{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PUEW2YYLCPUXNJLTJ5NSJSIMTR","short_pith_number":"pith:PUEW2YYL","schema_version":"1.0","canonical_sha256":"7d096d630b13e976a5734f5b24c90c9c645d94e0a6bbadea85280adeb8afbb6e","source":{"kind":"arxiv","id":"2607.01254","version":1},"attestation_state":"computed","paper":{"title":"The Benchmark Ceiling: Human Judgment, Evaluation Scarcity, and the Political Economy of AI Capability Measurement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["econ.GN","q-fin.EC"],"primary_cat":"cs.CY","authors_text":"Ali Ansari, Liu Zhang, Mark Esposito","submitted_at":"2026-06-04T04:34:57Z","abstract_excerpt":"Benchmarks are the primary instruments through which AI capability is measured, compared, and governed. This paper argues that the validity of frontier AI benchmarks is a function of the quality of human judgment embedded in their construction, and that this quality is structurally scarce in ways that standard scaling narratives obscure. As foundation models approach ceiling performance on existing evaluation suites, discriminating signal concentrates in the hardest benchmark items, precisely those requiring elite expert judgment to design. We term this the benchmark ceiling problem: the progr"},"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":"2607.01254","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CY","submitted_at":"2026-06-04T04:34:57Z","cross_cats_sorted":["econ.GN","q-fin.EC"],"title_canon_sha256":"c1a9aad83c31bac19530556a522a205d8e662c7bf70279be233ae6a2b7e37c67","abstract_canon_sha256":"f552706df0e518ce84a5165d789a1c6466a650fc0c9e191fc155ae88ca157289"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T00:16:55.634461Z","signature_b64":"JjUhwl0yDURNUYQQfSSrbz3bPBXkaZ9j+14DjYIyl6jzs/1jNpvH3wgRGrY/H+6sgorwuIZDnj1Frl1dtvJcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7d096d630b13e976a5734f5b24c90c9c645d94e0a6bbadea85280adeb8afbb6e","last_reissued_at":"2026-07-03T00:16:55.634101Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T00:16:55.634101Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Benchmark Ceiling: Human Judgment, Evaluation Scarcity, and the Political Economy of AI Capability Measurement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["econ.GN","q-fin.EC"],"primary_cat":"cs.CY","authors_text":"Ali Ansari, Liu Zhang, Mark Esposito","submitted_at":"2026-06-04T04:34:57Z","abstract_excerpt":"Benchmarks are the primary instruments through which AI capability is measured, compared, and governed. This paper argues that the validity of frontier AI benchmarks is a function of the quality of human judgment embedded in their construction, and that this quality is structurally scarce in ways that standard scaling narratives obscure. As foundation models approach ceiling performance on existing evaluation suites, discriminating signal concentrates in the hardest benchmark items, precisely those requiring elite expert judgment to design. We term this the benchmark ceiling problem: the progr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01254","kind":"arxiv","version":1},"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/2607.01254/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":"2607.01254","created_at":"2026-07-03T00:16:55.634161+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01254v1","created_at":"2026-07-03T00:16:55.634161+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01254","created_at":"2026-07-03T00:16:55.634161+00:00"},{"alias_kind":"pith_short_12","alias_value":"PUEW2YYLCPUX","created_at":"2026-07-03T00:16:55.634161+00:00"},{"alias_kind":"pith_short_16","alias_value":"PUEW2YYLCPUXNJLT","created_at":"2026-07-03T00:16:55.634161+00:00"},{"alias_kind":"pith_short_8","alias_value":"PUEW2YYL","created_at":"2026-07-03T00:16:55.634161+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PUEW2YYLCPUXNJLTJ5NSJSIMTR","json":"https://pith.science/pith/PUEW2YYLCPUXNJLTJ5NSJSIMTR.json","graph_json":"https://pith.science/api/pith-number/PUEW2YYLCPUXNJLTJ5NSJSIMTR/graph.json","events_json":"https://pith.science/api/pith-number/PUEW2YYLCPUXNJLTJ5NSJSIMTR/events.json","paper":"https://pith.science/paper/PUEW2YYL"},"agent_actions":{"view_html":"https://pith.science/pith/PUEW2YYLCPUXNJLTJ5NSJSIMTR","download_json":"https://pith.science/pith/PUEW2YYLCPUXNJLTJ5NSJSIMTR.json","view_paper":"https://pith.science/paper/PUEW2YYL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01254&json=true","fetch_graph":"https://pith.science/api/pith-number/PUEW2YYLCPUXNJLTJ5NSJSIMTR/graph.json","fetch_events":"https://pith.science/api/pith-number/PUEW2YYLCPUXNJLTJ5NSJSIMTR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PUEW2YYLCPUXNJLTJ5NSJSIMTR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PUEW2YYLCPUXNJLTJ5NSJSIMTR/action/storage_attestation","attest_author":"https://pith.science/pith/PUEW2YYLCPUXNJLTJ5NSJSIMTR/action/author_attestation","sign_citation":"https://pith.science/pith/PUEW2YYLCPUXNJLTJ5NSJSIMTR/action/citation_signature","submit_replication":"https://pith.science/pith/PUEW2YYLCPUXNJLTJ5NSJSIMTR/action/replication_record"}},"created_at":"2026-07-03T00:16:55.634161+00:00","updated_at":"2026-07-03T00:16:55.634161+00:00"}