{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S6B7DJ5H5GPF2WHN4QP4FIX72A","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":"10d7e152e0da03b6a62fa2139a38afffbe23cae26528e638bf11260cdd8461c5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-09T18:10:42Z","title_canon_sha256":"c1950352e6fec78e28d3f5edeec0275ba58eedb5473f13c80d39e9b3fc7dcbde"},"schema_version":"1.0","source":{"id":"2408.05284","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05284","created_at":"2026-07-05T11:21:34Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05284v3","created_at":"2026-07-05T11:21:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05284","created_at":"2026-07-05T11:21:34Z"},{"alias_kind":"pith_short_12","alias_value":"S6B7DJ5H5GPF","created_at":"2026-07-05T11:21:34Z"},{"alias_kind":"pith_short_16","alias_value":"S6B7DJ5H5GPF2WHN","created_at":"2026-07-05T11:21:34Z"},{"alias_kind":"pith_short_8","alias_value":"S6B7DJ5H","created_at":"2026-07-05T11:21:34Z"}],"graph_snapshots":[{"event_id":"sha256:712ef99d97b41fdb6de500d94e4c5c6aacee3eec5e158340a055ecb715228586","target":"graph","created_at":"2026-07-05T11:21:34Z","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/2408.05284/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Is there a way to design powerful AI systems based on machine learning methods that would satisfy probabilistic safety guarantees? With the long-term goal of obtaining a probabilistic guarantee that would apply in every context, we consider estimating a context-dependent bound on the probability of violating a given safety specification. Such a risk evaluation would need to be performed at run-time to provide a guardrail against dangerous actions of an AI. Noting that different plausible hypotheses about the world could produce very different outcomes, and because we do not know which one is r","authors_text":"Damiano Fornasiere, Matt MacDermott, Michael K. Cohen, Nikolay Malkin, Pietro Greiner, Yoshua Bengio, Younesse Kaddar","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-09T18:10:42Z","title":"Can a Bayesian Oracle Prevent Harm from an Agent?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05284","kind":"arxiv","version":3},"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":"sha256:27abe26228d325e009fe78e4cfc5a493f0b6bbf47f055a74865526443be88bab","target":"record","created_at":"2026-07-05T11:21:34Z","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":"10d7e152e0da03b6a62fa2139a38afffbe23cae26528e638bf11260cdd8461c5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-08-09T18:10:42Z","title_canon_sha256":"c1950352e6fec78e28d3f5edeec0275ba58eedb5473f13c80d39e9b3fc7dcbde"},"schema_version":"1.0","source":{"id":"2408.05284","kind":"arxiv","version":3}},"canonical_sha256":"9783f1a7a7e99e5d58ede41fc2a2ffd01c28809668b1c85ed05bd912bc60c8a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9783f1a7a7e99e5d58ede41fc2a2ffd01c28809668b1c85ed05bd912bc60c8a7","first_computed_at":"2026-07-05T11:21:34.865775Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:21:34.865775Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cLXPDyRsZhrsbTyC3fudEoHc0hSKsgNBwitJ20b+UelHh9W95Q2jPHyYXI/XYkOUV5SwOyqN+J2fMwo9lc9MAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:21:34.866305Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.05284","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27abe26228d325e009fe78e4cfc5a493f0b6bbf47f055a74865526443be88bab","sha256:712ef99d97b41fdb6de500d94e4c5c6aacee3eec5e158340a055ecb715228586"],"state_sha256":"8aa7cdaa2427e12a85166646500a721b70f48dc889e682b82bff8e3c9e3a95f9"}