{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AKYL3ORJ5YGSBEMLHRIO7MPT62","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":"e33e8ec650bb60caea26572214b4146bf38cf0a2e9cd08fba1a029f72737d568","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2025-07-22T03:27:42Z","title_canon_sha256":"8c0c9c01f84dece1ae858d9d6c5fc74b4b6481cc142e5bd148a2b2b919b59183"},"schema_version":"1.0","source":{"id":"2508.00875","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.00875","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"arxiv_version","alias_value":"2508.00875v1","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00875","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_12","alias_value":"AKYL3ORJ5YGS","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_16","alias_value":"AKYL3ORJ5YGSBEML","created_at":"2026-07-05T11:55:41Z"},{"alias_kind":"pith_short_8","alias_value":"AKYL3ORJ","created_at":"2026-07-05T11:55:41Z"}],"graph_snapshots":[{"event_id":"sha256:361f84bfa8d6ddefdc410a7e15e4cc9982e740998c4ad5b9a8394042f725a0bb","target":"graph","created_at":"2026-07-05T11:55:41Z","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/2508.00875/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This document presents a preliminary compilation of general-purpose AI (GPAI) evaluation practices that may promote internal validity, external validity and reproducibility. It includes suggestions for human uplift studies and benchmark evaluations, as well as cross-cutting suggestions that may apply to many different evaluation types. Suggestions are organised across four stages in the evaluation life cycle: design, implementation, execution and documentation. Drawing from established practices in machine learning, statistics, psychology, economics, biology and other fields recognised to have","authors_text":"Kevin Wei, Michael J. Byun, Patricia Paskov, Toby Webster","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2025-07-22T03:27:42Z","title":"Preliminary suggestions for rigorous GPAI model evaluations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00875","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":"sha256:27b939d1b610499a1067c156d9ed94d32c0441efb6cab8437d2d75a79dd5205f","target":"record","created_at":"2026-07-05T11:55:41Z","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":"e33e8ec650bb60caea26572214b4146bf38cf0a2e9cd08fba1a029f72737d568","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CY","submitted_at":"2025-07-22T03:27:42Z","title_canon_sha256":"8c0c9c01f84dece1ae858d9d6c5fc74b4b6481cc142e5bd148a2b2b919b59183"},"schema_version":"1.0","source":{"id":"2508.00875","kind":"arxiv","version":1}},"canonical_sha256":"02b0bdba29ee0d20918b3c50efb1f3f6b493c025eccd5d197ffbed2fc29f53a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"02b0bdba29ee0d20918b3c50efb1f3f6b493c025eccd5d197ffbed2fc29f53a6","first_computed_at":"2026-07-05T11:55:41.859403Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:41.859403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lVNVkXz8h6A3dHxtcmuO3OM65u0DEGgAjZyQgSwkNRfgGslw9vhwo510Cba3P4cFgGKG5cd/+MZmFg/YLcYFDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:41.859819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.00875","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:27b939d1b610499a1067c156d9ed94d32c0441efb6cab8437d2d75a79dd5205f","sha256:361f84bfa8d6ddefdc410a7e15e4cc9982e740998c4ad5b9a8394042f725a0bb"],"state_sha256":"22830314b70fb59c49e64e57bc52b13a9f58d5d6c570c5e1229da2fd302c6a68"}