vSmI7HxG9Vzhq0zNNZ+YDf0APdF+GUfdngzyM7/e+lOjH5l7qojDe4vnoTkcDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T07:18:09.797858Z","bundle_sha256":"b53db91a7e7a2e198a13aea7766f33d01b5ade677a42cbbea0d12fcc06cfa26d"}}