{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:VOPSUG2XRQ5IFUIWE4PE7TCAAY","short_pith_number":"pith:VOPSUG2X","schema_version":"1.0","canonical_sha256":"ab9f2a1b578c3a82d116271e4fcc4006147a0295a26621fec8a3d08efca6f9ee","source":{"kind":"arxiv","id":"2306.10512","version":4},"attestation_state":"computed","paper":{"title":"Position: AI Evaluation Should Learn from How We Test Humans","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Enhong Chen, Jiyun Zu, Patrick C. Kyllonen, Qi Liu, Shijin Wang, Yan Zhuang, Zachary A. Pardos, Zhenya Huang","submitted_at":"2023-06-18T09:54:33Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.10512","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-06-18T09:54:33Z","cross_cats_sorted":[],"title_canon_sha256":"c4c233eaf3585868bf513f0a84b020b24bcaa1e08ab333aac7e6927104fb783b","abstract_canon_sha256":"f23ac50bd3ab5cfb88510e450f7fb05c83a0f45f71ed1e36a3f779bcf3f8e6a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:59:56.227756Z","signature_b64":"0l8QhpY+nbrLRA599s2b58nFX8LCMiVnh+pWOmHwp20xq3c3dRoF1poxszMWmlbo+k2Xx/Svlatwg7SCn7ZLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab9f2a1b578c3a82d116271e4fcc4006147a0295a26621fec8a3d08efca6f9ee","last_reissued_at":"2026-07-05T10:59:56.227269Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:59:56.227269Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Position: AI Evaluation Should Learn from How We Test Humans","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Enhong Chen, Jiyun Zu, Patrick C. Kyllonen, Qi Liu, Shijin Wang, Yan Zhuang, Zachary A. Pardos, Zhenya Huang","submitted_at":"2023-06-18T09:54:33Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.10512","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.10512/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.10512","created_at":"2026-07-05T10:59:56.227336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.10512v4","created_at":"2026-07-05T10:59:56.227336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.10512","created_at":"2026-07-05T10:59:56.227336+00:00"},{"alias_kind":"pith_short_12","alias_value":"VOPSUG2XRQ5I","created_at":"2026-07-05T10:59:56.227336+00:00"},{"alias_kind":"pith_short_16","alias_value":"VOPSUG2XRQ5IFUIW","created_at":"2026-07-05T10:59:56.227336+00:00"},{"alias_kind":"pith_short_8","alias_value":"VOPSUG2X","created_at":"2026-07-05T10:59:56.227336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2509.19590","citing_title":"Position: AI Evaluations Should be Grounded on a Theory of Capability","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27405","citing_title":"Beyond the Mean: Within-Model Reliable Change Detection for LLM Evaluation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19357","citing_title":"FairTree: Subgroup Fairness Auditing of Machine Learning Models with Bias-Variance Decomposition","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VOPSUG2XRQ5IFUIWE4PE7TCAAY","json":"https://pith.science/pith/VOPSUG2XRQ5IFUIWE4PE7TCAAY.json","graph_json":"https://pith.science/api/pith-number/VOPSUG2XRQ5IFUIWE4PE7TCAAY/graph.json","events_json":"https://pith.science/api/pith-number/VOPSUG2XRQ5IFUIWE4PE7TCAAY/events.json","paper":"https://pith.science/paper/VOPSUG2X"},"agent_actions":{"view_html":"https://pith.science/pith/VOPSUG2XRQ5IFUIWE4PE7TCAAY","download_json":"https://pith.science/pith/VOPSUG2XRQ5IFUIWE4PE7TCAAY.json","view_paper":"https://pith.science/paper/VOPSUG2X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.10512&json=true","fetch_graph":"https://pith.science/api/pith-number/VOPSUG2XRQ5IFUIWE4PE7TCAAY/graph.json","fetch_events":"https://pith.science/api/pith-number/VOPSUG2XRQ5IFUIWE4PE7TCAAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VOPSUG2XRQ5IFUIWE4PE7TCAAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VOPSUG2XRQ5IFUIWE4PE7TCAAY/action/storage_attestation","attest_author":"https://pith.science/pith/VOPSUG2XRQ5IFUIWE4PE7TCAAY/action/author_attestation","sign_citation":"https://pith.science/pith/VOPSUG2XRQ5IFUIWE4PE7TCAAY/action/citation_signature","submit_replication":"https://pith.science/pith/VOPSUG2XRQ5IFUIWE4PE7TCAAY/action/replication_record"}},"created_at":"2026-07-05T10:59:56.227336+00:00","updated_at":"2026-07-05T10:59:56.227336+00:00"}