{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2DXL7W2GX7HRDS4AGRUZ4DDREP","short_pith_number":"pith:2DXL7W2G","schema_version":"1.0","canonical_sha256":"d0eebfdb46bfcf11cb8034699e0c7123c9f06838ad846c1ea9acab6dae6952d3","source":{"kind":"arxiv","id":"2407.15645","version":1},"attestation_state":"computed","paper":{"title":"Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benjamin W. Domingue, Emma Brunskill, Joy He-Yueya, Kanishk Gandhi, Noah D. Goodman, Wanjing Anya Ma","submitted_at":"2024-07-22T14:02:59Z","abstract_excerpt":"Language models (LMs) are increasingly used to simulate human-like responses in scenarios where accurately mimicking a population's behavior can guide decision-making, such as in developing educational materials and designing public policies. The objective of these simulations is for LMs to capture the variations in human responses, rather than merely providing the expected correct answers. Prior work has shown that LMs often generate unrealistically accurate responses, but there are no established metrics to quantify how closely the knowledge distribution of LMs aligns with that of humans. To"},"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":"2407.15645","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-22T14:02:59Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"519d112283d0f58d4b7ed461e086e4bcab0e87b7f7d09de4cbcab492ec610cf3","abstract_canon_sha256":"72fd81b72c05ff7bd0fd7c44be6d1cab0a0fd8100fc7c5b7e68217e3df1d94d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:46:59.260572Z","signature_b64":"MGyke2cjnThLwGvckhl6Eu8FneNlM5PgvtqJTD6oQWUypkunWcl16h9zaNsAurofKNdqQEIoHnvr+htuQhn3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0eebfdb46bfcf11cb8034699e0c7123c9f06838ad846c1ea9acab6dae6952d3","last_reissued_at":"2026-07-05T08:46:59.260074Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:46:59.260074Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benjamin W. Domingue, Emma Brunskill, Joy He-Yueya, Kanishk Gandhi, Noah D. Goodman, Wanjing Anya Ma","submitted_at":"2024-07-22T14:02:59Z","abstract_excerpt":"Language models (LMs) are increasingly used to simulate human-like responses in scenarios where accurately mimicking a population's behavior can guide decision-making, such as in developing educational materials and designing public policies. The objective of these simulations is for LMs to capture the variations in human responses, rather than merely providing the expected correct answers. Prior work has shown that LMs often generate unrealistically accurate responses, but there are no established metrics to quantify how closely the knowledge distribution of LMs aligns with that of humans. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15645","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/2407.15645/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":"2407.15645","created_at":"2026-07-05T08:46:59.260131+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15645v1","created_at":"2026-07-05T08:46:59.260131+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15645","created_at":"2026-07-05T08:46:59.260131+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DXL7W2GX7HR","created_at":"2026-07-05T08:46:59.260131+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DXL7W2GX7HRDS4A","created_at":"2026-07-05T08:46:59.260131+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DXL7W2G","created_at":"2026-07-05T08:46:59.260131+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.17773","citing_title":"How Many Human Survey Respondents is a Large Language Model Worth? An Uncertainty Quantification Perspective","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16290","citing_title":"MCQ Difficulty Prediction via Modeling Learner Heterogeneity Using Data-Driven Cognitive Profiling","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2512.05024","citing_title":"Model-Free Assessment of Simulator Fidelity via Quantile Curves","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DXL7W2GX7HRDS4AGRUZ4DDREP","json":"https://pith.science/pith/2DXL7W2GX7HRDS4AGRUZ4DDREP.json","graph_json":"https://pith.science/api/pith-number/2DXL7W2GX7HRDS4AGRUZ4DDREP/graph.json","events_json":"https://pith.science/api/pith-number/2DXL7W2GX7HRDS4AGRUZ4DDREP/events.json","paper":"https://pith.science/paper/2DXL7W2G"},"agent_actions":{"view_html":"https://pith.science/pith/2DXL7W2GX7HRDS4AGRUZ4DDREP","download_json":"https://pith.science/pith/2DXL7W2GX7HRDS4AGRUZ4DDREP.json","view_paper":"https://pith.science/paper/2DXL7W2G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15645&json=true","fetch_graph":"https://pith.science/api/pith-number/2DXL7W2GX7HRDS4AGRUZ4DDREP/graph.json","fetch_events":"https://pith.science/api/pith-number/2DXL7W2GX7HRDS4AGRUZ4DDREP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DXL7W2GX7HRDS4AGRUZ4DDREP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DXL7W2GX7HRDS4AGRUZ4DDREP/action/storage_attestation","attest_author":"https://pith.science/pith/2DXL7W2GX7HRDS4AGRUZ4DDREP/action/author_attestation","sign_citation":"https://pith.science/pith/2DXL7W2GX7HRDS4AGRUZ4DDREP/action/citation_signature","submit_replication":"https://pith.science/pith/2DXL7W2GX7HRDS4AGRUZ4DDREP/action/replication_record"}},"created_at":"2026-07-05T08:46:59.260131+00:00","updated_at":"2026-07-05T08:46:59.260131+00:00"}