{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:N3BKQSBEQKNXKXSISCFIWW42LP","short_pith_number":"pith:N3BKQSBE","schema_version":"1.0","canonical_sha256":"6ec2a84824829b755e48908a8b5b9a5bcfe22426a0af598a8e446749c60b9a10","source":{"kind":"arxiv","id":"2412.00033","version":1},"attestation_state":"computed","paper":{"title":"Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.AI","authors_text":"Fr\\'ed\\'eric Berdoz, Roger Wattenhofer","submitted_at":"2024-11-21T11:36:45Z","abstract_excerpt":"While autonomous agents often surpass humans in their ability to handle vast and complex data, their potential misalignment (i.e., lack of transparency regarding their true objective) has thus far hindered their use in critical applications such as social decision processes. More importantly, existing alignment methods provide no formal guarantees on the safety of such models. Drawing from utility and social choice theory, we provide a novel quantitative definition of alignment in the context of social decision-making. Building on this definition, we introduce probably approximately aligned (i"},"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":"2412.00033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-21T11:36:45Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"8cc5b2a43f297826e14aaf86cb349d44b7a0a922fbc9f74a8eb9bb44db0e58c7","abstract_canon_sha256":"dd81f927fc2b1a7805003193e9f2825bda8fcfef052d423cae92f414964f200f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:35.000455Z","signature_b64":"ezhEsvQ1FZnrk/sGvPrUrgHkdzF9MqGRmy1hzenJkPv8YOcKGHks13qdZwBH2P+tEQtoxk0LqsuGKBB8UpxBBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ec2a84824829b755e48908a8b5b9a5bcfe22426a0af598a8e446749c60b9a10","last_reissued_at":"2026-07-05T09:42:34.999947Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:34.999947Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.AI","authors_text":"Fr\\'ed\\'eric Berdoz, Roger Wattenhofer","submitted_at":"2024-11-21T11:36:45Z","abstract_excerpt":"While autonomous agents often surpass humans in their ability to handle vast and complex data, their potential misalignment (i.e., lack of transparency regarding their true objective) has thus far hindered their use in critical applications such as social decision processes. More importantly, existing alignment methods provide no formal guarantees on the safety of such models. Drawing from utility and social choice theory, we provide a novel quantitative definition of alignment in the context of social decision-making. Building on this definition, we introduce probably approximately aligned (i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.00033","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/2412.00033/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":"2412.00033","created_at":"2026-07-05T09:42:35.000006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.00033v1","created_at":"2026-07-05T09:42:35.000006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.00033","created_at":"2026-07-05T09:42:35.000006+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3BKQSBEQKNX","created_at":"2026-07-05T09:42:35.000006+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3BKQSBEQKNXKXSI","created_at":"2026-07-05T09:42:35.000006+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3BKQSBE","created_at":"2026-07-05T09:42:35.000006+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/N3BKQSBEQKNXKXSISCFIWW42LP","json":"https://pith.science/pith/N3BKQSBEQKNXKXSISCFIWW42LP.json","graph_json":"https://pith.science/api/pith-number/N3BKQSBEQKNXKXSISCFIWW42LP/graph.json","events_json":"https://pith.science/api/pith-number/N3BKQSBEQKNXKXSISCFIWW42LP/events.json","paper":"https://pith.science/paper/N3BKQSBE"},"agent_actions":{"view_html":"https://pith.science/pith/N3BKQSBEQKNXKXSISCFIWW42LP","download_json":"https://pith.science/pith/N3BKQSBEQKNXKXSISCFIWW42LP.json","view_paper":"https://pith.science/paper/N3BKQSBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.00033&json=true","fetch_graph":"https://pith.science/api/pith-number/N3BKQSBEQKNXKXSISCFIWW42LP/graph.json","fetch_events":"https://pith.science/api/pith-number/N3BKQSBEQKNXKXSISCFIWW42LP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3BKQSBEQKNXKXSISCFIWW42LP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3BKQSBEQKNXKXSISCFIWW42LP/action/storage_attestation","attest_author":"https://pith.science/pith/N3BKQSBEQKNXKXSISCFIWW42LP/action/author_attestation","sign_citation":"https://pith.science/pith/N3BKQSBEQKNXKXSISCFIWW42LP/action/citation_signature","submit_replication":"https://pith.science/pith/N3BKQSBEQKNXKXSISCFIWW42LP/action/replication_record"}},"created_at":"2026-07-05T09:42:35.000006+00:00","updated_at":"2026-07-05T09:42:35.000006+00:00"}