{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:P3CUP4WATGNCZBYMU25ZKNY56D","short_pith_number":"pith:P3CUP4WA","canonical_record":{"source":{"id":"2506.06959","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-08T01:01:06Z","cross_cats_sorted":[],"title_canon_sha256":"00f8d7b24e3e67a80cad527ce1d190b6f938ea657d576c3691aef1f003b6f259","abstract_canon_sha256":"db89610742283ee16df9a377d8f8a628ff99961a0aaf6127bef76ea967f929d9"},"schema_version":"1.0"},"canonical_sha256":"7ec547f2c0999a2c870ca6bb95371df0d315af6a07680e370a8581aa63fa0005","source":{"kind":"arxiv","id":"2506.06959","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06959","created_at":"2026-07-05T11:17:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06959v1","created_at":"2026-07-05T11:17:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06959","created_at":"2026-07-05T11:17:58Z"},{"alias_kind":"pith_short_12","alias_value":"P3CUP4WATGNC","created_at":"2026-07-05T11:17:58Z"},{"alias_kind":"pith_short_16","alias_value":"P3CUP4WATGNCZBYM","created_at":"2026-07-05T11:17:58Z"},{"alias_kind":"pith_short_8","alias_value":"P3CUP4WA","created_at":"2026-07-05T11:17:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:P3CUP4WATGNCZBYMU25ZKNY56D","target":"record","payload":{"canonical_record":{"source":{"id":"2506.06959","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-08T01:01:06Z","cross_cats_sorted":[],"title_canon_sha256":"00f8d7b24e3e67a80cad527ce1d190b6f938ea657d576c3691aef1f003b6f259","abstract_canon_sha256":"db89610742283ee16df9a377d8f8a628ff99961a0aaf6127bef76ea967f929d9"},"schema_version":"1.0"},"canonical_sha256":"7ec547f2c0999a2c870ca6bb95371df0d315af6a07680e370a8581aa63fa0005","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:58.776844Z","signature_b64":"jfarUd0qd4IpnmSSy/xs7tZ3ligSx2zj8xE6eSzPUuy2Kw7f8jz3QIYmocm+zqDyxBPG6ifiYs8K611G9tU9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ec547f2c0999a2c870ca6bb95371df0d315af6a07680e370a8581aa63fa0005","last_reissued_at":"2026-07-05T11:17:58.776353Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:58.776353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.06959","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":"2026-07-05T11:17:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/gOxkoBSOk66ljPmh0Bg2ibOSxzdoDXueGISY0KwJnpihMcD1Um8WD9Fc6eUea52i8qvREojYWiGbg+JLbi8DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:38:51.050527Z"},"content_sha256":"ac01672362d271a1dac955d3a9d77b9b8a9c56dc621d7a4509d102ac991b58bb","schema_version":"1.0","event_id":"sha256:ac01672362d271a1dac955d3a9d77b9b8a9c56dc621d7a4509d102ac991b58bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:P3CUP4WATGNCZBYMU25ZKNY56D","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deontically Constrained Policy Improvement in Reinforcement Learning Agents","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Alena Makarova, Houssam Abbas","submitted_at":"2025-06-08T01:01:06Z","abstract_excerpt":"Markov Decision Processes (MDPs) are the most common model for decision making under uncertainty in the Machine Learning community. An MDP captures non-determinism, probabilistic uncertainty, and an explicit model of action. A Reinforcement Learning (RL) agent learns to act in an MDP by maximizing a utility function. This paper considers the problem of learning a decision policy that maximizes utility subject to satisfying a constraint expressed in deontic logic. In this setup, the utility captures the agent's mission - such as going quickly from A to B. The deontic formula represents (ethical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06959","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/2506.06959/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":"2026-07-05T11:17:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MqVNQ3rWLhzFwOJ/SEoXS05xeSTaSp7EZr43YnWIzijXxmZXI03evE7mKd20aQ72++0XsslSlj07fSXBVCA4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T22:38:51.051025Z"},"content_sha256":"408abaf7231b31eaa8909d529de10f473d47b34c4ba023decf869b372018ec99","schema_version":"1.0","event_id":"sha256:408abaf7231b31eaa8909d529de10f473d47b34c4ba023decf869b372018ec99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/P3CUP4WATGNCZBYMU25ZKNY56D/bundle.json","state_url":"https://pith.science