{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HXZVXJNQPCT5IRQ5JTLHNHFJAW","short_pith_number":"pith:HXZVXJNQ","schema_version":"1.0","canonical_sha256":"3df35ba5b078a7d4461d4cd6769ca90584886cab253ca3ba7f7ba229d67174b3","source":{"kind":"arxiv","id":"2505.16164","version":2},"attestation_state":"computed","paper":{"title":"Can LLMs Simulate Human Behavioral Variability? A Case Study in the Phonemic Fluency Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mengyang Qiu, Siena Sun, Zoe Brisebois","submitted_at":"2025-05-22T03:08:27Z","abstract_excerpt":"Large language models (LLMs) are increasingly explored as substitutes for human participants in cognitive tasks, but their ability to simulate human behavioral variability remains unclear. This study examines whether LLMs can approximate individual differences in the phonemic fluency task, where participants generate words beginning with a target letter. We evaluated 34 distinct models across 45 configurations from major closed-source and open-source providers, and compared outputs to responses from 106 human participants. While some models, especially Claude 3.7 Sonnet, approximated human ave"},"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":"2505.16164","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-22T03:08:27Z","cross_cats_sorted":[],"title_canon_sha256":"b87073d9c63eedb223dfc875afcf29641147b2fcc7edde74ae6843587a34bee3","abstract_canon_sha256":"8fd3d0ce1f929ea8c1b6d91bf4d6faf05234d36a9cfe40afc82ae56bed2b14c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:16:51.697192Z","signature_b64":"vuOmbG+age/PsLGJoeqWrBUSKcuBdZv8zQgNpFinV6DJ7H0jFWEz4r0DCsYEfzJX2wuXjyOr6/sO8/UZPcr9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3df35ba5b078a7d4461d4cd6769ca90584886cab253ca3ba7f7ba229d67174b3","last_reissued_at":"2026-06-30T02:16:51.696541Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:16:51.696541Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can LLMs Simulate Human Behavioral Variability? A Case Study in the Phonemic Fluency Task","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mengyang Qiu, Siena Sun, Zoe Brisebois","submitted_at":"2025-05-22T03:08:27Z","abstract_excerpt":"Large language models (LLMs) are increasingly explored as substitutes for human participants in cognitive tasks, but their ability to simulate human behavioral variability remains unclear. This study examines whether LLMs can approximate individual differences in the phonemic fluency task, where participants generate words beginning with a target letter. We evaluated 34 distinct models across 45 configurations from major closed-source and open-source providers, and compared outputs to responses from 106 human participants. While some models, especially Claude 3.7 Sonnet, approximated human ave"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.16164","kind":"arxiv","version":2},"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/2505.16164/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":"2505.16164","created_at":"2026-06-30T02:16:51.696623+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.16164v2","created_at":"2026-06-30T02:16:51.696623+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.16164","created_at":"2026-06-30T02:16:51.696623+00:00"},{"alias_kind":"pith_short_12","alias_value":"HXZVXJNQPCT5","created_at":"2026-06-30T02:16:51.696623+00:00"},{"alias_kind":"pith_short_16","alias_value":"HXZVXJNQPCT5IRQ5","created_at":"2026-06-30T02:16:51.696623+00:00"},{"alias_kind":"pith_short_8","alias_value":"HXZVXJNQ","created_at":"2026-06-30T02:16:51.696623+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16164","citing_title":"Can LLMs Simulate Human Behavioral Variability? A Case Study in the Phonemic Fluency Task","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HXZVXJNQPCT5IRQ5JTLHNHFJAW","json":"https://pith.science/pith/HXZVXJNQPCT5IRQ5JTLHNHFJAW.json","graph_json":"https://pith.science/api/pith-number/HXZVXJNQPCT5IRQ5JTLHNHFJAW/graph.json","events_json":"https://pith.science/api/pith-number/HXZVXJNQPCT5IRQ5JTLHNHFJAW/events.json","paper":"https://pith.science/paper/HXZVXJNQ"},"agent_actions":{"view_html":"https://pith.science/pith/HXZVXJNQPCT5IRQ5JTLHNHFJAW","download_json":"https://pith.science/pith/HXZVXJNQPCT5IRQ5JTLHNHFJAW.json","view_paper":"https://pith.science/paper/HXZVXJNQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.16164&json=true","fetch_graph":"https://pith.science/api/pith-number/HXZVXJNQPCT5IRQ5JTLHNHFJAW/graph.json","fetch_events":"https://pith.science/api/pith-number/HXZVXJNQPCT5IRQ5JTLHNHFJAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HXZVXJNQPCT5IRQ5JTLHNHFJAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HXZVXJNQPCT5IRQ5JTLHNHFJAW/action/storage_attestation","attest_author":"https://pith.science/pith/HXZVXJNQPCT5IRQ5JTLHNHFJAW/action/author_attestation","sign_citation":"https://pith.science/pith/HXZVXJNQPCT5IRQ5JTLHNHFJAW/action/citation_signature","submit_replication":"https://pith.science/pith/HXZVXJNQPCT5IRQ5JTLHNHFJAW/action/replication_record"}},"created_at":"2026-06-30T02:16:51.696623+00:00","updated_at":"2026-06-30T02:16:51.696623+00:00"}