{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:T2QFMI4MSDL4MC3ZOYUAK47BB4","short_pith_number":"pith:T2QFMI4M","schema_version":"1.0","canonical_sha256":"9ea056238c90d7c60b7976280573e10f3acdda477afabc99af23da17d7f75ea2","source":{"kind":"arxiv","id":"2412.01934","version":1},"attestation_state":"computed","paper":{"title":"A Shared Standard for Valid Measurement of Generative AI Systems' Capabilities, Risks, and Impacts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"A. Feder Cooper, Alexandra Chouldechova, Chad Atalla, Dan Vann, Emily Corvi, Emily Sheng, Hannah Washington, Hanna Wallach, Jean Garcia-Gathright, Matthew Vogel, Nicholas Pangakis, P. Alex Dow, Solon Barocas, Stefanie Reed","submitted_at":"2024-12-02T19:50:00Z","abstract_excerpt":"The valid measurement of generative AI (GenAI) systems' capabilities, risks, and impacts forms the bedrock of our ability to evaluate these systems. We introduce a shared standard for valid measurement that helps place many of the disparate-seeming evaluation practices in use today on a common footing. Our framework, grounded in measurement theory from the social sciences, extends the work of Adcock & Collier (2001) in which the authors formalized valid measurement of concepts in political science via three processes: systematizing background concepts, operationalizing systematized concepts vi"},"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":"2412.01934","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2024-12-02T19:50:00Z","cross_cats_sorted":[],"title_canon_sha256":"e92a6695c2f4e53d68a37e364c31d7b393a622f756db2ce9437007a806b8018a","abstract_canon_sha256":"aa10d1c53996e1e0cf3775af73e74f84a021a2cb3825188161d8f9f99d33e069"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:41.217301Z","signature_b64":"F1gA+B+yUEmyaN6i5d7j9MhN6oEc4gIn7L7ISboWL0FzQnDIsDEeSotZ5HjAPZh/2UvpASU3G81w7ovxmggSDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ea056238c90d7c60b7976280573e10f3acdda477afabc99af23da17d7f75ea2","last_reissued_at":"2026-07-05T09:43:41.216827Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:41.216827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Shared Standard for Valid Measurement of Generative AI Systems' Capabilities, Risks, and Impacts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CY","authors_text":"A. Feder Cooper, Alexandra Chouldechova, Chad Atalla, Dan Vann, Emily Corvi, Emily Sheng, Hannah Washington, Hanna Wallach, Jean Garcia-Gathright, Matthew Vogel, Nicholas Pangakis, P. Alex Dow, Solon Barocas, Stefanie Reed","submitted_at":"2024-12-02T19:50:00Z","abstract_excerpt":"The valid measurement of generative AI (GenAI) systems' capabilities, risks, and impacts forms the bedrock of our ability to evaluate these systems. We introduce a shared standard for valid measurement that helps place many of the disparate-seeming evaluation practices in use today on a common footing. Our framework, grounded in measurement theory from the social sciences, extends the work of Adcock & Collier (2001) in which the authors formalized valid measurement of concepts in political science via three processes: systematizing background concepts, operationalizing systematized concepts vi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.01934","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/2412.01934/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":"2412.01934","created_at":"2026-07-05T09:43:41.216881+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.01934v1","created_at":"2026-07-05T09:43:41.216881+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.01934","created_at":"2026-07-05T09:43:41.216881+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2QFMI4MSDL4","created_at":"2026-07-05T09:43:41.216881+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2QFMI4MSDL4MC3Z","created_at":"2026-07-05T09:43:41.216881+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2QFMI4M","created_at":"2026-07-05T09:43:41.216881+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22612","citing_title":"Healthcare LLM Benchmarks Are Only as Good as Their Explicit Assumptions","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.06811","citing_title":"Making AI Evaluation Deployment Relevant Through Context Specification","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2QFMI4MSDL4MC3ZOYUAK47BB4","json":"https://pith.science/pith/T2QFMI4MSDL4MC3ZOYUAK47BB4.json","graph_json":"https://pith.science/api/pith-number/T2QFMI4MSDL4MC3ZOYUAK47BB4/graph.json","events_json":"https://pith.science/api/pith-number/T2QFMI4MSDL4MC3ZOYUAK47BB4/events.json","paper":"https://pith.science/paper/T2QFMI4M"},"agent_actions":{"view_html":"https://pith.science/pith/T2QFMI4MSDL4MC3ZOYUAK47BB4","download_json":"https://pith.science/pith/T2QFMI4MSDL4MC3ZOYUAK47BB4.json","view_paper":"https://pith.science/paper/T2QFMI4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.01934&json=true","fetch_graph":"https://pith.science/api/pith-number/T2QFMI4MSDL4MC3ZOYUAK47BB4/graph.json","fetch_events":"https://pith.science/api/pith-number/T2QFMI4MSDL4MC3ZOYUAK47BB4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2QFMI4MSDL4MC3ZOYUAK47BB4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2QFMI4MSDL4MC3ZOYUAK47BB4/action/storage_attestation","attest_author":"https://pith.science/pith/T2QFMI4MSDL4MC3ZOYUAK47BB4/action/author_attestation","sign_citation":"https://pith.science/pith/T2QFMI4MSDL4MC3ZOYUAK47BB4/action/citation_signature","submit_replication":"https://pith.science/pith/T2QFMI4MSDL4MC3ZOYUAK47BB4/action/replication_record"}},"created_at":"2026-07-05T09:43:41.216881+00:00","updated_at":"2026-07-05T09:43:41.216881+00:00"}