{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z4MKOTPZGADBX4YFG2IY442Z32","short_pith_number":"pith:Z4MKOTPZ","schema_version":"1.0","canonical_sha256":"cf18a74df930061bf30536918e7359debe43981220abc849643429cb2a469aec","source":{"kind":"arxiv","id":"2401.06514","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.06514","created_at":"2026-07-05T07:33:01.000662+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.06514v1","created_at":"2026-07-05T07:33:01.000662+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06514","created_at":"2026-07-05T07:33:01.000662+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4MKOTPZGADB","created_at":"2026-07-05T07:33:01.000662+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4MKOTPZGADBX4YF","created_at":"2026-07-05T07:33:01.000662+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4MKOTPZ","created_at":"2026-07-05T07:33:01.000662+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32","json":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32.json","graph_json":"https://pith.science/api/pith-number/Z4MKOTPZGADBX4YFG2IY442Z32/graph.json","events_json":"https://pith.science/api/pith-number/Z4MKOTPZGADBX4YFG2IY442Z32/events.json","paper":"https://pith.science/paper/Z4MKOTPZ"},"agent_actions":{"view_html":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32","download_json":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32.json","view_paper":"https://pith.science/paper/Z4MKOTPZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.06514&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4MKOTPZGADBX4YFG2IY442Z32/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4MKOTPZGADBX4YFG2IY442Z32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32/action/storage_attestation","attest_author":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32/action/author_attestation","sign_citation":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32/action/citation_signature","submit_replication":"https://pith.science/pith/Z4MKOTPZGADBX4YFG2IY442Z32/action/replication_record"}},"created_at":"2026-07-05T07:33:01.000662+00:00","updated_at":"2026-07-05T07:33:01.000662+00:00"}