{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:C3N7F6T4K7IHMSE7V57P5RAEZU","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":"beae1739d19c3ef470774bfe59ed1d197ff339afb16b505340490ea63e9ff338","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-11-26T18:00:36Z","title_canon_sha256":"b8e7ca299f97a08046c6c38b96dd445856276415ac46054cc59c807c54dacd67"},"schema_version":"1.0","source":{"id":"2412.08653","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08653","created_at":"2026-07-05T09:47:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08653v1","created_at":"2026-07-05T09:47:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08653","created_at":"2026-07-05T09:47:58Z"},{"alias_kind":"pith_short_12","alias_value":"C3N7F6T4K7IH","created_at":"2026-07-05T09:47:58Z"},{"alias_kind":"pith_short_16","alias_value":"C3N7F6T4K7IHMSE7","created_at":"2026-07-05T09:47:58Z"},{"alias_kind":"pith_short_8","alias_value":"C3N7F6T4","created_at":"2026-07-05T09:47:58Z"}],"graph_snapshots":[{"event_id":"sha256:7d84a800bbeeea1695a337d29b4805c3c1782e3f8d85dc6370f1d132c213621d","target":"graph","created_at":"2026-07-05T09:47:58Z","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/2412.08653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"AI evaluations are an important component of the AI governance toolkit, underlying current approaches to safety cases for preventing catastrophic risks. Our paper examines what these evaluations can and cannot tell us. Evaluations can establish lower bounds on AI capabilities and assess certain misuse risks given sufficient effort from evaluators.\n  Unfortunately, evaluations face fundamental limitations that cannot be overcome within the current paradigm. These include an inability to establish upper bounds on capabilities, reliably forecast future model capabilities, or robustly assess risks","authors_text":"Lisa Thiergart, Peter Barnett","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-11-26T18:00:36Z","title":"What AI evaluations for preventing catastrophic risks can and cannot do"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08653","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":"sha256:590d266f6717842318e72fd64c3a0b5d76698ad258949adc0c2d707cba98b529","target":"record","created_at":"2026-07-05T09:47:58Z","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":"beae1739d19c3ef470774bfe59ed1d197ff339afb16b505340490ea63e9ff338","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2024-11-26T18:00:36Z","title_canon_sha256":"b8e7ca299f97a08046c6c38b96dd445856276415ac46054cc59c807c54dacd67"},"schema_version":"1.0","source":{"id":"2412.08653","kind":"arxiv","version":1}},"canonical_sha256":"16dbf2fa7c57d076489faf7efec404cd131eca990d25c2be784ec53fd7deb2c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"16dbf2fa7c57d076489faf7efec404cd131eca990d25c2be784ec53fd7deb2c2","first_computed_at":"2026-07-05T09:47:58.608963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:47:58.608963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gLmaxiA5NiCVgym6U0x7qbOP1z7owjGo8w0wOI9bIBPGT+6TmFCLLUPL6RA/Qum0cgMnfCzGrLf32Lh38/EeDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:47:58.609440Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08653","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:590d266f6717842318e72fd64c3a0b5d76698ad258949adc0c2d707cba98b529","sha256:7d84a800bbeeea1695a337d29b4805c3c1782e3f8d85dc6370f1d132c213621d"],"state_sha256":"1c45b62ad16ea6b8b57f02552e01c44cfc2d274920e87c3372b1b41903a22617"}