/pith/P3CUP4WATGNCZBYMU25ZKNY56D/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/P3CUP4WATGNCZBYMU25ZKNY56D/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":"2026-08-04T22:38:51Z","links":{"resolver":"https://pith.science/pith/P3CUP4WATGNCZBYMU25ZKNY56D","bundle":"https://pith.science/pith/P3CUP4WATGNCZBYMU25ZKNY56D/bundle.json","state":"https://pith.science/pith/P3CUP4WATGNCZBYMU25ZKNY56D/state.json","well_known_bundle":"https://pith.science/.well-known/pith/P3CUP4WATGNCZBYMU25ZKNY56D/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:P3CUP4WATGNCZBYMU25ZKNY56D","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":"db89610742283ee16df9a377d8f8a628ff99961a0aaf6127bef76ea967f929d9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-08T01:01:06Z","title_canon_sha256":"00f8d7b24e3e67a80cad527ce1d190b6f938ea657d576c3691aef1f003b6f259"},"schema_version":"1.0","source":{"id":"2506.06959","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.06959","created_at":"2026-07-05T11:17:58Z"},{"alias_kind":"arxiv_version","alias_value":"2506.06959v1","created_at":"2026-07-05T11:17:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06959","created_at":"2026-07-05T11:17:58Z"},{"alias_kind":"pith_short_12","alias_value":"P3CUP4WATGNC","created_at":"2026-07-05T11:17:58Z"},{"alias_kind":"pith_short_16","alias_value":"P3CUP4WATGNCZBYM","created_at":"2026-07-05T11:17:58Z"},{"alias_kind":"pith_short_8","alias_value":"P3CUP4WA","created_at":"2026-07-05T11:17:58Z"}],"graph_snapshots":[{"event_id":"sha256:408abaf7231b31eaa8909d529de10f473d47b34c4ba023decf869b372018ec99","target":"graph","created_at":"2026-07-05T11:17:58Z","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/2506.06959/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Markov Decision Processes (MDPs) are the most common model for decision making under uncertainty in the Machine Learning community. An MDP captures non-determinism, probabilistic uncertainty, and an explicit model of action. A Reinforcement Learning (RL) agent learns to act in an MDP by maximizing a utility function. This paper considers the problem of learning a decision policy that maximizes utility subject to satisfying a constraint expressed in deontic logic. In this setup, the utility captures the agent's mission - such as going quickly from A to B. The deontic formula represents (ethical","authors_text":"Alena Makarova, Houssam Abbas","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-08T01:01:06Z","title":"Deontically Constrained Policy Improvement in Reinforcement Learning Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06959","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:ac01672362d271a1dac955d3a9d77b9b8a9c56dc621d7a4509d102ac991b58bb","target":"record","created_at":"2026-07-05T11:17:58Z","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":"db89610742283ee16df9a377d8f8a628ff99961a0aaf6127bef76ea967f929d9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-06-08T01:01:06Z","title_canon_sha256":"00f8d7b24e3e67a80cad527ce1d190b6f938ea657d576c3691aef1f003b6f259"},"schema_version":"1.0","source":{"id":"2506.06959","kind":"arxiv","version":1}},"canonical_sha256":"7ec547f2c0999a2c870ca6bb95371df0d315af6a07680e370a8581aa63fa0005","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7ec547f2c0999a2c870ca6bb95371df0d315af6a07680e370a8581aa63fa0005","first_computed_at":"2026-07-05T11:17:58.776353Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:58.776353Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jfarUd0qd4IpnmSSy/xs7tZ3ligSx2zj8xE6eSzPUuy2Kw7f8jz3QIYmocm+zqDyxBPG6ifiYs8K611G9tU9AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:58.776844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.06959","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ac01672362d271a1dac955d3a9d77b9b8a9c56dc621d7a4509d102ac991b58bb","sha256:408abaf7231b31eaa8909d529de10f473d47b34c4ba023decf869b372018ec99"],"state_sha256":"be2effa1cc68ccc416f9821c9571974e9e6e4e1b2b83cf85366264f7bd9ecd3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/yfsfaTlP4hOzhQvxxZXeD45eQYLKAeYAVtLZ2el0OyLfgoD2L0AWugWlyD63e8rSfbKFDYXphZCToj7AoXMCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T22:38:51.054515Z","bundle_sha256":"d01049a10892ee1cb759371ba64e2f46c8bbcd305f1575e3b9fdccacf250cdc1"}}