{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H5VN6ASXKBNKPOWRLSGFW7ZIVX","short_pith_number":"pith:H5VN6ASX","schema_version":"1.0","canonical_sha256":"3f6adf0257505aa7bad15c8c5b7f28addd486b4c4a11d9be002990c556303a85","source":{"kind":"arxiv","id":"2412.12362","version":1},"attestation_state":"computed","paper":{"title":"How Different AI Chatbots Behave? Benchmarking Large Language Models in Behavioral Economics Games","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Lin Shi, Matthew O. Jackson, Qiaozhu Mei, Walter Yuan, Xiyuan Wang, Yiyao Liu, Yutong Xie, Zhuang Ma","submitted_at":"2024-12-16T21:25:45Z","abstract_excerpt":"The deployment of large language models (LLMs) in diverse applications requires a thorough understanding of their decision-making strategies and behavioral patterns. As a supplement to a recent study on the behavioral Turing test, this paper presents a comprehensive analysis of five leading LLM-based chatbot families as they navigate a series of behavioral economics games. By benchmarking these AI chatbots, we aim to uncover and document both common and distinct behavioral patterns across a range of scenarios. The findings provide valuable insights into the strategic preferences of each LLM, h"},"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":"2412.12362","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-16T21:25:45Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"aabdc1a68a1984132070c6e587f1b4f9af58c1d059b5e86aad71db2ad40302a3","abstract_canon_sha256":"f68a23803de54a7db7a9aef7c3ea52bec389fb96a36fab06b4cf93cb1f5e582c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:50:37.800040Z","signature_b64":"3VTujFPhYHv1RT27sg/8gY1JoKB0cW5OcSgRaUO6YFgr5IOc9jAvAk+vPfgL+6djrhBS3lALWe9L5mJzsO5VAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f6adf0257505aa7bad15c8c5b7f28addd486b4c4a11d9be002990c556303a85","last_reissued_at":"2026-07-05T09:50:37.799542Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:50:37.799542Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How Different AI Chatbots Behave? Benchmarking Large Language Models in Behavioral Economics Games","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Lin Shi, Matthew O. Jackson, Qiaozhu Mei, Walter Yuan, Xiyuan Wang, Yiyao Liu, Yutong Xie, Zhuang Ma","submitted_at":"2024-12-16T21:25:45Z","abstract_excerpt":"The deployment of large language models (LLMs) in diverse applications requires a thorough understanding of their decision-making strategies and behavioral patterns. As a supplement to a recent study on the behavioral Turing test, this paper presents a comprehensive analysis of five leading LLM-based chatbot families as they navigate a series of behavioral economics games. By benchmarking these AI chatbots, we aim to uncover and document both common and distinct behavioral patterns across a range of scenarios. The findings provide valuable insights into the strategic preferences of each LLM, h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.12362","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/2412.12362/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":"2412.12362","created_at":"2026-07-05T09:50:37.799597+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.12362v1","created_at":"2026-07-05T09:50:37.799597+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.12362","created_at":"2026-07-05T09:50:37.799597+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5VN6ASXKBNK","created_at":"2026-07-05T09:50:37.799597+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5VN6ASXKBNKPOWR","created_at":"2026-07-05T09:50:37.799597+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5VN6ASX","created_at":"2026-07-05T09:50:37.799597+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06366","citing_title":"AI Agent Behavioral Science","ref_index":171,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H5VN6ASXKBNKPOWRLSGFW7ZIVX","json":"https://pith.science/pith/H5VN6ASXKBNKPOWRLSGFW7ZIVX.json","graph_json":"https://pith.science/api/pith-number/H5VN6ASXKBNKPOWRLSGFW7ZIVX/graph.json","events_json":"https://pith.science/api/pith-number/H5VN6ASXKBNKPOWRLSGFW7ZIVX/events.json","paper":"https://pith.science/paper/H5VN6ASX"},"agent_actions":{"view_html":"https://pith.science/pith/H5VN6ASXKBNKPOWRLSGFW7ZIVX","download_json":"https://pith.science/pith/H5VN6ASXKBNKPOWRLSGFW7ZIVX.json","view_paper":"https://pith.science/paper/H5VN6ASX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.12362&json=true","fetch_graph":"https://pith.science/api/pith-number/H5VN6ASXKBNKPOWRLSGFW7ZIVX/graph.json","fetch_events":"https://pith.science/api/pith-number/H5VN6ASXKBNKPOWRLSGFW7ZIVX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5VN6ASXKBNKPOWRLSGFW7ZIVX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5VN6ASXKBNKPOWRLSGFW7ZIVX/action/storage_attestation","attest_author":"https://pith.science/pith/H5VN6ASXKBNKPOWRLSGFW7ZIVX/action/author_attestation","sign_citation":"https://pith.science/pith/H5VN6ASXKBNKPOWRLSGFW7ZIVX/action/citation_signature","submit_replication":"https://pith.science/pith/H5VN6ASXKBNKPOWRLSGFW7ZIVX/action/replication_record"}},"created_at":"2026-07-05T09:50:37.799597+00:00","updated_at":"2026-07-05T09:50:37.799597+00:00"}