{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VOPSUG2XRQ5IFUIWE4PE7TCAAY","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":"f23ac50bd3ab5cfb88510e450f7fb05c83a0f45f71ed1e36a3f779bcf3f8e6a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-18T09:54:33Z","title_canon_sha256":"c4c233eaf3585868bf513f0a84b020b24bcaa1e08ab333aac7e6927104fb783b"},"schema_version":"1.0","source":{"id":"2306.10512","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.10512","created_at":"2026-07-05T10:59:56Z"},{"alias_kind":"arxiv_version","alias_value":"2306.10512v4","created_at":"2026-07-05T10:59:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10512","created_at":"2026-07-05T10:59:56Z"},{"alias_kind":"pith_short_12","alias_value":"VOPSUG2XRQ5I","created_at":"2026-07-05T10:59:56Z"},{"alias_kind":"pith_short_16","alias_value":"VOPSUG2XRQ5IFUIW","created_at":"2026-07-05T10:59:56Z"},{"alias_kind":"pith_short_8","alias_value":"VOPSUG2X","created_at":"2026-07-05T10:59:56Z"}],"graph_snapshots":[{"event_id":"sha256:1ee44ece6ba02ec2dafaf63899b134cdc1b24008a0c58ea07acb7117f3a7cc0f","target":"graph","created_at":"2026-07-05T10:59:56Z","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/2306.10512/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As AI systems continue to evolve, their rigorous evaluation becomes crucial for their development and deployment. Researchers have constructed various large-scale benchmarks to determine their capabilities, typically against a gold-standard test set and report metrics averaged across all items. However, this static evaluation paradigm increasingly shows its limitations, including high evaluation costs, data contamination, and the impact of low-quality or erroneous items on evaluation reliability and efficiency. In this Position, drawing from human psychometrics, we discuss a paradigm shift fro","authors_text":"Enhong Chen, Jiyun Zu, Patrick C. Kyllonen, Qi Liu, Shijin Wang, Yan Zhuang, Zachary A. Pardos, Zhenya Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-18T09:54:33Z","title":"Position: AI Evaluation Should Learn from How We Test Humans"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10512","kind":"arxiv","version":4},"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:dabc296d879e616827ef765222aaab1eca3556541aa6a57b8ccfc1c0727aa952","target":"record","created_at":"2026-07-05T10:59:56Z","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":"f23ac50bd3ab5cfb88510e450f7fb05c83a0f45f71ed1e36a3f779bcf3f8e6a6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-18T09:54:33Z","title_canon_sha256":"c4c233eaf3585868bf513f0a84b020b24bcaa1e08ab333aac7e6927104fb783b"},"schema_version":"1.0","source":{"id":"2306.10512","kind":"arxiv","version":4}},"canonical_sha256":"ab9f2a1b578c3a82d116271e4fcc4006147a0295a26621fec8a3d08efca6f9ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab9f2a1b578c3a82d116271e4fcc4006147a0295a26621fec8a3d08efca6f9ee","first_computed_at":"2026-07-05T10:59:56.227269Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:56.227269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0l8QhpY+nbrLRA599s2b58nFX8LCMiVnh+pWOmHwp20xq3c3dRoF1poxszMWmlbo+k2Xx/Svlatwg7SCn7ZLAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:56.227756Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.10512","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dabc296d879e616827ef765222aaab1eca3556541aa6a57b8ccfc1c0727aa952","sha256:1ee44ece6ba02ec2dafaf63899b134cdc1b24008a0c58ea07acb7117f3a7cc0f"],"state_sha256":"5cfb001860d1c9cd41934ff8d0a5806fd2f09fc64c6fdeadcf7bb040cac9ec53"}