{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:GQHJFRVRKAQQDJA3UXKSWFSMGP","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":"2a5424e9587c647de2aef9f4b0ee7edae8b245d57e88fe4d4a5a16cb08dc6009","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-08T16:55:07Z","title_canon_sha256":"db6648453b5542dd2db655baacf7597bb3d52e0f67a84d8eb020daadd135db0b"},"schema_version":"1.0","source":{"id":"2505.05541","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05541","created_at":"2026-07-05T11:00:27Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05541v1","created_at":"2026-07-05T11:00:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05541","created_at":"2026-07-05T11:00:27Z"},{"alias_kind":"pith_short_12","alias_value":"GQHJFRVRKAQQ","created_at":"2026-07-05T11:00:27Z"},{"alias_kind":"pith_short_16","alias_value":"GQHJFRVRKAQQDJA3","created_at":"2026-07-05T11:00:27Z"},{"alias_kind":"pith_short_8","alias_value":"GQHJFRVR","created_at":"2026-07-05T11:00:27Z"}],"graph_snapshots":[{"event_id":"sha256:450eab4bc50bd5b7d574e50c7603fc4d858e1ad8b29795d25cef08c5829384f4","target":"graph","created_at":"2026-07-05T11:00:27Z","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/2505.05541/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As frontier AI systems advance toward transformative capabilities, we need a parallel transformation in how we measure and evaluate these systems to ensure safety and inform governance. While benchmarks have been the primary method for estimating model capabilities, they often fail to establish true upper bounds or predict deployment behavior. This literature review consolidates the rapidly evolving field of AI safety evaluations, proposing a systematic taxonomy around three dimensions: what properties we measure, how we measure them, and how these measurements integrate into frameworks. We sh","authors_text":"Charbel-Rapha\\\"el Segerie, Markov Grey","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-08T16:55:07Z","title":"Safety by Measurement: A Systematic Literature Review of AI Safety Evaluation Methods"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05541","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":"sha256:9310ebc75d9a1233ceb6d8ce6a1de6d999f61636cd3cfe10c87f685f17394201","target":"record","created_at":"2026-07-05T11:00:27Z","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":"2a5424e9587c647de2aef9f4b0ee7edae8b245d57e88fe4d4a5a16cb08dc6009","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-05-08T16:55:07Z","title_canon_sha256":"db6648453b5542dd2db655baacf7597bb3d52e0f67a84d8eb020daadd135db0b"},"schema_version":"1.0","source":{"id":"2505.05541","kind":"arxiv","version":1}},"canonical_sha256":"340e92c6b1502101a41ba5d52b164c33d3c57f1c60425e36b29541ca6f9d4644","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"340e92c6b1502101a41ba5d52b164c33d3c57f1c60425e36b29541ca6f9d4644","first_computed_at":"2026-07-05T11:00:27.671528Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:27.671528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z9FeevnmoUqOtL2UN86YIDQLFXz7PCw8/ShL66Ry+fbEi3o5WiSdXVecifhJJQ4vkyljAKT5+wA5eRY752odBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:27.672062Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05541","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9310ebc75d9a1233ceb6d8ce6a1de6d999f61636cd3cfe10c87f685f17394201","sha256:450eab4bc50bd5b7d574e50c7603fc4d858e1ad8b29795d25cef08c5829384f4"],"state_sha256":"f82fb09c2180406cf09951facb42931e9adb7e4d7e55024d8c43618d09651dd4"}