{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CBR2F3ZW4Q6WANEAW5ZEXUXMA5","short_pith_number":"pith:CBR2F3ZW","schema_version":"1.0","canonical_sha256":"1063a2ef36e43d603480b7724bd2ec0779d6153b6547dd05d4059710ca6036aa","source":{"kind":"arxiv","id":"2504.21582","version":3},"attestation_state":"computed","paper":{"title":"MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Bo An, Cheng Deng, Haifeng Zhang, Jun Wang, Mengyue Yang, Qirui Mi, Xiangning Yu, Xu Chen, Zhiyu Zhao","submitted_at":"2025-04-30T12:41:51Z","abstract_excerpt":"Simulating collective decision-making involves more than aggregating individual behaviors; it emerges from dynamic interactions among individuals. While large language models (LLMs) offer strong potential for social simulation, achieving quantitative alignment with real-world data remains a key challenge. To bridge this gap, we propose the Mean-Field LLM (MF-LLM) framework, the first to incorporate mean field theory into LLM-based social simulation. MF-LLM models bidirectional interactions between individuals and the population through an iterative process, generating population signals to gui"},"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":"2504.21582","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2025-04-30T12:41:51Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2236b9fdd4342b5dfbd8bcbdbd81165d650619a0a9dbd32d6053e36233fbce9b","abstract_canon_sha256":"60d628ed06365d24cb420175ffc8e4adf08a76ba351184c3b43eb18ed25015c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:50.783664Z","signature_b64":"aNch2qqoXz3mW0tKhBSlEpnBzYcAe2sO6QzNnoKr63LvNgRSl7GTKrAfji+ONRuBTlrEg58cGlhxB/Gh0/OPAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1063a2ef36e43d603480b7724bd2ec0779d6153b6547dd05d4059710ca6036aa","last_reissued_at":"2026-07-05T11:34:50.783137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:50.783137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.MA","authors_text":"Bo An, Cheng Deng, Haifeng Zhang, Jun Wang, Mengyue Yang, Qirui Mi, Xiangning Yu, Xu Chen, Zhiyu Zhao","submitted_at":"2025-04-30T12:41:51Z","abstract_excerpt":"Simulating collective decision-making involves more than aggregating individual behaviors; it emerges from dynamic interactions among individuals. While large language models (LLMs) offer strong potential for social simulation, achieving quantitative alignment with real-world data remains a key challenge. To bridge this gap, we propose the Mean-Field LLM (MF-LLM) framework, the first to incorporate mean field theory into LLM-based social simulation. MF-LLM models bidirectional interactions between individuals and the population through an iterative process, generating population signals to gui"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.21582","kind":"arxiv","version":3},"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/2504.21582/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":"2504.21582","created_at":"2026-07-05T11:34:50.783185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.21582v3","created_at":"2026-07-05T11:34:50.783185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.21582","created_at":"2026-07-05T11:34:50.783185+00:00"},{"alias_kind":"pith_short_12","alias_value":"CBR2F3ZW4Q6W","created_at":"2026-07-05T11:34:50.783185+00:00"},{"alias_kind":"pith_short_16","alias_value":"CBR2F3ZW4Q6WANEA","created_at":"2026-07-05T11:34:50.783185+00:00"},{"alias_kind":"pith_short_8","alias_value":"CBR2F3ZW","created_at":"2026-07-05T11:34:50.783185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30258","citing_title":"EASE Configuration Facilitates A Reproducible Science of LLM Social Simulations","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18890","citing_title":"Stop Drawing Scientific Claims from LLM Social Simulations Without Robustness Audits","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06600","citing_title":"IntervenSim: Intervention-Aware Social Network Simulation for Opinion Dynamics","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CBR2F3ZW4Q6WANEAW5ZEXUXMA5","json":"https://pith.science/pith/CBR2F3ZW4Q6WANEAW5ZEXUXMA5.json","graph_json":"https://pith.science/api/pith-number/CBR2F3ZW4Q6WANEAW5ZEXUXMA5/graph.json","events_json":"https://pith.science/api/pith-number/CBR2F3ZW4Q6WANEAW5ZEXUXMA5/events.json","paper":"https://pith.science/paper/CBR2F3ZW"},"agent_actions":{"view_html":"https://pith.science/pith/CBR2F3ZW4Q6WANEAW5ZEXUXMA5","download_json":"https://pith.science/pith/CBR2F3ZW4Q6WANEAW5ZEXUXMA5.json","view_paper":"https://pith.science/paper/CBR2F3ZW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.21582&json=true","fetch_graph":"https://pith.science/api/pith-number/CBR2F3ZW4Q6WANEAW5ZEXUXMA5/graph.json","fetch_events":"https://pith.science/api/pith-number/CBR2F3ZW4Q6WANEAW5ZEXUXMA5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CBR2F3ZW4Q6WANEAW5ZEXUXMA5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CBR2F3ZW4Q6WANEAW5ZEXUXMA5/action/storage_attestation","attest_author":"https://pith.science/pith/CBR2F3ZW4Q6WANEAW5ZEXUXMA5/action/author_attestation","sign_citation":"https://pith.science/pith/CBR2F3ZW4Q6WANEAW5ZEXUXMA5/action/citation_signature","submit_replication":"https://pith.science/pith/CBR2F3ZW4Q6WANEAW5ZEXUXMA5/action/replication_record"}},"created_at":"2026-07-05T11:34:50.783185+00:00","updated_at":"2026-07-05T11:34:50.783185+00:00"}