{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JAG7JOBOQKX6KF36QQJ6PV4IAO","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":"fd19b117da14632906cd111bc0c31397ccd2a669b2fbc49fa8cec2d4fad4e876","cross_cats_sorted":["cs.AI","cs.CL","cs.CR","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-30T12:51:47Z","title_canon_sha256":"8eda025641aa8c0478cfb1dfd18ccf1bf2586aa4dd4fe649c770b897066d11d9"},"schema_version":"1.0","source":{"id":"2503.23424","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23424","created_at":"2026-07-05T10:41:36Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23424v1","created_at":"2026-07-05T10:41:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23424","created_at":"2026-07-05T10:41:36Z"},{"alias_kind":"pith_short_12","alias_value":"JAG7JOBOQKX6","created_at":"2026-07-05T10:41:36Z"},{"alias_kind":"pith_short_16","alias_value":"JAG7JOBOQKX6KF36","created_at":"2026-07-05T10:41:36Z"},{"alias_kind":"pith_short_8","alias_value":"JAG7JOBO","created_at":"2026-07-05T10:41:36Z"}],"graph_snapshots":[{"event_id":"sha256:e5801053069e5627fa3c65a0453a7b2645a837ead3e4fa48287d1e96f1c071c7","target":"graph","created_at":"2026-07-05T10:41:36Z","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/2503.23424/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Following the rapid increase in Artificial Intelligence (AI) capabilities in recent years, the AI community has voiced concerns regarding possible safety risks. To support decision-making on the safe use and development of AI systems, there is a growing need for high-quality evaluations of dangerous model capabilities. While several attempts to provide such evaluations have been made, a clear definition of what constitutes a \"good evaluation\" has yet to be agreed upon. In this practitioners' perspective paper, we present a set of best practices for safety evaluations, drawing on prior work in ","authors_text":"Dan Lahav, Gil Gekker, Meirav Segal, Omer Nevo","cross_cats":["cs.AI","cs.CL","cs.CR","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-30T12:51:47Z","title":"What Makes an Evaluation Useful? Common Pitfalls and Best Practices"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23424","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":"sha256:593f6c6921c2c91d96c77a0f3abff64c7b0680479e063db89790d306361b26b3","target":"record","created_at":"2026-07-05T10:41:36Z","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":"fd19b117da14632906cd111bc0c31397ccd2a669b2fbc49fa8cec2d4fad4e876","cross_cats_sorted":["cs.AI","cs.CL","cs.CR","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-30T12:51:47Z","title_canon_sha256":"8eda025641aa8c0478cfb1dfd18ccf1bf2586aa4dd4fe649c770b897066d11d9"},"schema_version":"1.0","source":{"id":"2503.23424","kind":"arxiv","version":1}},"canonical_sha256":"480df4b82e82afe5177e8413e7d788039092012edbeb0d84402cc804403e8523","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"480df4b82e82afe5177e8413e7d788039092012edbeb0d84402cc804403e8523","first_computed_at":"2026-07-05T10:41:36.175896Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:36.175896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wSuU1tWSFY73ENwcZcMOA7t9j6G5B2CxKiVRdu6UVpwcUz0diYsTbge4kXc4wg0Vje+78WwPHDrE9TYLhAJECA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:36.176397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23424","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:593f6c6921c2c91d96c77a0f3abff64c7b0680479e063db89790d306361b26b3","sha256:e5801053069e5627fa3c65a0453a7b2645a837ead3e4fa48287d1e96f1c071c7"],"state_sha256":"0c9ee322f66bf3a7fbeb6a2254d04d8f51c0e024c0d6e2901efdc49fd9d99e2d"}