{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T4KUPOFFQBAQ2Z7HU43B2HU43A","short_pith_number":"pith:T4KUPOFF","schema_version":"1.0","canonical_sha256":"9f1547b8a580410d67e7a7361d1e9cd836913810134e813977539390aafc2d63","source":{"kind":"arxiv","id":"2408.00147","version":1},"attestation_state":"computed","paper":{"title":"Formal Ethical Obligations in Reinforcement Learning Agents: Verification and Policy Updates","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LO"],"primary_cat":"cs.AI","authors_text":"Colin Shea-Blymyer, Houssam Abbas","submitted_at":"2024-07-31T20:21:15Z","abstract_excerpt":"When designing agents for operation in uncertain environments, designers need tools to automatically reason about what agents ought to do, how that conflicts with what is actually happening, and how a policy might be modified to remove the conflict. These obligations include ethical and social obligations, permissions and prohibitions, which constrain how the agent achieves its mission and executes its policy. We propose a new deontic logic, Expected Act Utilitarian deontic logic, for enabling this reasoning at design time: for specifying and verifying the agent's strategic obligations, then m"},"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":"2408.00147","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-07-31T20:21:15Z","cross_cats_sorted":["cs.LO"],"title_canon_sha256":"6bd108f61b1a68831f42d583d2f022e1cf4b11129953782c7bce6f8ec46f52e1","abstract_canon_sha256":"c1e319ca0063090cc343443f71c427e17d782682ece034124a39dfe52a52ec7a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:50:59.223010Z","signature_b64":"hA6vRtVImzSS5rTSv9RDUaLpEbMfm9Tiv2uSuGhwG7OfqZqJE9ntXZ95hP3OioU3pq8mpaQgH2Fytw1ue7K7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f1547b8a580410d67e7a7361d1e9cd836913810134e813977539390aafc2d63","last_reissued_at":"2026-07-05T08:50:59.222626Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:50:59.222626Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Formal Ethical Obligations in Reinforcement Learning Agents: Verification and Policy Updates","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.LO"],"primary_cat":"cs.AI","authors_text":"Colin Shea-Blymyer, Houssam Abbas","submitted_at":"2024-07-31T20:21:15Z","abstract_excerpt":"When designing agents for operation in uncertain environments, designers need tools to automatically reason about what agents ought to do, how that conflicts with what is actually happening, and how a policy might be modified to remove the conflict. These obligations include ethical and social obligations, permissions and prohibitions, which constrain how the agent achieves its mission and executes its policy. We propose a new deontic logic, Expected Act Utilitarian deontic logic, for enabling this reasoning at design time: for specifying and verifying the agent's strategic obligations, then m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00147","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/2408.00147/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":"2408.00147","created_at":"2026-07-05T08:50:59.222680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00147v1","created_at":"2026-07-05T08:50:59.222680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00147","created_at":"2026-07-05T08:50:59.222680+00:00"},{"alias_kind":"pith_short_12","alias_value":"T4KUPOFFQBAQ","created_at":"2026-07-05T08:50:59.222680+00:00"},{"alias_kind":"pith_short_16","alias_value":"T4KUPOFFQBAQ2Z7H","created_at":"2026-07-05T08:50:59.222680+00:00"},{"alias_kind":"pith_short_8","alias_value":"T4KUPOFF","created_at":"2026-07-05T08:50:59.222680+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/T4KUPOFFQBAQ2Z7HU43B2HU43A","json":"https://pith.science/pith/T4KUPOFFQBAQ2Z7HU43B2HU43A.json","graph_json":"https://pith.science/api/pith-number/T4KUPOFFQBAQ2Z7HU43B2HU43A/graph.json","events_json":"https://pith.science/api/pith-number/T4KUPOFFQBAQ2Z7HU43B2HU43A/events.json","paper":"https://pith.science/paper/T4KUPOFF"},"agent_actions":{"view_html":"https://pith.science/pith/T4KUPOFFQBAQ2Z7HU43B2HU43A","download_json":"https://pith.science/pith/T4KUPOFFQBAQ2Z7HU43B2HU43A.json","view_paper":"https://pith.science/paper/T4KUPOFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00147&json=true","fetch_graph":"https://pith.science/api/pith-number/T4KUPOFFQBAQ2Z7HU43B2HU43A/graph.json","fetch_events":"https://pith.science/api/pith-number/T4KUPOFFQBAQ2Z7HU43B2HU43A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T4KUPOFFQBAQ2Z7HU43B2HU43A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T4KUPOFFQBAQ2Z7HU43B2HU43A/action/storage_attestation","attest_author":"https://pith.science/pith/T4KUPOFFQBAQ2Z7HU43B2HU43A/action/author_attestation","sign_citation":"https://pith.science/pith/T4KUPOFFQBAQ2Z7HU43B2HU43A/action/citation_signature","submit_replication":"https://pith.science/pith/T4KUPOFFQBAQ2Z7HU43B2HU43A/action/replication_record"}},"created_at":"2026-07-05T08:50:59.222680+00:00","updated_at":"2026-07-05T08:50:59.222680+00:00"}