{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X2Q352X7HPEABZA2QTYOADVCTZ","short_pith_number":"pith:X2Q352X7","schema_version":"1.0","canonical_sha256":"bea1beeaff3bc800e41a84f0e00ea29e60b3058d578ddec258f96282c0b79995","source":{"kind":"arxiv","id":"2510.03310","version":2},"attestation_state":"computed","paper":{"title":"Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mingyang Zhao, Runze Zhang, Xiaowei Zhang","submitted_at":"2025-09-30T20:20:58Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to simulate human behavior in business, economics, and the social sciences, offering a low-cost complement to laboratory experiments, field studies, and surveys. This paper evaluates how well LLMs replicate human behavior in operations management. Using nine published behavioral-operations experiments, we assess LLM performance along two dimensions: whether LLM-generated data reproduce the original hypothesis-test outcomes, and whether their full response distributions align with human data, measured by Wasserstein distance. We find that LLMs "},"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":"2510.03310","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-09-30T20:20:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4e5f6c040ebbe2d102e01342529b26ccc5bba0fbf9f0775fe327783e80525f37","abstract_canon_sha256":"08927954ccb41bcd9e9f3bf1c77d6443fd15eb5674371da061a13de5333fbd6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:16:25.561680Z","signature_b64":"6R+Ze7+ETCO3liz2ivjDYW4Tz5AD8SQKo+Pg1FhXl5tUODRCd7r7TASFnOYlaIF0oQUceM3KWPEdJUsfu7XgDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bea1beeaff3bc800e41a84f0e00ea29e60b3058d578ddec258f96282c0b79995","last_reissued_at":"2026-06-30T01:16:25.561027Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:16:25.561027Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Predicting Effects, Missing Distributions: Evaluating LLMs as Human Behavior Simulators in Operations Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Mingyang Zhao, Runze Zhang, Xiaowei Zhang","submitted_at":"2025-09-30T20:20:58Z","abstract_excerpt":"Large language models (LLMs) are increasingly used to simulate human behavior in business, economics, and the social sciences, offering a low-cost complement to laboratory experiments, field studies, and surveys. This paper evaluates how well LLMs replicate human behavior in operations management. Using nine published behavioral-operations experiments, we assess LLM performance along two dimensions: whether LLM-generated data reproduce the original hypothesis-test outcomes, and whether their full response distributions align with human data, measured by Wasserstein distance. We find that LLMs "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.03310","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/2510.03310/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":"2510.03310","created_at":"2026-06-30T01:16:25.561098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.03310v2","created_at":"2026-06-30T01:16:25.561098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.03310","created_at":"2026-06-30T01:16:25.561098+00:00"},{"alias_kind":"pith_short_12","alias_value":"X2Q352X7HPEA","created_at":"2026-06-30T01:16:25.561098+00:00"},{"alias_kind":"pith_short_16","alias_value":"X2Q352X7HPEABZA2","created_at":"2026-06-30T01:16:25.561098+00:00"},{"alias_kind":"pith_short_8","alias_value":"X2Q352X7","created_at":"2026-06-30T01:16:25.561098+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/X2Q352X7HPEABZA2QTYOADVCTZ","json":"https://pith.science/pith/X2Q352X7HPEABZA2QTYOADVCTZ.json","graph_json":"https://pith.science/api/pith-number/X2Q352X7HPEABZA2QTYOADVCTZ/graph.json","events_json":"https://pith.science/api/pith-number/X2Q352X7HPEABZA2QTYOADVCTZ/events.json","paper":"https://pith.science/paper/X2Q352X7"},"agent_actions":{"view_html":"https://pith.science/pith/X2Q352X7HPEABZA2QTYOADVCTZ","download_json":"https://pith.science/pith/X2Q352X7HPEABZA2QTYOADVCTZ.json","view_paper":"https://pith.science/paper/X2Q352X7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.03310&json=true","fetch_graph":"https://pith.science/api/pith-number/X2Q352X7HPEABZA2QTYOADVCTZ/graph.json","fetch_events":"https://pith.science/api/pith-number/X2Q352X7HPEABZA2QTYOADVCTZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X2Q352X7HPEABZA2QTYOADVCTZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X2Q352X7HPEABZA2QTYOADVCTZ/action/storage_attestation","attest_author":"https://pith.science/pith/X2Q352X7HPEABZA2QTYOADVCTZ/action/author_attestation","sign_citation":"https://pith.science/pith/X2Q352X7HPEABZA2QTYOADVCTZ/action/citation_signature","submit_replication":"https://pith.science/pith/X2Q352X7HPEABZA2QTYOADVCTZ/action/replication_record"}},"created_at":"2026-06-30T01:16:25.561098+00:00","updated_at":"2026-06-30T01:16:25.561098+00:00"}